Electroplating site soil optimal control pollution source identification method and system

Abstract

The present invention discloses a method and system for identifying optimally controlled pollution sources in the soil of an electroplating site, and belongs to the technical field of data mining. The method comprises the following steps: inputting a company name and an electroplating process into an input module, and generating a survey scope based on the company name; a search module obtains historical pollution information based on the survey scope, and sends the information to an analysis module; the analysis module obtains a first pollutant element based on the electroplating process and a process comparison table; the analysis module analyzes the historical pollution information to obtain a second pollutant element, and sends the first pollutant element and the second pollutant element as electroplating characteristic pollutants to a recommendation module; the recommendation module uses the required elements and electroplating characteristic pollutants as preliminary screening pollution sources, and a user collects and analyzes the preliminary screening pollution sources to identify optimally controlled pollution sources, and finally calculates the size of a source strength assessment index to assess the intensity of soil pollution sources in the electroplating site; the present invention introduces historical pollution information to identify optimally controlled pollution sources, thereby making subsequent identification results more comprehensive.

Description

Technical Field

[0001] The present invention belongs to the technical field of data mining, and in particular relates to a method and system for identifying optimally controlled pollution sources in soil of electroplating sites. Background Art

[0002] A large amount of chemicals containing heavy metals and other harmful substances are used in the electroplating process. If not properly treated, these substances may enter the soil through wastewater, waste gas or solid waste, causing pollution to the soil environment, and may eventually pose a threat to human health through the food chain. Therefore, it is necessary to regularly test the soil in and around electroplating plants for pollution.

[0003] In the prior art, the priority controlled pollutant sources are generally obtained by analyzing the information of the raw and auxiliary materials, products, and three wastes produced by the enterprise. For example, the Chinese patent application document with publication number CN112990717A discloses a method for evaluating the pollution source strength of an electroplating site. The method first constructs a source strength evaluation index candidate index library, and then optimizes and analyzes the indicators of the candidate index library in combination with the characteristics of the actual research object, so as to obtain the priority controlled pollutant sources; for example, the Chinese patent application document with publication number CN116341918A discloses a method, device and computer equipment for identifying industry characteristic pollutants. The method first obtains soil pollutant detection information obtained by detecting sites corresponding to multiple enterprises under the target industry, and the soil pollutant detection information includes the detection results corresponding to each target detection pollutant; according to the soil pollutant detection information, the number of enterprises, and the risk indicators corresponding to each target detection pollutant, the detection rate and the exceedance rate of each target detection pollutant are determined; based on the target detection pollutants whose detection rate or exceedance rate is higher than the preset threshold, and the characteristic information of each enterprise, the characteristic pollutants of the target industry are determined.

[0004] Both of the above-mentioned existing technologies set priority screening targets based on the company's situation before testing, without taking into account historical pollution conditions, which will cause incomplete identification results. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method and system for identifying optimally controlled pollution sources of soil in electroplating sites to solve the problems in the prior art.

[0006] In order to achieve the above-mentioned purpose of the invention, the present invention proposes a method for identifying the optimal pollution source of the soil in an electroplating site, comprising:

[0007] Entering the company name and the electroplating process used by the company in the input module, generating a survey scope based on the company name, the input module sending the electroplating process to the analysis module, and sending the survey scope to the search module;

[0008] The search module obtains a variety of historical pollution information of the survey scope based on the survey scope, and sends the historical pollution information to the analysis module;

[0009] The analysis module is provided with a process comparison table, which includes the correspondence between the electroplating process and the pollutant elements, and the first pollutant element generated by the enterprise production is obtained based on the electroplating process and the process comparison table;

[0010] The analysis module analyzes the historical pollution information to obtain the second pollution element generated when each historical pollution information occurs, and the analysis module sends the first pollution element and the second pollution element as electroplating characteristic pollutants to the recommendation module;

[0011] The recommendation module is provided with a plurality of mandatory elements. The recommendation module recommends the mandatory elements and the electroplating characteristic pollutants as preliminary screening pollution sources to the user. The user collects and analyzes the preliminary screening pollution sources, and identifies the preliminary screening pollution sources exceeding the screening value as priority control pollution sources. The evaluation module directly evaluates the intensity of the soil pollution source in the electroplating site as strong.

[0012] If all the initially screened pollution sources do not exceed the screening threshold, a source strength assessment index system is constructed in the assessment module, a source strength assessment index is calculated based on the source strength assessment index system, and the intensity of soil pollution sources in the electroplating site is assessed according to the size of the source strength assessment index.

[0013] Furthermore, obtaining the historical pollution information includes the following steps:

[0014] Based on the survey scope, corresponding location information is determined, the location information includes administrative information and geographic information, a first search statement corresponding to each type of historical pollution information is generated through the location information, each of the first search statements is used to search, and a first search result corresponding to each of the first search statements is obtained, the first search result includes multiple result texts, the result texts are split into multiple subject blocks, target blocks related to the first search statement are extracted from the subject blocks, and the target blocks extracted from the multiple result texts are summarized and analyzed to obtain the historical pollution information.

[0015] Furthermore, splitting the result text into multiple subject blocks comprises the following steps:

[0016] Splitting the result text into multiple independent sentences, numbering the independent sentences from 1 to N according to the order of appearance in the result text, setting a lower limit and an upper limit, taking the independent sentence numbered 1 as the starting point, dividing the independent sentences of the lower limit into a first language block, and dividing the independent sentences other than the first language block into a second language block;

[0017] Starting from the independent sentence numbered 2, the lower limit number of independent sentences are re-divided into the first language block, and the independent sentences before and after the first language block are respectively divided into the second language block and the third language block, starting from the independent sentence numbered 3, repeating this step until the independent sentence numbered N is divided into the first language block, so as to complete the traversal and division of the result text using the lower limit number;

[0018] Add 1 to the lower limit to obtain the advanced number, use the advanced number to traverse and divide the result text, and after the traversal is completed, add 1 to the advanced number again, and repeat this step until the advanced value reaches the upper limit.

[0019] Furthermore, extracting the target language chunk from the subject language chunk includes the following steps:

[0020] Keywords are extracted from the first search statement, and scores of the first language block, the second language block, or the third language block are calculated based on a first formula, where the first formula is: , wherein P1 is the number of the independent sentences included in the first language block, the second language block or the third language block, P2 is the number of the keywords included in the first language block, the second language block or the third language block, X is a preset value, and the subject language block with the highest score is used as the target language block.

[0021] Furthermore, summarizing and analyzing the target language block includes the following steps:

[0022] The target language blocks from different result texts are compared in pairs to obtain multiple similarities. When comparing, the similarity L of two target language blocks is calculated based on a second formula. The second formula is: , where D is the number of identical characters in the two target language blocks, a and b are the number of characters in the two target language blocks respectively, and MAX (a, b) returns the larger value of a or b;

[0023] A summary template is set, the summary template includes a time description, a location description and a reason description, and if all the calculated similarities are greater than a first threshold, one of the target language blocks is selected, and corresponding information is extracted from it and filled into the summary template to complete the summary analysis of the target language block. Further, obtaining the second contamination element includes the following steps:

[0024] A second search statement is generated based on the historical pollution information, the second search statement is used to search to obtain a second search result, a detection field is set, and an element name located after the detection field is extracted from the result text of the second search result as the second pollution element.

[0025] Furthermore, a first database and a second database are set, and after the second search statement is generated, the second search statement is preferentially used to search in the first database, and if the second search result is not obtained, the second database is then used to search.

[0026] Furthermore, the historical pollution information includes historical landfill information, historical pollution accident information, historical groundwater pollution information and historical layout information of pollutant auxiliary facilities.

[0027] Furthermore, the required elements include arsenic, cadmium, hexavalent chromium, copper, lead, mercury, nickel, cyanide and petroleum hydrocarbons.

[0028] The present invention also provides a system for identifying optimally controlled pollution sources in the soil of an electroplating site, which is used to implement the above-mentioned method for identifying optimally controlled pollution sources in the soil of an electroplating site, and the system comprises:

[0029] An input module, the input module is used to input the company name and the electroplating process used by the company, generate a survey scope based on the company name, and send the electroplating process to the analysis module and send the survey scope to the search module;

[0030] A search module, which searches based on the survey scope to obtain a variety of historical pollution information within the survey scope, and sends the historical pollution information to the analysis module;

[0031] An analysis module is provided with a process comparison table, the process comparison table includes a correspondence between the electroplating process and the pollutant elements, obtains a first pollutant element generated by the enterprise production based on the electroplating process and the process comparison table, analyzes the historical pollution information, obtains a second pollutant element generated when each historical pollution information occurs, and the analysis module sends the first pollutant element and the second pollutant element as electroplating characteristic pollutants to the recommendation module;

[0032] A recommendation module is provided with a plurality of required test elements. The recommendation module recommends the required test elements and the electroplating characteristic pollutants as preliminary screening pollution sources to the user. The user collects and analyzes the preliminary screening pollution sources and identifies the preliminary screening pollution sources that exceed the screening value as priority control pollution sources;

[0033] The evaluation module directly evaluates the intensity of the soil pollution source in the electroplating site as strong if there are any initially screened pollution sources that exceed the screening value. If all the initially screened pollution sources do not exceed the screening threshold, a source strength evaluation index system is constructed in the evaluation module, and a source strength evaluation index is calculated based on the source strength evaluation index system. The intensity of the soil pollution source in the electroplating site is evaluated according to the size of the source strength evaluation index.

[0034] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0035] In the present invention, after the relevant personnel input the company name through the input module, the system can automatically determine the location information of the company based on the company name, generate the investigation scope based on the location information, and search on the Internet based on the investigation scope to determine whether there is any historical pollution information within the investigation scope and what the historical pollution information is; then, based on the production process used by the company and the historical pollution information, determine which polluting elements may exist, and the relevant personnel analyze these elements after collecting the soil to obtain more comprehensive analysis results; the present invention introduces historical pollution information during the investigation process, so that in the subsequent investigation process, not only the production level of the enterprise is targeted, but also the historical pollution level is paid attention to, ensuring that no pollution sources are missed. After introducing historical pollution information, the system can also automatically analyze and recommend suitable investigation objects, thereby greatly reducing the data collection time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of the steps of the method for identifying the optimal pollution source of the electroplating site soil of the present invention;

[0037] Figure 2 It is a structural schematic diagram of the soil pollution source identification system for electroplating sites of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0039] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0040] First, the overall process of determining the priority pollution sources of the present invention is introduced. The identification of priority pollution sources in the electroplating site soil is intended to accurately identify the pollution sources that pose a major threat to the soil environment during electroplating activities. When identifying, data collection is first carried out. For example, according to the electroplating production process of the site, the pollutants in the electroplating site are compared, and a preliminary analysis is conducted to form a preliminary screening list of priority pollutants for electroplating. Then, a comprehensive analysis is conducted on the raw and auxiliary materials of the electroplating enterprise to determine the characteristic pollutants of electroplating. After that, soil sampling is carried out. The soil sampling process includes procedures such as sampling points, sampling methods, sample preservation and circulation, sample analysis, quality targets and quality control, and finally data analysis is carried out.

[0041] In principle, only key areas are sampled and surveyed during soil sampling. Generally, no less than two sampling areas should be selected. In principle, at least two soil sampling points should be set up in each sampling area, which can be adjusted appropriately according to the actual situation such as the size of the sampling area and the distribution of pollutants. For closed and relocated enterprises, soil sampling points should be determined without causing safety hazards or secondary pollution (for example, the drilling process may cause explosions, collapses, penetration of pipelines or impermeable layers, etc.). For enterprises in production, soil sampling points should be determined without affecting the normal production of the enterprise and without causing safety hazards or secondary pollution (for example, the drilling process may cause explosions, collapses, penetration of pipelines or impermeable layers, etc.); if the selected sampling location does not have sampling conditions on site, the sampling location should be selected nearby in the downstream direction of pollutant migration.

[0042] For sampling depth, the thickness of the non-soil hardened layer on the surface should be deducted. In principle, 0~0.5 m surface soil samples should be collected. Soil sample collection is generally carried out by excavation, generally using simple tools such as shovels, spades and bamboo strips, and drilling sampling can also be carried out; if there are underground facilities such as underground tanks, troughs, and water storage tanks, in addition to taking the surface soil, a soil sample should be taken at least 3m below the bottom of the underground tanks, troughs, and water storage tanks; if there are underground facilities such as underground pipelines and ditches, in addition to taking the surface soil, a soil sample should be taken at least 2m below the bottom of the underground pipelines and ditches.

[0043] After obtaining the soil samples, chemical analysis is carried out to obtain the values ​​of various pollutant elements, which are compared with the screening values. The pollutant elements that are greater than the screening values ​​are set as priority pollution sources.

[0044] The present invention is applied to the process of collecting enterprise production data, and aims to reduce the workload of investigators in the process of data collection.

[0045] Specifically, Figure 1 As shown, a method for identifying optimally controlled pollution sources of soil in electroplating sites comprises:

[0046] S1: Enter the company name and the electroplating process used by the company in the input module, generate a survey scope based on the company name, and the input module sends the electroplating process to the analysis module and sends the survey scope to the search module.

[0047] S2: The search module obtains various historical pollution information of the investigation scope based on the investigation scope, and sends the historical pollution information to the analysis module.

[0048] After determining the name of the enterprise to be investigated, the input module automatically searches the Internet based on the enterprise name, or manually searches to obtain the location area of ​​the enterprise, and sets the location area as the investigation scope. The investigation scope includes administrative information and geographic information. Administrative information includes province-city-county, etc. Geographic information includes the road name surrounding the investigation scope, or the house number used to indicate the location of the enterprise. The input module sends the investigation scope obtained by the search together with the enterprise name to the search module. In addition, the electroplating process used by the enterprise can be obtained by telephone inquiry or other methods.

[0049] The search module extracts keywords from administrative information, such as enterprise house numbers, and generates search statements to search on the Internet. The search statement is, for example, "What accident occurred at No. 66, B Road, County A?" The search results are used to determine whether the soil within the scope of the investigation has been polluted in the past and what substances have polluted it. In other embodiments, historical pollution information can also be obtained through manual investigation, and then the historical pollution information is input into the search module; historical pollution information includes multiple types, and the specific types are listed later.

[0050] S3: A process comparison table is provided in the analysis module, and the process comparison table includes the correspondence between the electroplating process and the pollution elements. The first pollution element generated by the enterprise's production is obtained based on the electroplating process and the process comparison table.

[0051] S4: The analysis module analyzes the historical pollution information to obtain the second pollution element generated when each historical pollution information occurs. The analysis module sends the first pollution element and the second pollution element as electroplating characteristic pollutants to the recommendation module.

[0052] After receiving the electroplating process used by the electroplating plant, the analysis module determines what pollutants will be produced by each electroplating process according to the pre-set process comparison table, and uses these pollutants as the first pollutant elements. After determining that there is historical pollution information within the scope of the investigation, the analysis module speculates what additional pollutants may exist in the soil based on the historical pollution information, and uses the speculated pollutants as the second pollutant elements. Finally, the analysis module removes the duplicate elements in the first pollutant element and the second pollutant element, and sends them to the recommendation module as electroplating characteristic pollutants.

[0053] S5: There are multiple mandatory elements in the recommendation module. The recommendation module recommends the mandatory elements and electroplating characteristic pollutants as preliminary screening pollution sources to users. Users collect and analyze the preliminary screening pollution sources, and identify the preliminary screening pollution sources that exceed the screening values ​​as priority control pollution sources. The evaluation module directly evaluates the intensity of soil pollution sources in electroplating sites as strong.

[0054] In this embodiment, the required elements include arsenic, cadmium, hexavalent chromium, copper, lead, mercury, nickel, cyanide and petroleum hydrocarbons. In practice, the required elements can also be manually adjusted by the operation of relevant personnel; the recommendation module recommends the required elements and electroplating characteristic pollutants to relevant personnel in the form of text, and also displays the basis for the speculation of electroplating characteristic pollutants. After checking, the relevant personnel will focus on testing the recommended preliminary screening pollution sources during the soil analysis process, and specifically use the above-mentioned analysis process to finally determine which elements belong to the priority control pollution sources.

[0055] S6: If all the initially screened pollution sources do not exceed the screening threshold, a source strength assessment index system is constructed in the assessment module, and the source strength assessment index is calculated based on the source strength assessment index system. The intensity of soil pollution sources in the electroplating site is assessed according to the size of the source strength assessment index.

[0056] In the present invention, after the relevant personnel input the company name through the input module, the system can automatically determine the location information of the company based on the company name, generate the investigation scope based on the location information, and search on the Internet based on the investigation scope to determine whether there is any historical pollution information within the investigation scope and what the historical pollution information is; then, based on the production process used by the company and the historical pollution information, determine which polluting elements may exist, and the relevant personnel analyze these elements after collecting the soil to obtain more comprehensive analysis results; the present invention introduces historical pollution information during the investigation process, so that in the subsequent investigation process, not only the production level of the enterprise is targeted, but also the historical pollution level is paid attention to, ensuring that no pollution sources are missed. After introducing historical pollution information, the system can also automatically analyze and recommend suitable investigation objects, thereby greatly reducing the data collection time.

[0057] It is particularly noteworthy that the present invention introduces historical pollution information to identify the optimal pollution sources, thereby making the subsequent identification results more comprehensive.

[0058] With the development of current artificial intelligence technology, various fields are trying to combine their own professional knowledge with artificial intelligence technology to improve work efficiency. Therefore, the present invention combines the above-mentioned pollution source identification needs and also proposes the following method to automatically collect historical pollution information. This embodiment of obtaining historical pollution information includes the following steps:

[0059] Based on the scope of the investigation, the corresponding location information is determined, and the location information includes administrative information and geographic information. The first search statement corresponding to each type of historical pollution information is generated through the location information. Each first search statement is used to search to obtain the first search result corresponding to each first search statement. The first search result includes multiple result texts. The result texts are split into multiple subject blocks. Target blocks related to the first search statement are extracted from the subject blocks. The target blocks extracted from the multiple result texts are summarized and analyzed to obtain historical pollution information.

[0060] This embodiment needs to obtain a variety of historical pollution information, such as historical accident data and historical landfill data. When obtaining historical accident data, as before, the following first search statement can be generated based on the location information: "What accident occurred at No. 66, B Road, County A?". To obtain historical landfill data, the first search statement generated is "What pollutants are buried in the plot where No. 66, B Road, County A is located?". After searching with each first search statement, the corresponding first search result can be obtained. The first search result generally has multiple result texts, such as news reports, microblog articles, etc. For news reports, the location, time, cause, process, damage caused, and evaluation of the writer may be included. Since the present invention is to determine whether an accident occurred within the scope of the investigation and what kind of accident occurred, in order to shorten the subsequent analysis process, it is necessary to eliminate irrelevant content and only retain the location, time, and cause.

[0061] After obtaining the result text, the present invention splits each result text into multiple subject blocks, extracts the subject blocks related to the cause of the accident, and finally summarizes and analyzes the multiple subject blocks; the purpose of the summary and analysis is twofold, on the one hand, to verify the contents of multiple subject blocks with each other to avoid searching for false information, and on the other hand, to convert multiple subject blocks into a standard summary template to facilitate the subsequent generation of a second search statement.

[0062] In this embodiment, splitting the result text into multiple subject blocks includes the following steps:

[0063] The result text is split into multiple independent sentences, which are numbered from 1 to N according to the order in which they appear in the result text. The lower limit and upper limit are set. Starting from the independent sentence numbered 1, the lower limit of independent sentences are divided into the first language block, and the independent sentences other than the first language block are divided into the second language block.

[0064] Starting from the independent sentence numbered 2, the lower limit number of independent sentences are re-divided into the first language block, and the independent sentences before and after the first language block are respectively divided into the second language block and the third language block. Starting from the independent sentence numbered 3, this step is repeated until the independent sentence numbered N is divided into the first language block, so as to complete the traversal and division of the result text using the lower limit number.

[0065] This implementation uses punctuation marks as dividing points to split the result text, and punctuation marks include commas, semicolons, periods, etc. The lower limit is set to 2, and the upper limit is set to 4. Assuming that the result text is split into 30 independent sentences, the independent sentences are numbered 1-30 in sequence according to the order in which the independent sentences appear in the result text. First, starting from independent sentence 1, independent sentences 1-2 are divided into the first language block 1, and the remaining independent sentences 3-30 are divided into the second language block 1; then, starting from independent sentence 2, independent sentences 2-3 are divided into the first language block 2, independent sentence 1 is divided into the second language block 1, and independent sentences 4-30 are divided into the third language block 1, and then starting from independent sentence 3, the division continues until the first language block 29 is divided. Since the first language block 29 includes independent sentences 29-30, multiple first language blocks, second language blocks, and third language blocks are obtained in the division process.

[0066] Add 1 to the lower limit to obtain the advanced number, and use the advanced number to traverse and divide the result text. After the traversal is completed, add 1 to the advanced number again and repeat this step until the advanced value reaches the upper limit.

[0067] After adding 1 to the lower limit, the advanced number is 3. The same steps as the above division of language blocks are used to divide based on the advanced number, that is, the independent sentences 1-3 are initially divided into the first language block. After the traversal division of language blocks is completed using the advanced number, the advanced number is increased by 1, and the traversal division is performed using the upper limit 4. Therefore, a large number of first language blocks, second language blocks, and third language blocks can be obtained through this step.

[0068] In this embodiment, extracting the target chunk from the subject chunk includes the following steps:

[0069] Keywords are extracted from the first search sentence, and scores of the divided first language block, second language block, or third language block are calculated based on a first formula. The first formula is: , where P1 is the number of independent sentences included in the first block, the second block or the third block, P2 is the number of keywords included in the first block, the second block or the third block, and X is a preset value. The subject block with the highest score is taken as the target block.

[0070] The keywords in the first search sentence include administrative information obtained according to the scope of the investigation. For example, the keywords in "What accident happened at No. 66, B Road, County A?" are County A, B Road, and No. 66. In the first formula, the more independent sentences a block includes, the lower the calculated score is, and the more keywords it includes, the greater the calculated score is. X is set according to the actual situation, for example, X is set to 3. This formula can filter out blocks that still contain a large number of keywords even when they include fewer independent sentences. In this way, the smallest block can be filtered out from blocks that include more keywords, which is convenient for subsequent analysis of the target block. For example, "On March 21, an XX leakage accident occurred at the HH electroplating plant in County A" will be filtered out as the target block.

[0071] In other embodiments, a large language model LM can also be used to split the language chunks. As is known to all, a large language model requires a large amount of training data for training before application, and the parameters need to be constantly adjusted during the training process to prevent it from overfitting or underfitting. If a third-party large model is used, it will bring higher usage costs. Therefore, this embodiment provides a language chunk splitting method that is particularly suitable for the applicable scenarios of the present invention. Not only is the splitting speed fast, but also the upper and lower limits set later, as well as the first formula, can quickly obtain a target language chunk that is related to the first search statement and is brief. Compared with commonly used artificial intelligence technology, the extraction method of the present invention greatly improves the result generation speed.

[0072] In this embodiment, summarizing and analyzing the target language block includes the following steps:

[0073] The target language blocks from different result texts are compared in pairs to obtain multiple similarities. When comparing, the similarity L of the two target language blocks is calculated based on the second formula. The second formula is: , where D is the number of identical characters in the two target language blocks, a and b are the number of characters contained in the two target language blocks respectively, and MAX (a, b) returns the larger value of a or b.

[0074] A summary template is set, which includes a time description, a place description and a reason description. If all the calculated similarities are greater than the first threshold, one of the target language blocks is selected, and the corresponding information is extracted from it and filled into the summary template to complete the summary analysis of the target language block.

[0075] The above process is described in detail below. First, assume that target chunk 1 and target chunk 2 are extracted from result text 1 and result text 2 respectively. Then count the number of characters in target chunk 1, the number of characters in target chunk 2, and how many identical characters there are in target chunk 1 and target chunk 2. For example, target chunk 1 has 20 characters and target chunk 2 has 22 characters, both of which include "On March 21, 2021, FF leakage occurred at Factory B, County A", a total of 18 characters. The calculated similarity is 18 / 23=0.82. Then extract the target chunk from other result texts and continue the above process for comparison. The first threshold is set to 0.7. If all the calculated similarities are greater than the first threshold, it indicates that all search results are consistent, and the search results are considered to be relatively reliable. The content is extracted and filled into the summary template. This comparison method will have a large error when comparing longer paragraphs, but due to the previous chunk extraction method, the target chunk will not include more characters. Therefore, the comparison method still has a high accuracy while ensuring the simplicity of calculation.

[0076] In this embodiment, obtaining the second contamination element includes the following steps:

[0077] A second search statement is generated based on the historical pollution information, the second search statement is used to search to obtain a second search result, a detection field is set, and an element name located after the detection field is extracted from the result text of the second search result as a second pollution element.

[0078] For example, the summary template for historical pollution information related to accidents is "During CC time, a DD accident occurred", where CC and DD are blank items to be filled in. When generating the second search statement, only the second half of the summary template is captured to generate the second search statement, such as "What harmful substances will be produced when a DD accident occurs". Therefore, the generation speed of the subsequent second search statement can be improved through the summary template of the prior process. The second search result obtained later will also include multiple result texts. This embodiment only captures the element name located after the detection field as the second pollution element. The detection field includes "will produce", "will cause", "will appear", etc. For example, if the search results show that "wastewater A leaks and produces toxic elements 1, toxic elements 2, and toxic elements 3", then toxic elements 1-3 are used as the second pollution elements. Through this step, even data organizers who do not understand the basic knowledge in this field can use this system to quickly obtain the second pollution element, thereby greatly improving the application scope of this system.

[0079] In this embodiment, a first database and a second database are set. After the second search statement is generated, the second search statement is preferentially used to search in the first database. If the second search result is not obtained, the second database is then used to search.

[0080] Specifically, the first database is a pre-established accident analysis database, which includes various accident names and corresponding harmful elements. The second database is an Internet database. Searching in the first database first can obtain the second search result faster and more accurately. Since the first database is artificially established, it is impossible to cover all accident situations. If the second search result is not obtained in the first database, continue to search in the second database.

[0081] The historical pollution information in the present invention includes historical landfill information, historical pollution accident information, historical groundwater pollution information and historical layout information of pollutant auxiliary facilities. In particular, in combination with the actual situation of the factory and the historical pollution information, the soil collection points can be set in the production equipment area, the storage and loading and unloading area of ​​toxic and hazardous materials, the storage tanks and tanks in the toxic and hazardous material transportation corridor area, the underground transportation pipelines of toxic and hazardous substances, the pollution treatment facility area, the hazardous material storage depot, and the waste slag underground landfill area in the historical pollution information, the area involved in the pollution accident, the polluted groundwater pollution area, and the auxiliary facilities of toxic and hazardous pollutants, and the auxiliary facilities refer to the transportation pipelines used to transport toxic and hazardous substances.

[0082] This embodiment of evaluating the intensity of soil pollution sources in electroplating sites specifically includes the following steps:

[0083] This embodiment selects indicators for this evaluation indicator system in accordance with the principles of indicator indicativeness, data availability, indicator comparability, and indicator independence. The evaluation indicator system consists of a target layer (V), a solution layer (A), a factor layer (B), and an indicator layer (C). For different electroplating sites, different types of representative indicators can be selected for combination while satisfying the factor layer indicators as much as possible.

[0084] In the process of determining the standard values ​​of indicators, the main reference is the regional standards that have been determined through research; the goals of regional soil environmental quality and environmental management are used as reference standards; for those indicators that are currently less studied but are more important for the assessment of soil pollution source intensity, in the absence of relevant indicator statistical data, empirical data are temporarily used as reference standards.

[0085] The scheme-level evaluation adopts a hierarchical scoring and step-by-step weighting method, including the calculation of the indicator-level score, the calculation of the indicator-level weight to the scheme-level, and the calculation of the scheme-level score. For the calculation of the indicator-level score, the type of evaluation indicator is determined based on the original data of the evaluation indicator and the corresponding standard value, and the score of the evaluation indicator is calculated using the data preprocessing formula, that is, the dimensionless value ( ). The calculation formula of the indicator layer weight to the solution layer is: , where is the weight coefficient of the C-layer index factor relative to the solution layer A; is the weight coefficient of the i-th indicator factor in layer C relative to factor layer B; is the weight coefficient of factor layer B relative to solution layer A;

[0086] After the dimensionless value and weight of each indicator are determined, according to the formula Calculate the score of each solution layer, where: The calculation result of the score value of the kth solution layer; is the dimensionless value of the evaluation index, which must satisfy 0≤ ≤1, if greater than 1, the value is 1; is the weight coefficient of the C-layer indicator factor relative to the solution layer A.

[0087] For the target layer assessment, the target layer assessment is a comprehensive assessment of pollution source strength. The weighted summation method is used to calculate the soil pollution source strength index (PSII) of the electroplating site. The result is a value of 1 to 100. The specific formula is: In the formula, PSII is the soil pollution source strength index of the electroplating site; is the score value of the k-th solution layer; is the weight coefficient of the k-th solution layer to the target layer.

[0088] The present invention divides the emission intensity assessment index of the preferred controlled pollution sources in the electroplating sites in the Pearl River Delta into four levels: strong, relatively strong, medium and weak. Among them, the soil pollution source intensity index between 80 and 100 is classified as strong, between 60 and 80 is classified as relatively strong, between 30 and 60 is classified as medium, and less than 30 is classified as weak.

[0089] like Figure 2 As shown, the present invention also provides a system for identifying optimally controlled pollution sources in the soil of an electroplating site, which is used to implement the above-mentioned method for identifying optimally controlled pollution sources in the soil of an electroplating site, and the system includes:

[0090] An input module, which is used to input the company name and the electroplating process used by the company, and to generate a survey scope based on the company name. The input module sends the electroplating process to the analysis module and sends the survey scope to the search module;

[0091] A search module, which obtains various historical pollution information of the investigation scope based on the investigation scope, and sends the historical pollution information to the analysis module;

[0092] The analysis module is provided with a process comparison table, which includes the correspondence between the electroplating process and the pollution elements. The first pollution element generated by the enterprise production is obtained based on the electroplating process and the process comparison table. The historical pollution information is analyzed to obtain the second pollution element generated when each historical pollution information occurs. The analysis module sends the first pollution element and the second pollution element as electroplating characteristic pollutants to the recommendation module;

[0093] The recommendation module is equipped with multiple mandatory elements. The recommendation module recommends mandatory elements and electroplating characteristic pollutants as preliminary screening pollution sources to users. Users collect and analyze the preliminary screening pollution sources and identify the preliminary screening pollution sources that exceed the screening value as priority control pollution sources.

[0094] Evaluation module: If there are primary screening pollution sources that exceed the screening value, the evaluation module will directly evaluate the intensity of soil pollution sources in the electroplating site as strong. If all primary screening pollution sources do not exceed the screening threshold, a source strength evaluation index system will be constructed in the evaluation module. The source strength evaluation index will be calculated based on the source strength evaluation index system, and the intensity of soil pollution sources in the electroplating site will be evaluated according to the size of the source strength evaluation index.

[0095] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0096] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying optimally controlled pollution sources in electroplating site soil, characterized in that: include: Entering the company name and the electroplating process used by the company in the input module, generating a survey scope based on the company name, the input module sending the electroplating process to the analysis module, and sending the survey scope to the search module; The search module obtains a variety of historical pollution information of the survey scope based on the survey scope, and sends the historical pollution information to the analysis module; The analysis module is provided with a process comparison table, which includes the correspondence between the electroplating process and the pollutant elements, and the first pollutant element generated by the enterprise production is obtained based on the electroplating process and the process comparison table; The analysis module analyzes the historical pollution information to obtain the second pollution element generated when each historical pollution information occurs, and the analysis module sends the first pollution element and the second pollution element as electroplating characteristic pollutants to the recommendation module; The recommendation module is provided with a plurality of mandatory elements. The recommendation module recommends the mandatory elements and the electroplating characteristic pollutants as preliminary screening pollution sources to the user. The user collects and analyzes the preliminary screening pollution sources, and identifies the preliminary screening pollution sources exceeding the screening value as priority control pollution sources. The evaluation module directly evaluates the intensity of the soil pollution source in the electroplating site as strong. If all the initially screened pollution sources do not exceed the screening value, a source strength assessment index system is constructed in the assessment module, a source strength assessment index is calculated based on the source strength assessment index system, and the intensity of the soil pollution source in the electroplating site is assessed according to the size of the source strength assessment index; Obtaining the historical pollution information includes the following steps: Determine corresponding location information based on the survey scope, the location information includes administrative information and geographic information, generate a first search statement corresponding to each type of historical pollution information through the location information, use each of the first search statements to search, obtain a first search result corresponding to each of the first search statements, the first search result includes multiple result texts, split the result texts into multiple subject blocks, extract target blocks related to the first search statement from the subject blocks, and summarize and analyze the target blocks extracted from the multiple result texts to obtain the historical pollution information; Splitting the result text into multiple subject blocks includes the following steps: Splitting the result text into multiple independent sentences, numbering the independent sentences from 1 to N according to the order of appearance in the result text, setting a lower limit and an upper limit, taking the independent sentence numbered 1 as the starting point, dividing the independent sentences of the lower limit into a first language block, and dividing the independent sentences other than the first language block into a second language block; Starting from the independent sentence numbered 2, the lower limit number of independent sentences are re-divided into the first language block, and the independent sentences before and after the first language block are respectively divided into the second language block and the third language block, starting from the independent sentence numbered 3, repeating this step until the independent sentence numbered N is divided into the first language block, so as to complete the traversal and division of the result text using the lower limit number; The lower limit number is increased by 1 to obtain the advanced number, and the advanced number is used to traverse and divide the result text. After the traversal is completed, the advanced number is increased by 1 again, and this step is repeated until the advanced number reaches the upper limit number.

2. The method according to claim 1, characterized in that Extracting the target chunk from the subject chunk includes the following steps: Keywords are extracted from the first search statement, and scores of the first language block, the second language block, or the third language block are calculated based on a first formula, where the first formula is: , wherein P1 is the number of the independent sentences included in the first language block, the second language block or the third language block, P2 is the number of the keywords included in the first language block, the second language block or the third language block, X is a preset value, and the subject language block with the highest score is used as the target language block.

3. The method according to claim 1, characterized in that Summarizing and analyzing the target language block includes the following steps: The target language blocks from different result texts are compared in pairs to obtain multiple similarities. When comparing, the similarity L of two target language blocks is calculated based on a second formula. The second formula is: , where D is the number of identical characters in the two target language blocks, a and b are the number of characters in the two target language blocks respectively, and MAX (a, b) returns the larger value of a or b; A summary template is set, which includes a time description, a place description and a reason description. If all the calculated similarities are greater than a first threshold, one of the target language blocks is selected, and corresponding information is extracted from it and filled into the summary template to complete the summary analysis of the target language block.

4. The method according to claim 1, characterized in that: Obtaining the second contamination element comprises the following steps: A second search statement is generated based on the historical pollution information, the second search statement is used to search to obtain a second search result, a detection field is set, and an element name located after the detection field is extracted from the result text of the second search result as the second pollution element.

5. The method according to claim 4, characterized in that A first database and a second database are set. After the second search statement is generated, the second search statement is preferentially used to search in the first database. If the second search result is not obtained, the second database is then used to search.

6. The method according to claim 1, characterized in that The historical pollution information includes historical landfill information, historical pollution accident information, historical groundwater pollution information and historical layout information of pollutant auxiliary facilities.

7. The method according to claim 1, characterized in that The required elements include arsenic, cadmium, hexavalent chromium, copper, lead, mercury, nickel, cyanide and petroleum hydrocarbons.

8. A system for identifying optimally controlled pollution sources in electroplating sites, used to implement the method according to any one of claims 1 to 7, characterized in that: include: An input module, the input module is used to input the company name and the electroplating process used by the company, generate a survey scope based on the company name, and send the electroplating process to the analysis module and send the survey scope to the search module; A search module obtains a variety of historical pollution information within the survey scope based on the survey scope, and sends the historical pollution information to the analysis module, wherein corresponding location information is determined based on the survey scope, the location information includes administrative information and geographic information, a first search statement corresponding to each type of historical pollution information is generated through the location information, each of the first search statements is used to search, and a first search result corresponding to each of the first search statements is obtained, the first search result includes a plurality of result texts, the result text is split into a plurality of subject blocks, target blocks related to the first search statement are extracted from the subject blocks, the target blocks extracted from the plurality of result texts are summarized and analyzed to obtain the historical pollution information, and when splitting the result text, the result text is split into a plurality of independent statements, and the independent statements are numbered according to the order in which they appear in the result text. 1 to N, set a lower limit and an upper limit, take the independent statement numbered 1 as the starting point, divide the independent statements of the lower limit into the first language block, divide the independent statements other than the first language block into the second language block, take the independent statement numbered 2 as the starting point, re-divide the independent statements of the lower limit into the first language block, and divide the independent statements before and after the first language block into the second language block and the third language block respectively, take the independent statement numbered 3 as the starting point, repeat this step until the independent statement numbered N is divided into the first language block, so as to complete the traversal and division of the result text using the lower limit, add 1 to the lower limit, obtain the advanced number, use the advanced number to traverse and divide the result text, after the traversal is completed, add 1 to the advanced number again, and repeat this step until the advanced number reaches the upper limit; An analysis module is provided with a process comparison table, the process comparison table includes a correspondence between the electroplating process and the pollutant elements, obtains a first pollutant element generated by the enterprise production based on the electroplating process and the process comparison table, analyzes the historical pollution information, obtains a second pollutant element generated when each historical pollution information occurs, and the analysis module sends the first pollutant element and the second pollutant element as electroplating characteristic pollutants to the recommendation module; A recommendation module is provided with a plurality of required test elements. The recommendation module recommends the required test elements and the electroplating characteristic pollutants as preliminary screening pollution sources to the user. The user collects and analyzes the preliminary screening pollution sources and identifies the preliminary screening pollution sources that exceed the screening value as priority control pollution sources; An evaluation module, if there are any initially screened pollution sources that exceed the screening value, the evaluation module directly evaluates the intensity of the soil pollution source in the electroplating site as strong; if all the initially screened pollution sources do not exceed the screening value, a source strength evaluation index system is constructed in the evaluation module, and a source strength evaluation index is calculated based on the source strength evaluation index system, and the intensity of the soil pollution source in the electroplating site is evaluated according to the size of the source strength evaluation index.

Images