Pollutant emission enterprise filling data quality control method and equipment

Abstract

The embodiment of the invention provides a pollution emission enterprise filling data quality control method and equipment. The pollution emission enterprise filling data quality control method comprises the following steps: mining and analyzing production technology and production process data of each industry, and constructing a raw material-output product association database; under the condition that the data filled by the pollution emission enterprise is received, querying the raw material-output product association database based on the filled data, and determining possible unfilled data; and generating a corresponding filling data frame and / or filling prompt information based on the possibly unfilled data. According to the method, a raw material-product association database is constructed in advance, and under the condition that part of filling data filled by a pollution emission enterprise is obtained, whether the filling data has possible missing data or not is inquired through the part of filling data. And when it is determined that the data is possibly missed to be filled, prompting can be carried out by generating a corresponding filling data frame or filling prompt information, and a pollution emission enterprise is guided to realize filling of the data which is possibly missed to be filled.

Description

Technical Field

[0001] The present disclosure relates to the technical field of pollutant emission accounting, and particularly to a method and device for quality control of data filled in by pollution-emitting enterprises. Background Art

[0002] The data filled in by pollution sources is the basis for calculating pollution emissions, and the correctness and rationality of the filled-in data directly affect the statistical accounting of regional pollution emissions. Currently, the filling in of fixed pollution source data is carried out by manufacturing enterprises that are the direct responsible parties for pollution sources. There are problems such as random filling, missing filling, and incorrect filling in the existing filling in of fixed pollution source data, and the accuracy of the corresponding filled-in data cannot be guaranteed. Based on the aforementioned untrustworthy filled-in data, reliable statistical accounting data cannot be obtained. Summary of the Invention

[0003] In a first aspect, an embodiment of the present disclosure provides a method for quality control of data filled in by pollution-emitting enterprises, including: Mining and analyzing the production processes and production process data of each industry to construct a raw material-output product association database, where the raw material-output product association database includes the input-output association relationships of production processes, raw materials, end products, and intermediate products in each industry; When receiving the data filled in by a pollution-emitting enterprise, querying the raw material-output product association database based on the filled-in data to determine possible unfilled data; the filled-in data includes at least one of the industry, production process, some raw materials, some end products, and some intermediate products; the possible unfilled data includes at least one of unfilled initial raw materials, unfilled intermediate products, and unfilled end products; Generating corresponding data filling frames and / or filling prompt messages based on the possible unfilled data; the data filling frames are used to receive possible unfilled data of corresponding attributes, and the filling prompt messages are used to prompt the existence of the possible unfilled data.

[0004] Optionally, mining and analyzing the production processes and production process data of each industry to construct a raw material-output product association database includes: Collecting historical filled-in data and performing standardized sorting to obtain standardized names for various raw materials and output products; Based on the input-output relationships in the production processes and production process data of each industry, establishing a raw material-output product association database with standardized names under various production processes.

[0005] Optionally, it further includes: when the filled-in data includes the process steps of a production process, determining whether the production process of the pollution-emitting enterprise is a combined process; In the case where the production process is determined to be a combined process, determine the unreported process steps according to the reported process steps and the corresponding combined process, and determine the output products of the unreported process steps based on the raw material-product association database; Generate a filling prompt message that prompts the unreported process steps and the corresponding output products, and / or generate a filling data frame for filling the output products corresponding to the unreported process steps.

[0006] Optionally, in the case where the reported data includes the first numerical data related to raw material consumption or output product quantity, the method further includes: Judge whether the first numerical data is outside the normal production activity level range, where the normal production activity level range is determined by statistical analysis of historical numerical data, and the historical numerical data is obtained for similar enterprises related to the corresponding raw material consumption or output product quantity according to the industry type and enterprise scale of the pollution emission enterprise; In the case where the first numerical data is outside the normal production activity level, generate a prompt message for judging whether the first numerical data is abnormally reported data.

[0007] Optionally, in the case where the first numerical data is outside the normal production activity level, generating a prompt message for judging whether the first numerical data is abnormally reported data further includes: Judge whether there is second numerical data in the reported data that has an association relationship with the first numerical data; In the case where there is second numerical data associated with the first numerical data in the reported data, calculate the actual correlation coefficient between the first numerical data and the second numerical data; Judge whether the actual correlation coefficient is outside the pre-determined reasonable correlation coefficient range; In the case where the actual correlation coefficient is outside the pre-determined reasonable correlation coefficient range, generate a prompt message for judging whether the first numerical data is abnormally reported data.

[0008] Optionally, in the case where the reported data includes the first numerical data related to raw material consumption or output product quantity, the method further includes: Obtain the historical numerical data of the pollution emission enterprise related to the corresponding raw material consumption or output product quantity, and sort the historical numerical data according to time to obtain a sorted sequence; Identify whether the first numerical data is abnormal data based on the sorted sequence; In the case where the first numerical data is abnormal data, generate a prompt message for indicating whether the first numerical data is abnormally reported data.

[0009] Optionally, when the filled data includes two numerical data related to raw material consumption and / or output product output, and it is determined according to the production process adopted by the pollution-emitting enterprise that the two numerical data are related data, the method further includes: Calculating an actual correlation coefficient based on the two numerical data, and determining whether the actual correlation coefficient is outside a pre-determined reasonable correlation coefficient interval; When the actual correlation coefficient is outside the pre-determined reasonable correlation coefficient interval, generating a prompt message indicating that at least one of the two numerical data is abnormal data.

[0010] Optionally, the filled data includes basic information, and the basic information includes specific information of the production line, a detailed description of the production process, and a classified description of raw material types; The method further includes: when the filled data includes numerical data related to raw material consumption or output product output, performing semantic information mining based on the basic information, the numerical data, and the attributes of the numerical data to determine whether there is abnormal data in the numerical data; When it is determined that there is abnormal data in the numerical data, determining the target numerical data identified as abnormal data, and generating a prompt message indicating that the target numerical data is abnormal data.

[0011] Optionally, it further includes: obtaining market industry data; the market industry data includes historical data and / or prediction data related to the market status of the industry to which the pollution-emitting enterprise belongs; Performing semantic information mining based on the basic information, the numerical data, and the attributes of the numerical data to determine whether there is abnormal data in the numerical data, including: Performing semantic information mining based on the basic information, the numerical data, the attribute information of the numerical data, and the market industry data to determine whether there is abnormal data in the numerical data.

[0012] In a second aspect, an embodiment of the present disclosure provides a computing device, including a storage and a processor, where the storage is used to store a computer program; when the computer program is loaded by the processor, the processor executes the pollution-emitting enterprise filled data quality control method as described above.

[0013] Adopting the solution of the embodiment of the present disclosure, by pre-constructing a raw material-output product association database, when obtaining some filled data filled by a pollution-emitting enterprise, it is possible to query whether there are possible missing filled data through the partial filled data. When it is determined that there are possible missing filled data, it can be prompted by generating a corresponding filled data box or a filled prompt message to guide the pollution-emitting enterprise to fill in the possible missing filled data. Description of the Drawings

[0014] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0015] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings, where: Figure 1 is a flowchart of a method for quality control of data filled in by pollution emission enterprises provided by some embodiments of the present disclosure; Figure 2 is a flowchart of a method for prompting missing data in filled-in data provided by some embodiments of the present disclosure; Figure 3 is a flowchart of a method for determining abnormal numerical data provided by some embodiments of the present disclosure; Figure 4 is a flowchart of a method for determining abnormal numerical data provided by still some other embodiments of the present disclosure; Figure 5 is a schematic structural diagram of a computing device provided by an embodiment of the present disclosure. Detailed Embodiments

[0016] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the accompanying drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0017] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. In this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0018] To solve the problem of inaccurate accounting data of pollution emissions in the later stage caused by incorrect filling of some data, the embodiments of the present disclosure provide a new quality control method for the data filled by pollution-emitting enterprises. The quality control method for the data filled by pollution-emitting enterprises provided by the embodiments of the present disclosure realizes the rapid mining of the filled data by guiding the data fillers to fill in the data and discovering the problems that do not conform to the data logic in the filled data during the filling process of pollution-emitting enterprises.

[0019] Figure 1 It is a flowchart of the quality control method for the data filled by pollution-emitting enterprises provided by some embodiments of the present disclosure. As Figure 1 shown, the quality control method for the data filled by pollution-emitting enterprises provided by the embodiments of the present disclosure includes S110 - S130.

[0020] S110: Mine and analyze the production process and production process data of each industry, and construct a raw material-output product association database.

[0021] During the process of filling in the data of fixed pollution sources, the data items filled in by pollution source emission enterprises are arbitrary. Often, the data fillers fill in the data according to their own experience and the existing data around them, filling in whatever data items come to mind, without having a global understanding or comprehension of the production process, input, and output of the enterprise where they are located. And it is precisely the aforementioned problems that cause the filled items of many filling enterprises to be significantly inconsistent with the actual situation of the enterprise.

[0022] To solve this problem, the embodiments of the present disclosure consider reducing the dependence on the quality of pollution-emitting enterprises and their data fillers as much as possible. It does not require them to have a profound understanding of the enterprise where they are located in terms of technology and production. The filling of relevant data of pollution-emitting enterprises is realized through an active guiding method.

[0023] To achieve the goal in the previous paragraph, relevant basic data is first required, that is, the premise for realizing the guided filling of enterprises. In the embodiments of the present disclosure, this premise is the raw material-output product association database. The raw material-output product association library is a database that stores and reflects the corresponding raw materials input by a production enterprise under specific process conditions and what types of output products will be produced based on the production process. The aforementioned output products include the intermediate output products and terminal output products of the enterprise. That is to say, as long as there is the input of corresponding types of raw materials and the output of corresponding products in the corresponding production process, this data will be written into the raw material-output product association database. The output products mentioned here should be understood in a broad sense, which includes both the sales products and intermediate products produced by the enterprise with the goal of production stress, as well as the associated pollutants produced in the production of the aforementioned products.

[0024] In specific implementation, by mining and analyzing the production processes and production process data of various industries, the input-output correlation relationships among raw material inputs, intermediate outputs, and end products when corresponding production processes are adopted in specific industries are sorted out, and then a raw material-output product correlation database is obtained.

[0025] In a specific implementation, the process of mining and analyzing the production processes and production process data of various industries and constructing a raw material-output product correlation database includes S111 - S112.

[0026] S111: Collect historical reported data and perform standardized sorting to obtain standardized names for various raw materials and output products.

[0027] In actual operation, the randomness of data reported by pollution-emitting enterprises is reflected in the non-standardization of the names of raw materials, output products, and even production processes they report. Due to the non-standardization of the aforementioned data names, it is difficult to form a tight correlation between data, affecting the quality of the subsequent established correlation database.

[0028] To solve this problem, some embodiments of the present disclosure collect historical reported data from various industries and perform standardized processing on the data names to form standard names for various production processes, raw materials, and output products. In specific implementation, it is possible to refer to the industry's pollutant discharge coefficient manual and analyze based on the relationship between raw materials and output products in the industry's production process, mapping various raw materials and output products in the sorted historical reported data to the corresponding standard product names. By sorting out the historical reported data, it is determined that there are approximately 5,200 types of output products reported by pollution-emitting enterprises, and the standardization of the aforementioned 5,200 types of products can be mapped to a total of 421 standardized product names in 230 industries.

[0029] S112: Based on the production processes of various industries and the relationship between pollutant discharge coefficients in the production process, establish a raw material-output product correlation database with standardized names under various production processes.

[0030] Through the analysis of historical reported data, it is found that pollution-emitting enterprises usually only report information on initial raw materials and end products. However, the pollution emissions in actual production are not limited to the end. Intermediate products in the intermediate links of various production processes are also important sources of pollution and should be included in the calculation of pollution emissions. Based on this, the embodiment solution of the present disclosure, based on the production processes of various industries and the relationship between pollutant discharge coefficients in the production process, conducts in-depth mining and analysis work with the help of big data analysis technology, reveals the internal connection and interaction between key raw materials and pollutants, and constructs a raw material-output product correlation database with standardized names under various production processes.

[0031] As analyzed above, since the output products include end products and intermediate products, and different output products may produce pollutants, the aforementioned raw material-output product association data can also be understood as an output product-required pollutant association database. That is to say, through the raw material-output product association database, based on a single raw material and a single product (including production processes in some cases), the association relationship between intermediate products and required pollutants can be determined. Furthermore, based on specific raw materials and output products, the upstream, midstream, and downstream products and their required pollutants can be determined.

[0032] In specific implementation, a dynamic update mechanism can be introduced to ensure that the data in the constructed raw material-output product association database is synchronized with the development of industry technologies, reflecting the changes in industry processes and industry output products with technological progress, thereby ensuring the timeliness and accuracy of the data filled in by enterprises.

[0033] S120: When the data filled in by a pollution-emitting enterprise is received, query the raw material-output product association database based on the filled-in data to determine the possible unfilled data.

[0034] When a pollution-emitting enterprise fills in relevant data, the filling personnel complete the filling of part of the data based on known situations and data, forming the filled-in data. In specific implementation, the filled-in data may include at least one of the sub-sectors to which the pollution-emitting enterprise belongs, the production processes adopted, some raw materials, some end products, and some intermediate products.

[0035] After obtaining the filled-in data, retrieve the raw material-output product association data with the filled-in data to obtain the possible unfilled data. In specific implementation, the possible unfilled data includes at least one of the unfilled initial raw materials, unfilled intermediate products, and unfilled end products. It should be noted here that the possible unfilled data may overlap with some of the filled-in data (it may be that due to technological reasons, a certain raw material is the output product of an intermediate process or even an end product).

[0036] In specific implementation, the data filling of pollution-emitting enterprises is mostly achieved through enterprise-side electronic devices, while the querying of data to determine the possible unfilled data is mostly achieved by data servers deployed by industry competent departments. Therefore, in specific implementation, it is mostly the data servers deployed by industry competent departments that receive the data filled in by pollution-emitting enterprises and then query the data based on the filled-in data to determine the possible unfilled data (this helps to ensure data confidentiality). Of course, in some embodiments, the aforementioned raw material-output product association database may also be sent to the enterprise-side electronic devices, and the enterprise-side electronic devices retrieve the data based on the filled-in data to determine the unfilled data.

[0037] For example, in a specific application, the industry code of a pollution reporting enterprise is 2622. In the data already reported by this pollution reporting enterprise, only phosphate rock and sulfuric acid are written. According to the industry code and the production process adopted by the enterprise, it is determined that this pollution reporting enterprise uses phosphate rock, sulfuric acid, phosphoric acid, and synthetic ammonia as raw materials to produce diammonium phosphate. Through the raw material-output product association database, it is determined that the key product (which is also a major pollutant) synthetic ammonia is missing in its raw materials.

[0038] For another example, in another specific application, a pollution reporting enterprise in the cogeneration industry (industry code 4412) reports that the raw material (fuel) used is natural gas. According to its production process and the aforementioned raw material-output product association database, the output products (pollutants) at the industrial boiler exhaust port of this pollution emission enterprise include sulfur dioxide, nitrogen oxides, and volatile organic compounds. However, in the data already reported by the enterprise, only sulfur dioxide and volatile organic compounds are reported. Through the raw material-output product association database, it is determined that the important output product (pollutant) nitrogen oxides is missing in its raw materials.

[0039] S130: Generate corresponding data filling frames and / or filling prompt messages based on the possibly unreported data.

[0040] After determining the possibly unreported data, a data filling frame or a filling prompt message can be generated according to specific circumstances. A data filling frame is a data frame used to receive the possibly unreported data of corresponding attributes. A filling prompt message is a prompt message used to prompt the possibly unreported data.

[0041] In specific implementation, when the device for performing data processing is a background server controlled by the competent department, the background server can send an instruction to generate a data filling frame or a filling prompt message to the enterprise-side electronic device, and then the enterprise-side electronic device directly generates a data filling frame or a filling prompt message. When the device for performing data processing is an enterprise-side electronic device, the enterprise-side electronic device directly generates the corresponding data filling frame or filling prompt message.

[0042] Adopting the solution of the embodiment of the present disclosure, by pre-constructing a raw material-output product association database, in the case of obtaining partial reported data of a pollution emission enterprise, it is queried whether there is possibly missing data in the reported data through the partial reported data.

[0043] In the case of determining that there is possibly missing data, it can be prompted by generating a corresponding data filling frame or a filling prompt message, guiding the pollution emission enterprise to fill in the possibly missing data.

[0044] By analyzing the current process status of a large number of industries and enterprises, it is found that the production processes of many industries are combined processes, that is, at least two process steps are required to convert raw materials into end products. For example, through in-depth research and analysis of the production processes of various industries, it is determined that 16 specific industry sub-categories have combined processes, namely: nitrogen fertilizer manufacturing, steelmaking, coking, ironmaking, coal-to-syngas production, coal products manufacturing, coal-to-liquid fuel production, other non-metallic mineral products manufacturing, other basic chemical raw material manufacturing, other coal processing, light building materials manufacturing, biomass densified briquette fuel processing, cement products manufacturing, inorganic alkali manufacturing, inorganic acid manufacturing, and inorganic salt manufacturing.

[0045] For the aforementioned industries adopting combined processes, the embodiments of the present disclosure further carefully sort out and analyze the production processes of these industries' combined processes, mark and classify the emission process nodes that may occur in each combined process, and determine the process steps included in the combined process and the output products of each process step.

[0046] Figure 2 It is a flowchart of a method for prompting missing data in the data to be filled in provided by some embodiments of the present disclosure. As Figure 2 shown, during the process of data filling by a pollution reporting enterprise, if the data it has filled in includes the process steps of the production process, the following S140-S160 can also be executed.

[0047] S140: Determine whether the production process of the pollution emission enterprise is a combined process; if so, execute S150; if not, end the execution.

[0048] Determining whether the production process of the pollution emission enterprise is a combined process is based on the industry to which the pollution emission enterprise belongs and the process type it fills in. After determining the process type it fills in, it can be judged whether the process adopted by this enterprise is a combined process through the corresponding process database.

[0049] S150: Determine the unreported process steps according to the already filled-in process steps and the corresponding combined process, and determine the output products of the unreported process steps based on the raw material-product association database.

[0050] S160: Generate a filling prompt message indicating unreported process steps and the corresponding output products, and / or generate a filling data frame for filling in the output products corresponding to the unreported process steps.

[0051] In the case where it is determined that the production process adopted by a pollution-emitting enterprise is a combined process, it is then possible to determine whether there are unreported process steps based on the combined process, and further determine the output products of the unreported process steps. After determining the aforementioned data, it is also possible to generate a filling prompt message indicating unreported process steps and corresponding output products, or generate a filling data frame for filling in the output products corresponding to the unreported process steps, in a method similar to that mentioned above.

[0052] By adopting the aforementioned S140 - S160, through automatically identifying the process flow of the combined process, it is possible to achieve automatic verification of the data to be filled in for the combined process in an automated manner without manual review, improving work efficiency and also reducing the problem of errors caused by the filling personnel's lack of understanding of the process.

[0053] For example, a coking enterprise produces coke from coking coal. Since coking belongs to one of the aforementioned combined process industries, combined process quality control is required. The complete combined process in the coking industry is: coal charging ground station, coke pushing ground station, coke oven chimney, general emission port, and fugitive emissions. However, a certain enterprise's coking production line did not account for the coke pushing ground station. According to the aforementioned method, it can be identified that the accounting of the coke pushing ground station is missing, and a filling data frame for filling in the data of the coke pushing ground station can be generated.

[0054] In addition to the aforementioned missing data filling in the enterprise's filled data, there may also be problems with incorrect numerical data filling. The following is a solution for identifying possible incorrect filled numerical data.

[0055] Figure 3 It is a flowchart of a method for determining abnormal numerical data provided in some embodiments of the present disclosure. In some embodiments, in the case where the filled data includes first numerical data related to raw material consumption or output product output, the quality control method for the filled data may further include the following S170 - S180.

[0056] S170: Determine whether the first numerical data is outside the normal production activity level range; if so, execute S180.

[0057] S180: Generate a prompt message indicating whether the first numerical data is abnormally filled data.

[0058] Based on a large amount of data experience, it is found that for pollution-emitting enterprises with generally the same scale in the same industry, the raw material consumption or the output of output products has a specific numerical range. Based on this, in the embodiments of the present disclosure, when determining the industry type and enterprise scale of a pollution-emitting enterprise, historical data related to the corresponding raw material consumption or output product output of similar enterprises will be obtained, and the historical data will be statistically analyzed to determine the normal production activity level range of enterprises of the corresponding scale.

[0059] In a specific implementation, the quartile method can be used to perform statistical analysis on the historical numerical data of enterprises of corresponding scales, determine the quartile values, and use the box plot method to determine the normal threshold value based on the quartile values, and use the above-mentioned normal threshold value determination interval as the normal production activity level interval. For example, in some embodiments, by comprehensively collecting and integrating the historical data recorded in the emission source statistical table of different time periods, the normal production activity level intervals of 3481 different types and sizes of enterprises are listed in detail. These production activity level intervals cover various scale levels from small and micro handicraft workshops to medium and large-scale enterprises, and corresponding production activity level intervals are provided for various output products.

[0060] If the first numerical data is outside the normal production activity level range, it is determined that the first numerical data is abnormal reporting data, and thus corresponding prompt information is generated.

[0061] In specific implementation, it may be difficult to detect whether there is a problem with the data reported by the pollution-emitting enterprise simply from the first numerical data reported. By comparing the first numerical data reported by the pollution-emitting enterprise with the corresponding normal production activity level interval, abnormal numbers can be identified, reminding the enterprise data reporting personnel to complete the data reporting according to the specific situation, even if erroneous numerical data is found in the reported data. In addition, this method can also enable enterprises to more accurately determine the development trend of industry process technology, and then reasonably plan the direction of future technological improvements based on the technological evolution, so that enterprises can adapt to market competition. In specific implementation, in order to ensure the correctness of the normal activity level intervals of enterprises of all sizes, a dynamic update mechanism can also be used to readjust the normal production activity level interval according to the specific situation, thereby ensuring that the normal production activity level interval represents the actual situation of the industry.

[0062] In some embodiments, when it is determined that the first numerical data is outside the normal production activity level, it may be due to industry cycles, enterprise production line transformation, etc., which is inconsistent with the actual situation. To solve this problem, when it is determined that the first numerical data is outside the normal production activity level, the following S190-S210 may be performed first.

[0063] S190: Determine whether there is second numerical data associated with the first numerical data in the reported data; if yes, execute S200; if not, execute S180.

[0064] S200: Calculate the actual correlation coefficient between the first numerical data and the second numerical data.

[0065] S210: Determine whether the actual correlation coefficient is outside the predetermined reasonable correlation coefficient range; if so, execute S180; if not, end the execution.

[0066] The aforementioned first numerical data is related to the second numerical data, and in most cases, it means that the first numerical data and the second numerical data have a positive correlation. For example, the relationship between the amount of coking coal used in the production line of a coking enterprise and the output of crude benzene produced during the coking process is approximately 100:1 (here, the reasonable coefficient range is set to 90:1 - 110:1). Correspondingly, if the reported output of crude benzene from a pollution-emitting enterprise is 100 tons (as the first numerical data), and the amount of coking coal used as raw material is 1,000,000 tons (as the second numerical data), the actual correlation coefficient between the first numerical data and the second numerical data is 1000:1. The actual correlation coefficient is clearly outside the pre-determined reasonable relationship coefficient range. At this time, it can be directly determined that the first numerical data is abnormally reported data, so S180 as described above can be executed.

[0067] Of course, in practical applications, when the first numerical data is related to the second numerical data, S190 - S210 as described above can also be only executed to identify whether the first numerical data is abnormal data. The aforementioned method determines whether the first reported data filled by a pollution enterprise is abnormal data through horizontal comparison. In other embodiments, vertical comparison can also be used to determine whether the first numerical data is abnormal data. Figure 4 It is a flowchart of a method for determining abnormal numerical data provided in still some other embodiments of the present disclosure. As Figure 4 shown, in some embodiments, the method for determining abnormal data includes S220 - S240 as follows.

[0068] S220: Obtain the historical numerical data of a pollution-emitting enterprise related to the corresponding raw material consumption or product output, and sort the historical numerical data according to time to obtain a sorted sequence.

[0069] For pollution-emitting enterprises such as refining enterprises, the shutdown cost of their production lines is extremely high after startup. Even if the enterprise has a loss problem, it still needs to maintain the normal production of the production line. In addition, if a pollution-emitting enterprise does not adjust its production capacity, its production activity level should follow the market law. Correspondingly, in this case, it is determined that the raw material consumption and product output of the enterprise have obvious data inertia and always remain within a relatively reasonable numerical range. Based on this, the embodiments of the present disclosure obtain the historical numerical data of a pollution-emitting enterprise related to the corresponding raw material consumption or product output, and sort the historical numerical data according to time to obtain a sorted sequence.

[0070] S230: Based on the sorted sequence, identify whether the first numerical data is abnormal data; if so, execute S240.

[0071] S240: Generate a prompt message indicating that the first numerical data may be abnormally reported data.

[0072] After obtaining the sorted sequence, numerical analysis can be performed on the sorted sequence to determine a reasonable statistical range and determine whether the first numerical data is within the reasonable statistical range. If it is determined based on the sorted sequence that the first numerical data is not within the reasonable statistical range, the first numerical data is determined to be abnormal data.

[0073] In a specific application, historical data of a polluting enterprise's specific raw materials or products in the past three years can be sorted to construct a sorted sequence, and the first numerical data is added to the data sequence. If it is observed that the first numerical data shows a significant fluctuation in the data sequence (for example, a sharp increase, reaching ten times or more of other data), it is determined that the first numerical data is already an outlier abnormal data, and thus a corresponding prompt message is generated.

[0074] In specific implementation, it may be incorrect to identify the first numerical data as abnormal data using the sorted sequence. For example, when an enterprise enters the production capacity ramp-up stage after a trial operation, its raw material consumption and product output may show a sharp increase. In this case, during the execution of S240, the aforementioned S190 - S210 may be executed again to further determine whether the data is abnormal.

[0075] In addition, in specific implementation, the raw materials and product output of polluting enterprises are also affected by industry development trends and market demands. In this case, the industry development trend and market demand can also be used as reference factors (for example, determining a reasonable scaling factor range based on the industry development trend or market demand, and comparing the scaling factor range with the historical data mean) to determine whether the first numerical data is abnormal data.

[0076] In some embodiments, the filled data also includes basic data. The basic data includes the specific information of the production line, the detailed description of the production process, and the classification description of the raw material types. In this case, when the filled data includes numerical data related to raw material consumption or product output, the following S250 - S260 can also be executed.

[0077] S250: Perform semantic information mining based on the basic information, numerical data, and the attributes of the numerical data to determine whether there is abnormal data in the numerical data; if so, execute S260.

[0078] S260: Determine the target numerical data identified as abnormal data, and generate a prompt message indicating that the target numerical data is abnormal data.

[0079] In specific implementation, semantic information mining is performed based on basic information, numerical data, and attribute information of the numerical data. This can be achieved by inputting the aforementioned information into a pre-trained language recognition model to determine whether the numerical data and the corresponding attribute information conflict with the basic information. If there is a conflict and the probability of the aforementioned conflict reaches a preset probability, the corresponding numerical data is determined to be abnormal data. Correspondingly, a language recognition model can be used to determine which numerical data is the target numerical data identified as abnormal data, and then a prompt message indicating that the target numerical data is abnormal data is generated.

[0080] In specific implementation, the method can be used to identify abnormal data at specific points in the reported data, prompting enterprises that there may be problems such as inaccurate time records or opaque production activity levels when reporting production activity levels, thereby prompting enterprises to improve the integrity and transparency of the reported data and ensuring the authenticity and reliability of data reporting. More specifically, this method can identify whether the numerical data reported for some production lines is abnormal data when the reporting enterprise includes combined processes and a single process in the combined process includes multiple production lines.

[0081] In some other more specific applications, it is considered that the market conditions will also affect the determination of whether the data is abnormal. In this case, market industry data can also be obtained. The market industry data includes historical data or predicted data related to the market state of the industry to which the pollution emission enterprise belongs. Correspondingly, the aforementioned S250 can be further refined as: performing semantic information mining based on basic information, numerical data, attribute information of the numerical data, and market industry data to determine whether the numerical data is abnormal data.

[0082] As analyzed above, the quality control method for pollution reporting data provided by the embodiments of the present disclosure uses data analysis technology and combines the specific industry characteristics of enterprises to establish a pollution reporting data instruction method based on industry characteristics and data fusion, realizing precise quality control of emission source data. Through process monitoring and automated correction prompts, the data processing efficiency and accuracy can be significantly improved, and human errors and malicious interventions in the data reporting stage can be reduced. In addition, if a certain data is determined to be abnormal data by using this method but the enterprise verifies that the relevant data is normal data, it can also prompt the enterprise to discover potential problems in production activities, provide reliable decision-making support, and increase the transparency and scientific nature of management.

[0083] In addition to providing the aforementioned method for statistically calculating the volatile organic compound emissions in the storage and transportation link, the embodiments of the present disclosure also provide a computing device for implementing the aforementioned method. Figure 5 It is a schematic structural diagram of the computing device provided by the embodiments of the present disclosure. Specifically, refer to Figure 5 below, which shows a schematic structural diagram of the computing device 500 suitable for implementing the embodiments of the present disclosure. Figure 5The computing device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0084] As Figure 5 shown, the computing device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501, which may perform various appropriate actions and processes according to a program in the read-only memory ROM 502 or a program loaded from the storage device 508 into the random access memory RAM 503. In the RAM 503, various programs and data required for the operation of the computing device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. The input / output I / O interface 505 is also connected to the bus 504.

[0085] Generally, the following devices may be connected to the I / O interface 505: an input device 505 including, for example, a touch screen, a touchpad, a camera, a microphone, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the computing device 500 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 5 the computing device 500 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0086] Specifically, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

[0087] It should be noted that the above-mentioned computer-readable medium of the present disclosure may be a computer-readable storage medium, a computer-readable signal medium, or any combination of the above two.

[0088] A computer-readable storage medium may, for example, but is not limited to, a system, apparatus, or device of electricity, magnetism, optics, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0089] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0090] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of the communication network include a local area network (“LAN”), a wide area network (“WAN”), the Internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future-developed network.

[0091] The above computer-readable medium may be included in the above computing device; or may exist separately without being assembled into the computing device.

[0092] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the tester's computer, partially on the tester's computer, execute as a stand-alone software package, execute partially on the tester's computer and partially on a remote computer, or execute entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the tester's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0094] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. Wherein, the name of the unit does not constitute a limitation to the unit itself in some cases. The functions described above herein may be performed at least in part by one or more hardware logic components. For example, by way of non-limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0095] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for quality control of data reported by pollution emission enterprises, characterized in that: include: Mining and analyzing the production technology and production process data of various industries, and building a raw material-output product association database, which includes the input-output association relationship of the production technology, raw materials, terminal output products, and intermediate output products of various industries; In the case of receiving the reported data of the pollution emission enterprise, querying the raw material-output product association database based on the reported data to determine the possible unreported data; the reported data includes at least one of the industry, production process, part of the raw materials, part of the terminal output products and part of the intermediate output products; the possible unreported data includes at least one of the unreported initial raw materials, unreported intermediate products and unreported terminal output products; Generate a corresponding reporting data box and / or reporting prompt information based on the possibly unreported data; The reported data box is used to receive the possible unreported data of the corresponding attribute, and the reported prompt information is used to prompt the existence of the possible unreported data.

2. The method according to claim 1, characterized in that Mining and analyzing the production technology and production process data of various industries, building a raw material-output product association database, including: Collect historical reporting data and standardize them to obtain standardized names for various raw materials and output products; Based on the production processes of various industries and the input-output relationship in the production process data, a raw material-output product association database with standardized naming under various production processes is established.

3. The method according to claim 1 or 2, characterized in that: Also includes: In the case where the reported data include process steps of a production process, determine whether the production process of the pollution-emitting enterprise is a combined process; In the case where the production process is determined to be a combination process, determining the unreported process steps based on the reported process steps and the corresponding combination process, and determining the output products of the unreported process steps based on the raw material-product association database; Generate reporting prompt information to indicate that there are unreported process steps and corresponding output products, and / or generate a reporting data frame for reporting the output products corresponding to the unreported process steps.

4. The method according to claim 1 or 2, characterized in that: In the case where the reported data includes first numerical data related to raw material consumption or output product yield, the method further includes: Determine whether the first numerical data is outside a normal production activity level interval, wherein the normal production activity level interval is determined by statistically analyzing historical numerical data, and the historical numerical data is obtained based on the industry type and enterprise scale of the pollution-emitting enterprise and the corresponding raw material consumption or output product output of similar enterprises; In the case where the first numerical data is outside the normal production activity level, prompt information is generated to determine whether the first numerical data is abnormal reporting data.

5. The method according to claim 4, characterized in that In the case where the first numerical data is outside the normal production activity level, generating prompt information for determining whether the first numerical data is abnormal reporting data further includes: Determining whether there is second numerical data associated with the first numerical data in the reported data; When the reported data includes second numerical data associated with the first numerical data, calculating an actual correlation coefficient between the first numerical data and the second numerical data; Determine whether the actual correlation coefficient is outside the predetermined reasonable correlation coefficient range; When the actual correlation coefficient is outside the predetermined reasonable correlation coefficient interval, prompt information is generated to determine whether the first numerical data is abnormal reported data.

6. The method according to claim 1 or 2, characterized in that: In the case where the reported data includes first numerical data related to raw material consumption or output product yield, the method further includes: Obtaining historical numerical data of the pollution-emitting enterprise involving corresponding raw material consumption or output product output, and sorting the historical numerical data according to time to obtain a sorted sequence; identifying whether the first numerical data is abnormal data based on the sorting sequence; In the case where the first numerical data is abnormal data, prompt information is generated to determine whether the first numerical data is abnormal reported data.

7. The method according to claim 1 or 2, characterized in that: In the case where the reported data includes two numerical data related to raw material consumption and / or output product output and the two numerical data are determined to be relevant data based on the production process adopted by the pollution-emitting enterprise, the method further includes: Calculating an actual correlation coefficient based on the two numerical data, and determining whether the actual correlation coefficient is outside a predetermined reasonable correlation coefficient interval; When the actual correlation coefficient is outside the predetermined reasonable correlation coefficient interval, prompt information is generated indicating that at least one of the two numerical data is abnormal data.

8. The method according to claim 1 or 2, characterized in that: The reported data includes basic information, including specific information of the production line, detailed description of the production process and classification description of raw material types; The method further includes: in a case where the reported data includes numerical data related to raw material consumption or output product output, performing semantic information mining based on the basic information, the numerical data, and attributes of the numerical data to determine whether there is abnormal data in the numerical data; In the case where it is determined that there is abnormal data in the numerical data, target numerical data identified as abnormal data is determined, and prompt information that the target numerical data is abnormal data is generated.

9. The method according to claim 8, characterized in that Also includes: Obtaining market industry data; the market industry data includes historical data and / or forecast data related to the market status of the industry to which the pollution-emitting enterprise belongs; Performing semantic information mining based on the basic information, the numerical data, and the attributes of the numerical data to determine whether there is abnormal data in the numerical data includes: Semantic information mining is performed based on the basic information, the numerical data, the attribute information of the numerical data and the market industry data to determine whether the numerical data has abnormal data.

10. A computing device, characterized in that It includes a storage device and a processor, wherein the storage device is used to store a computer program; when the computer program is loaded by the processor, the processor executes the method for quality control of data reported by pollution emission enterprises as described in any one of claims 1 to 9.

Images