Data acquisition method and device for life cycle list database

Abstract

The invention relates to a data collection method and device for a life cycle list database, and the method comprises the steps: carrying out the data retrieval of a data source and a preset life cycle list database according to a preset keyword combination, and obtaining a first retrieval data set and a second retrieval data set; respectively extracting the preprocessed data and the second retrieval data set according to keywords in a keyword dictionary; respectively determining a first corresponding relation and a second corresponding relation between the literature data containing the keywords and the life cycle evaluation stage based on the extraction result; determining a first environment influence value and a second environment influence value related to the first retrieval data set according to the first corresponding relation and the second corresponding relation; and under the condition that the difference value between the first environment influence value and the second environment influence value is smaller than a preset threshold value, merging the literature data containing keywords into the life cycle list database. According to the invention, representativeness, transparency, consistency, systematicness and traceability in a data acquisition process can be ensured.

Description

Technical Field

[0001] The present application relates to the technical field of life cycle assessment, and in particular to a data collection method and device for a life cycle inventory database. Background Art

[0002] The life cycle assessment method (LCA) can systematically quantify and optimize the material flow, energy flow and environmental effects of product production activities, and has become an internationally recognized essential tool for environmental management, sustainable development assessment and ecological design. Since China started late in the research and application of life cycle assessment, the life cycle impact assessment model and life cycle inventory database are still in the development stage. There are many problems in life cycle assessment research, such as lack of original evaluation methods and models, incomplete inventory data and over-reliance on foreign data. In the process of carrying out life cycle assessment or carbon footprint accounting of products, due to the limitations of data availability and usability, the use of background databases is inevitable. The use of databases can greatly reduce the threshold for enterprises to carry out product life cycle assessment / product carbon footprint accounting. In this case, in order to improve the accuracy, credibility and comparability of life cycle assessment / product carbon footprint accounting, it is necessary to ensure the data quality of background data, that is, the selected database needs to fit the actual production situation of specific products as much as possible.

[0003] The use of life cycle assessment (LCA) to disclose data related to the environmental impact of the entire life cycle of a product is currently the most systematic and detailed environmental footprint assessment method system in the world. As a data-intensive method, life cycle assessment requires the support of a large amount of basic data. It covers all links in the product production chain. Taking steel products as an example, it includes input and output materials and energy consumption information (materials, energy, water, chemicals, wastewater, waste gas, waste slag, etc.) related to mining, blast furnace ironmaking, converter steelmaking, steel manufacturing product processing, transportation, etc. By collecting and integrating this information, the environmental and social impact of steel products can be evaluated. However, due to the lack of experience of LCA researchers, lack of data collection equipment, large workload and low efficiency of data collection, the accumulation process of life cycle assessment related data is slow and the data quality is poor. Industry experts are usually required to identify and sort out the data of each process of steel smelting, and analyze whether the collected data is reasonable. For example, the coke ratio and blast furnace gas output for producing one ton of molten iron are relatively familiar to industry experts, but for general LCA analysts, it is relatively complicated. Based on the initial data collection and expert feedback, and data processing according to region, process, product, etc., representative data is formed to form the initial life cycle assessment process data set.

[0004] At present, China's domestic life cycle inventory database mainly relies on manual literature retrieval, research, and data collation, sorting, and entry. Generally, the carbon footprint accounting results of various materials, energy, and products in literature or reports published through public channels are collected and sorted into carbon emission factors to form a data set or database for use by users with background data needs. The accumulation cycle of database data volume is long and requires a lot of manpower and material resources. Although this type of data set or database can provide users with background data and realize the accounting of product carbon footprint or environmental footprint, due to the different life cycle assessment methods in the literature and the lack of unified standards, models, and structures, the data quality is poor, which is specifically reflected in:

[0005] Poor representativeness: Most of the data in the data set are obtained from literature. The real-life data used in the literature to conduct carbon footprint evaluation is usually obtained by researching a specific product of a specific company. It is not reasonable to use such data as the average data for the industry.

[0006] Opaque: The unit process data set, system boundaries, assumptions and trade-offs, model building methods, and life cycle environmental impact assessment (LCIA) methods used in the product model of carbon emission factor data are all opaque;

[0007] Inconsistency: Since the data sets come from many sources, and the background databases, modeling rules and LCIA methods used by data from different sources are often not exactly the same, there is a lack of consistency;

[0008] Unsystematic: The carbon emission factors in the data set are not generated based on a unified model system, in accordance with unified specifications and processes, and cannot be updated and iterated uniformly;

[0009] Poor traceability: Using this type of carbon emission factor to calculate the carbon footprint of a product cannot be traced back upstream, which is not conducive to conducting contribution analysis on the results and supporting the formulation of carbon reduction and emission reduction plans. Summary of the invention

[0010] In response to the problems existing in the prior art, the present application provides a data collection solution for a life cycle inventory database, which collects life cycle assessment method (LCA) and inventory database (LCI) data, and can effectively ensure the representativeness, transparency, consistency, systematicness and traceability of the data collection process.

[0011] According to a first aspect of the present application, a method for collecting data of a life cycle inventory database is provided, characterized in that it includes:

[0012] According to a preset keyword combination, data retrieval is performed on a data source and a preset life cycle inventory database respectively to obtain a first retrieval data set and a second retrieval data set;

[0013] Preprocessing the first search data set to obtain preprocessed data;

[0014] extracting the preprocessed data and the second search data set respectively according to the keywords in the keyword dictionary;

[0015] Determine, based on the extraction results, a first correspondence between the document data containing the keyword and the life cycle assessment stage and a second correspondence between the document data containing the keyword and the life cycle assessment stage;

[0016] Determine a first environmental impact value associated with the first search data set according to the first corresponding relationship;

[0017] Determining a second environmental impact value associated with the second search data set according to the second corresponding relationship; and

[0018] In a case where a difference between the first environmental impact value and the second environmental impact value is less than a preset threshold, the document data containing the keyword is incorporated into the life cycle inventory database.

[0019] According to a second aspect of the present application, a data collection device for a life cycle inventory database is provided, characterized in that it includes:

[0020] A retrieval module, used to perform data retrieval on a data source and a preset life cycle inventory database according to a preset keyword combination, to obtain a first retrieval data set and a second retrieval data set;

[0021] A preprocessing module, used for preprocessing the first search data set to obtain preprocessed data;

[0022] An extraction module, used for extracting the preprocessed data and the second search data set respectively according to the keywords in the keyword dictionary;

[0023] A first determination module, used to determine a first correspondence between the document data containing the keyword and the life cycle assessment stage and a second correspondence between the document data containing the keyword and the life cycle assessment stage based on the extraction result;

[0024] A second determining module, configured to determine a first environmental impact value associated with the first search data set according to the first corresponding relationship;

[0025] A third determining module, configured to determine a second environmental impact value associated with the second search data set according to the second corresponding relationship; and

[0026] The first incorporation module is configured to, when a difference between the first environmental impact value and the second environmental impact value is less than a preset threshold, incorporate the literature data containing the keyword into the life cycle inventory database.

[0027] According to a third aspect of the present application, an electronic device is provided, including:

[0028] Processor; and

[0029] A memory storing computer instructions, which, when executed by the processor, causes the processor to execute the method described in the first aspect.

[0030] According to a fourth aspect of the present application, a non-transitory computer storage medium is provided, storing a computer program, which, when executed by multiple processors, enables the processors to execute the method described in the first aspect.

[0031] According to the data collection method and device for the life cycle inventory database provided by this application, life cycle assessment methods and inventory data can be collected in batches, replacing manual data collection and expert review, improving data verification and review efficiency, thereby shortening the database construction cycle and reducing data collection costs. At the same time, through automated and intelligent data collection technology, the accuracy and reliability of data are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without exceeding the scope of protection required by the present application.

[0033] Figure 1 It is a flowchart of a data collection method for a life cycle inventory database according to an embodiment of the present application.

[0034] Figure 2 It is a schematic diagram of the four stages included in the life cycle assessment method framework.

[0035] Figure 3 It is a flowchart of a data collection method for a life cycle inventory database according to another embodiment of the present application.

[0036] Figure 4 It is a flow chart of a data collection method for a life cycle inventory database according to yet another embodiment of the present application.

[0037] Figure 5 It is a schematic diagram of a data collection device for a life cycle inventory database according to an embodiment of the present application.

[0038] Figure 6 It is a schematic diagram of a data collection device for a life cycle inventory database according to another embodiment of the present application.

[0039] Figure 7 It is a schematic diagram of a data collection device for a life cycle inventory database according to another embodiment of the present application.

[0040] Figure 8 It is a structural diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0042] In view of the problems of poor representativeness, opacity, inconsistency, unsystematicity and poor traceability in the process of establishing a life cycle inventory database in the prior art, this application proposes a data collection solution for a life cycle inventory database. Generally speaking, the solution includes the following processes: data collection, data preprocessing, data mining, comparative analysis, and data statistics and display. The solution provided in this application can collect life cycle assessment methods and inventory data in batches, replace manual data collection and expert review, improve data verification and audit efficiency, thereby shortening the database construction cycle and reducing data collection costs, and can effectively ensure the representativeness, transparency, consistency, systematicity and traceability of the data collection process.

[0043] According to one aspect of the present application, a method for collecting data for a life cycle inventory database is provided. Figure 1 FIG. 1 is a flow chart of a method for collecting data from a life cycle inventory database according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps.

[0044] Step S101 , performing data retrieval on a data source and a preset life cycle inventory database according to a preset keyword combination, to obtain a first retrieval data set and a second retrieval data set.

[0045] Web crawler technology can be used to automatically retrieve data from multiple data sources (such as professional databases, academic journals, corporate reports, etc.). According to a specific embodiment, a systematic literature search is performed on relevant LCA methods and data according to a preset keyword combination to collect a large number of documents related to life cycle assessment methods and data. The literature search scope covers electronic books, journals, conference papers, patents, dissertations, scientific and technological reports, product information, and other specific application case reports. For example, the preset keyword combination can be "iron and steel" AND "emission factor" AND "life cycle assessment" OR "LCA", where the keywords can be replaced or added as dynamic, static, forecast, field data, background data, process, location, product name, time, attributional, consequential, etc. The preset keyword combination is not limited to the above examples and can be customized according to the life cycle assessment method and data type to be collected.

[0046] According to some embodiments, in the process of searching, each keyword is assigned the same or different importance weights. The limitations of text mining in data mining are mainly related to the original data or, rather than being limited to data related to technology or algorithms. Since the search process is only used for multiple keyword counts, the analysis of the entire context may be missed. In order to avoid this problem, it is necessary to screen and pre-process the previous documents. In addition, since the counting combination model does not consider the length of the text, longer texts have more statistical chances to produce a larger number of repeated keywords. Therefore, the text data source recommended by this application is a paper with a specified number of pages published in a scientific journal.

[0047] In this way, the first search data set is obtained after the data source is collected. For a preset life cycle inventory database, such as the currently existing life cycle inventory database, the same collection method as the data source is adopted to collect data from the preset life cycle inventory database according to the preset keyword combination to obtain the second search data set. If it does not currently exist in the preset life cycle inventory database, the above collection process is performed again after the first batch of data collected by file mining.

[0048] Step S102: preprocess the first search data set to obtain preprocessed data.

[0049] According to some embodiments, natural language processing (NLP) technology is applied to pre-process the collected text data, including cleaning, word segmentation, entity recognition, etc.

[0050] According to a specific embodiment, the collection was performed according to the embodiment shown in step S101, and a total of 915 papers were collected. The first step is to use the reference manager to automatically delete duplicates, which resulted in the exclusion of 220 papers. Of the remaining 695 articles, the second step is to read the title of the document, and articles that are not related to LCA or from journals that do not cover such topics are further deleted. After the second round of screening, 135 articles remain. The third step is to read the abstract of each article and retain the literature that focuses on LCA (whether it is a review paper, case study or other literature). After three rounds of screening, 56 articles remain for text mining. The size of the final article sample is still statistically significant to ensure the quality of text mining analysis.

[0051] According to another specific embodiment, the text data set is cleaned and tokenized. Due to the differences in language style and grammar of different documents, the initial text needs to be preprocessed to unify different forms of terms with the same meaning. For example, the Chinese "life cycle assessment" and "life cycle assessment", the English "ex-post (after the event)" and "expost (after the event)" should be counted as the same word. If there is no preprocessing, the text mining tool will calculate each term separately. In addition, the capitalization (English) is unified, and references, numbers, uniform resource locators URLs, special characters, and a list of stop words (such as articles, prepositions, pronouns, conjunctions, etc.) are deleted. Abbreviations with all uppercase characters are retained. Cleaning and tokenization can be performed using the open source R language text mining tool Quanteda package.

[0052] The text data of life cycle assessment literature is cleaned and according to the requirements of life cycle assessment method, the user's complete field data and referenced background data are obtained, and the obtained data will be stored in the background database.

[0053] Step S103, extracting the preprocessed data and the second search data set respectively according to the keywords in the keyword dictionary;

[0054] Step S104 : determining a first correspondence between the document data containing the keyword and the life cycle assessment stage and a second correspondence between the document data containing the keyword and the life cycle assessment stage based on the extraction result.

[0055] According to some embodiments, a keyword dictionary is first established. Users create keyword and synonym dictionaries based on their own work needs, as shown in Table 1. It should be noted that some keywords in English may miss their ends. This is because some suffixes are deleted during preprocessing (for example, Conseq. represents the result). The ends of some other keywords are not completely deleted (for example, Consequential). All keywords that reference these methods should be unique to avoid duplication.

[0056] Table 1

[0057]

[0058] According to some embodiments, the open source R language text mining Quanteda package is used to extract keywords, and the statistical extension model of the tool can also be used to perform internal error testing based on automatic asymptotic standard error verification. Then, the keywords in the paper are counted according to the keyword dictionary and the collected results. The number of counts is the same as the number of keywords and synonyms found in a single paper. Keywords are ranked by statistical inference methods such as the Wald z-statistic. Keyword co-occurrence refers to writing two or three unique words within a distance of four words, and creating a co-occurrence matrix to calculate the distance between two unique words. The life cycle assessment stage includes the goals and scope G&S stage, the life cycle inventory LCI stage, the life cycle impact assessment LCIA stage and the results interpretation stage. Figure 2 is a schematic diagram of the four phases of the LCA method framework. Each LCA phase has a corresponding definition, which allows to distinguish specific phases and / or understand specific elements of the LCA phase in more detail. For example, the G&S phase defines the selection of product categories or system boundaries; the LCI phase defines the semantic areas of "input" and "modeling" and the modeling part. In summary, the terms used in the definitions or terms that often appear together can be analyzed and associated with the corresponding phases belonging to the LCA framework.

[0059] Table 2 shows the keywords used for extraction, the proportion of literature data containing the keywords in the four stages, and the LCA stage to which the literature data containing the keywords belong.

[0060] Table 2

[0061]

[0062] According to some embodiments, according to the definitions corresponding to each of the four stages, the proportion of literature data containing the keyword belonging to the four stages is determined. For example, as shown in Table 2, the literature data containing the keyword "Attributional attribution" in the goal and scope G&S stage, the life cycle inventory LCI stage, the life cycle impact assessment LCIA stage and the result interpretation stage are 11%, 27%, 7% and 0%, respectively. The highest proportion is the life cycle inventory LCI. The literature data containing "Attributional attribution" is determined to be 27% corresponding to the stage, namely, the life cycle impact assessment LCIA.

[0063] In this way, a first correspondence between the literature data containing the keyword and the life cycle assessment stage is determined based on the extraction result, including: determining the proportion of the literature data containing the keyword belonging to different stages according to the corresponding definitions of the objective and scope stage, the life cycle inventory stage, the life cycle impact assessment stage and the result interpretation stage; and then, determining the stage corresponding to the highest proportion as the life cycle assessment stage to which the literature data containing the keyword belongs.

[0064] In the same way, the second search data set corresponding to the preset life cycle inventory database is extracted, and the relationship between the literature data containing the keyword and the life cycle assessment stage is determined based on the extraction result.

[0065] Step S105, determining a first environmental impact value associated with the first search data set according to the first corresponding relationship;

[0066] Step S106: determining a second environmental impact value associated with the second search data set according to the second corresponding relationship.

[0067] The four stages of the life cycle assessment (LCA) method can be described by mathematical formulas. Usually, the environmental impact (vector r) of a product or service LCA result can be calculated by formula (1):

[0068] r=M×P×I -1 ×f

[0069] Among them, M is the characteristic factor matrix (LCIA part), which is related to the environmental assessment method. After the environmental assessment method is determined, M is determined; P is the environmental impact matrix of each unit process emission of the product or service system (LCI); M and P are related to the life cycle impact assessment LCIA; I is the technical matrix representing the inter-process flows required for the functions of the product or service system (product system), which is related to the life cycle inventory LCI; f is the external supply (or final demand) vector, representing the functional unit, and its dimensions are related to the defined goal and scope set (G&S).

[0070] After determining the first correspondence between the literature data containing the keyword and the life cycle assessment stage and the second correspondence between the literature data containing the keyword and the life cycle assessment stage, that is, after determining the life cycle assessment stage to which the literature data containing the keyword in the data source and the preset life cycle inventory database belongs, the respective environmental impact values ​​(calculated r value) are calculated according to formula (1), that is, the first environmental impact value and the second environmental impact value.

[0071] Step S107: when the difference between the first environmental impact value and the second environmental impact value is less than a preset threshold, the document data containing the keyword is incorporated into the life cycle inventory database.

[0072] According to a specific embodiment, a threshold value, such as 10%, can be set. When the r vector difference between the first environmental impact value and the second environmental impact value is less than 10%, the literature data containing the keyword is incorporated into the life cycle inventory database. When the r vector difference between the two is not less than 10%, it is considered that there is an error in the literature data or database data, and external intervention (such as LCA experts or industry experts) is required to review the data results and determine whether to include them in the life cycle inventory database. Table 3 shows four examples of comparisons between the first environmental impact value and the second environmental impact value and whether to include them in the database:

[0073] Table 3

[0074]

[0075]

[0076] According to some embodiments, after completing text mining to obtain literature data, other keyword "combinations" can be selected from the keyword dictionary for multi-word filtering. After filtering, the results are selectively analyzed and irrelevant multiple keywords are excluded, especially overly general keywords such as method, research, environment, framework, etc.

[0077] When the filtered documents are associated with the LCA stage, according to some embodiments, such documents will be further extracted to extract the final data results, and detailed unit process data will be classified, such as all inputs (raw materials, energy) and outputs (products, emissions, waste, etc.) of the process. That is, the document data is searched according to keywords related to the unit process data, and the retrieved unit process data is classified in the life cycle inventory database. According to other embodiments, data processing such as classification, aggregation and weighted averaging are performed according to keywords related to representative data, such as country or region, process, product name, etc., to form representative data, that is, the document data is searched according to keywords related to the representative data, and the retrieved representative data is classified in the life cycle inventory database.

[0078] In this way, in the process of incorporating literature data into the life cycle inventory database, unit process data and representative data related to the literature data will also be classified, for example, listed in the life cycle inventory database in the form of a list.

[0079] Figure 3 is a flow chart of a data collection method for a life cycle inventory database according to another embodiment of the present application. Figure 1 compared to, Figure 3 Steps S301 to S307 of the method shown are Figure 1 The steps S101 to S107 are the same as above, except that: Figure 3 The method shown also includes:

[0080] Step S308, when the difference between the first environmental impact value and the second environmental impact value is not less than the preset threshold, obtaining an external judgment result on the document data containing the keyword; and

[0081] Step S309: When the external judgment result determines that the data quality of the document data containing the keyword meets the requirements, the document data containing the keyword is incorporated into the life cycle inventory database.

[0082] As described above, when the r vector difference between the first environmental impact value and the second environmental impact value is not less than a preset threshold (e.g., 10%), it is considered that there is an error in the literature data or database data, and external intervention (e.g., LCA experts or industry experts) is required to review the data results and determine whether to include them in the life cycle inventory database. After external intervention, it is determined whether to incorporate the literature data into the life cycle inventory database. If the data quality of the literature data containing the keyword meets the requirements after receiving the external judgment result, the literature data will be incorporated into the life cycle inventory database, otherwise it will not be incorporated.

[0083] Figure 4 is a flow chart of a data collection method for a life cycle inventory database according to another embodiment of the present application. Figure 1 compared to, Figure 4 Steps S401 to S407 of the method shown are Figure 1 The steps S101 to S107 are the same as above, except that: Figure 4 The method shown also includes:

[0084] Step S408, displaying the preset keyword combination, the first corresponding relationship, the second corresponding relationship, the first environmental impact value, the second environmental impact value, and the literature data information incorporated into the life cycle inventory database during the collection process.

[0085] After completing the collection of literature data, the information involved in the collection process will be displayed, including preset keyword combinations, first corresponding relationships, second corresponding relationships, first environmental impact values, second environmental impact values, and literature data information incorporated into the life cycle inventory database, such as unit process data and representative data.

[0086] According to another aspect of the present application, a data collection device for a life cycle inventory database is provided. Figure 5 Schematic diagram of a data collection device for a life cycle inventory database according to an embodiment of the present application. Figure 5As shown, the device includes a retrieval module 501, a preprocessing module 502, an extraction module 503, a first determination module 504, a second determination module 505, a third determination module 506 and a first incorporation module 507. Among them, the retrieval module 501 is used to perform data retrieval on the data source and the preset life cycle inventory database respectively according to the preset keyword combination to obtain the first retrieval data set and the second retrieval data set; the preprocessing module 502 is used to preprocess the first retrieval data set to obtain the preprocessed data; the extraction module 503 is used to extract the preprocessed data and the second retrieval data set respectively according to the keywords in the keyword dictionary; the first determination module 504 is used to determine the first correspondence between the document data containing the keyword and the life cycle assessment stage and the second correspondence between the document data containing the keyword and the life cycle assessment stage based on the extraction result; the second determination module 505 is used to determine the first environmental impact value related to the first retrieval data set according to the first correspondence; the third determination module 506 is used to determine the second environmental impact value related to the second retrieval data set according to the second correspondence; the first incorporation module 507 is used to incorporate the document data containing the keyword into the life cycle inventory database when the difference between the first environmental impact value and the second environmental impact value is less than a preset threshold.

[0087] According to some embodiments, the life cycle assessment phase includes a goal and scope phase, a life cycle inventory phase, a life cycle impact assessment phase, and a result interpretation phase. The first determination module 504 may be used to:

[0088] According to the definitions corresponding to the four stages, determining the proportion of the document data containing the keyword belonging to the four stages; and

[0089] The stage corresponding to the highest proportion is determined as the life cycle assessment stage to which the literature data containing the keyword belongs.

[0090] According to some embodiments, the first incorporation module 507 may be used to:

[0091] Retrieving the literature data according to keywords related to unit process data, and classifying the retrieved unit process data in the life cycle inventory database; and / or

[0092] The literature data is retrieved according to keywords related to the representative data, and the retrieved representative data is classified in the life cycle inventory database.

[0093] Figure 6 Schematic diagram of a data collection device for a life cycle inventory database according to another embodiment of the present application. Figure 5 compared to, Figure 6 Modules 601 to 607 of the device shown are Figure 5 Modules 501 to 507 are the same except that Figure 6 The device shown also includes:

[0094] An acquisition module 608 is configured to acquire an external judgment result of the document data containing the keyword when the difference between the first environmental impact value and the second environmental impact value is not less than the preset threshold; and

[0095] The second incorporation module 609 is configured to, if the external judgment result determines that the data quality of the document data containing the keyword meets the requirements, incorporate the document data containing the keyword into the life cycle inventory database.

[0096] Figure 7 Schematic diagram of a data collection device for a life cycle inventory database according to another embodiment of the present application. Figure 5 compared to, Figure 7 Modules 701 to 707 of the device shown are Figure 5 Modules 501 to 507 are the same except that Figure 7 The device shown also includes:

[0097] The display module 708 is used to display the preset keyword combination, the first corresponding relationship, the second corresponding relationship, the first environmental impact value, the second environmental impact value and the literature data information incorporated into the life cycle inventory database during the collection process.

[0098] The improvements and beneficial effects of the data collection scheme of the life cycle inventory database in the construction of life cycle databases in various industries (including the steel industry) include the following aspects:

[0099] 1. Automated data collection technology: By using technologies such as machine learning and natural language processing, the automated collection and analysis of various data sources such as web pages, documents, and images related to life cycle assessment methods and data can be achieved, thereby improving the efficiency and accuracy of data collection.

[0100] 2. Combination of text mining and life cycle assessment (LCA): Text mining technology can help analyze and process large amounts of unstructured data, such as technical reports, environmental impact assessment documents, etc., to more comprehensively evaluate the environmental impact of steel products throughout their life cycle.

[0101] 3. Intelligence of data collection system: The data collection system achieves self-optimization and autonomous learning through intelligent technologies, such as artificial intelligence and machine learning, to improve the comprehensiveness and real-time nature of data collection.

[0102] 4. Integration of cloud computing and edge computing: Through the combination of cloud computing and edge computing, the data acquisition system can quickly transmit and analyze massive data in real time, break geographical restrictions, and improve the breadth and depth of data collection.

[0103] 5. Privacy protection and compliant collection: During the data collection process, we focus on personal privacy protection and compliant collection, and apply technologies such as differential privacy and homomorphic encryption to ensure data security and compliance.

[0104] Thus, the benefits brought by the solution of this application include at least:

[0105] 1. Improve data quality: Improve data accuracy and reliability through automated and intelligent data collection technology.

[0106] 2. Enhanced real-time performance: The improvement of IoT technology and real-time data transmission capabilities makes data collection more timely, which helps to quickly respond to market and production changes.

[0107] 3. Optimize decision support: Combined with the life cycle assessment method of text mining, it provides steel companies with a more comprehensive product environmental impact assessment to support the company's green manufacturing and sustainable development.

[0108] 4. Reduce costs: Automated and intelligent data collection reduces the cost and time of manual collection.

[0109] 5. Improve security: The application of privacy protection and compliance collection technology improves the security of data collection and reduces the risk of data leakage and abuse.

[0110] 6. Support innovation: Through in-depth analysis of the collected data, new business opportunities and innovations can be discovered, promoting technological progress and product innovation in the steel industry.

[0111] In summary, the application of the data collection solution of the life cycle inventory database in the steel industry not only improves the efficiency and quality of data collection, but also provides strong support for decision-making support, environmental protection and innovative development of steel enterprises.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical connection or other forms.

[0115] See also Figure 8 , Figure 8 An electronic device is provided, comprising a processor and a memory. The memory stores computer instructions, and when the computer instructions are executed by the processor, the processor executes the computer instructions to achieve the following Figure 1 , Figure 3 and Figure 4 The method and refinement scheme shown.

[0116] It should be understood that the above device embodiments are only illustrative, and the device disclosed in the present invention can also be implemented in other ways. For example, the division of units / modules described in the above embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0117] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present invention may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0118] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not otherwise specified, the processor or chip may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not otherwise specified, the on-chip cache, the off-chip memory, and the memory may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0119] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer electronic device (which can be a personal computer, a server or a network electronic device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0120] The present application also provides a non-transitory computer storage medium storing a computer program. When the computer program is executed by a plurality of processors, the processors execute the following Figure 1 , Figure 3 and Figure 4 The method and refinement scheme shown.

[0121] The embodiments of the present application are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. At the same time, changes or deformations made by those skilled in the art based on the ideas of the present application, the specific implementation methods and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A data collection method for a life cycle inventory database, characterized in that: include: According to a preset keyword combination, data retrieval is performed on a data source and a preset life cycle inventory database respectively to obtain a first retrieval data set and a second retrieval data set; Preprocessing the first search data set to obtain preprocessed data; extracting the preprocessed data and the second search data set respectively according to the keywords in the keyword dictionary; Determine, based on the extraction results, a first correspondence between the document data containing the keyword and the life cycle assessment stage and a second correspondence between the document data containing the keyword and the life cycle assessment stage; Determine a first environmental impact value associated with the first search data set according to the first corresponding relationship; Determine a second environmental impact value associated with the second search data set according to the second corresponding relationship; as well as In a case where a difference between the first environmental impact value and the second environmental impact value is less than a preset threshold, the document data containing the keyword is incorporated into the life cycle inventory database.

2. The method according to claim 1, characterized in that The life cycle assessment phase includes a target and scope phase, a life cycle inventory phase, a life cycle impact assessment phase, and a result interpretation phase. The first corresponding relationship between the literature data containing the keyword and the life cycle assessment phase is determined based on the extraction result, including: Determine the proportion of literature data containing the keyword belonging to different stages according to the corresponding definitions of the objective and scope stage, life cycle inventory stage, life cycle impact assessment stage and results interpretation stage; and The stage corresponding to the highest proportion is determined as the life cycle assessment stage to which the literature data containing the keyword belongs.

3. The method according to claim 1, characterized in that Incorporating literature data containing the keywords into the life cycle inventory database includes: The literature data is retrieved according to keywords related to the unit process data, and the retrieved unit process data is classified in the life cycle inventory database.

4. The method according to claim 3, characterized in that Incorporating literature data containing the keywords into the life cycle inventory database further includes: The literature data is retrieved according to keywords related to the representative data, and the retrieved representative data is classified in the life cycle inventory database.

5. The method according to any one of claims 1 to 4, characterized in that: Also includes: When the difference between the first environmental impact value and the second environmental impact value is not less than the preset threshold, obtaining an external judgment result on the document data containing the keyword; as well as When the external judgment result determines that the data quality of the document data containing the keyword meets the requirements, the document data containing the keyword is incorporated into the life cycle inventory database.

6. The method according to any one of claims 1 to 4, characterized in that: Also includes: The preset keyword combination, the first corresponding relationship, the second corresponding relationship, the first environmental impact value, the second environmental impact value and the literature data information incorporated into the life cycle inventory database during the collection process are displayed.

7. The method according to any one of claims 1 to 4, characterized in that Preprocessing the first search data set to obtain preprocessed data includes: The first search data set is cleaned, segmented and entity recognized to obtain the preprocessed data.

8. A data collection device for a life cycle inventory database, characterized in that: include: A retrieval module, used to perform data retrieval on a data source and a preset life cycle inventory database according to a preset keyword combination, to obtain a first retrieval data set and a second retrieval data set; A preprocessing module, used for preprocessing the first search data set to obtain preprocessed data; An extraction module, used for extracting the preprocessed data and the second search data set respectively according to the keywords in the keyword dictionary; A first determination module, used to determine a first correspondence between the document data containing the keyword and the life cycle assessment stage and a second correspondence between the document data containing the keyword and the life cycle assessment stage based on the extraction result; A second determining module, configured to determine a first environmental impact value associated with the first search data set according to the first corresponding relationship; A third determining module, configured to determine a second environmental impact value associated with the second search data set according to the second corresponding relationship; as well as The first incorporation module is configured to, when a difference between the first environmental impact value and the second environmental impact value is less than a preset threshold, incorporate the literature data containing the keyword into the life cycle inventory database.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images