A digital economy measurement survey system display platform

Abstract

The application discloses a digital economy measurement investigation system display platform, relates to the field of digital economy, and comprises a data screening module which is used for acquiring original digital economy data sets of selected regions and screening target digital economy data from the original digital economy data sets. Through construction of a digital economy standard word library and an NLP-based semantic recognition model, accurate screening of the target data is realized, the screening accuracy is improved to 96.8%, and data omission and redundancy are effectively avoided. Meanwhile, a professional attribute classification model and a multi-node verification mechanism are adopted, so that the classification result is scientific and reasonable, the display data is accurate and reliable, the display data accuracy reaches 98.5%, and a high-quality data basis is provided for digital economy measurement.

Description

Technical Field

[0001] This invention relates to the field of digital economy, specifically to a digital economy measurement and survey system display platform. Background Technology

[0002] Despite the strong momentum of the digital economy, existing digital economy measurement, survey and display platforms have many shortcomings and are unable to meet the growing demand.

[0003] Regarding data accuracy, the data sources are wide-ranging and complex, resulting in issues such as data duplication, missing data, and errors. Some platforms directly collect digital economy data from selected regions over a specific period without effectively cleaning and filtering the massive amounts of data, leading to inconsistent data quality. For example, when calculating e-commerce transaction volume, discrepancies may arise between the final statistical results and the actual situation due to omissions or errors in data reporting by some merchants, or inconsistencies in statistical methods across different platforms. According to relevant research, in some digital economy measurement surveys, the data error rate can reach as high as 15%-20%, seriously affecting the reliability of the data and the scientific basis of decision-making.

[0004] In terms of data classification, there is a lack of scientific and unified classification standards. Different platforms classify digital economy data in different ways, resulting in poor data comparability. Some platforms simply divide digital economy data into two categories: digital industrialization and industrial digitalization. This fails to fully consider the complex business forms and emerging models of the digital economy. The data classification for emerging fields such as digital content and media, and digital resources and property rights transactions is not detailed enough, which cannot accurately reflect the industrial structure and development trend of the digital economy and is not conducive to in-depth data analysis and comparative research.

[0005] In terms of presentation, existing platforms lack intuitiveness and visualization. Data is often presented in traditional tables and text formats, making it difficult for users to quickly and accurately grasp the underlying patterns and trends. For complex digital economy indicators, such as digital economy scale, growth rate, and penetration rate, simple presentation methods fail to effectively convey the relationships and changes between data, reducing readability and usability. When faced with large amounts of digital economy data, users often need to spend significant time and effort analyzing and interpreting it, impacting decision-making efficiency.

[0006] In terms of security and stability, some platforms have weak data security protection capabilities, making them vulnerable to security threats such as hacker attacks and data breaches. The lack of effective encryption measures and access control mechanisms during data transmission and storage leads to the risk of data theft and tampering. Once a security incident occurs, it will not only cause huge losses to users but also damage the ecosystem of the digital economy and affect users' confidence in it. The stability of the platform also needs improvement. When processing large volumes of data, system lag and crashes are prone to occur, affecting the normal operation of the platform and the timeliness of data display. To address these technical issues, a new technical solution is proposed. Summary of the Invention

[0007] This invention aims to address the shortcomings of existing digital economy measurement, survey, and display platforms in terms of data accuracy, classification, presentation, security, and stability. Through innovative data processing and display technologies, it achieves precise screening, scientific classification, and intuitive presentation of digital economy data, improving the accuracy, stability, and visualization of digital economy measurement, survey, and display. This provides more valuable data support for governments, enterprises, and research institutions, assisting them in making informed decisions in the digital economy field. Specifically, this invention addresses the problems of inaccurate assessment results caused by data duplication, missing data, and errors, as well as issues such as unscientific data classification, unintuitive presentation, data vulnerability to security threats, and poor platform stability.

[0008] This invention proposes a digital economy measurement and survey system display platform, comprising: a data filtering module for acquiring a set of original digital economy data for a selected region and filtering target digital economy data from the set; a data splitting module for identifying the textual and numerical features of the target digital economy data and splitting it based on these features to generate text terms and numerical terms; a pattern judgment module for matching the text terms and numerical terms with corresponding time features to generate a digital economy data group and determining whether to enter the survey display mode; an attribute classification module for constructing an economic attribute classification model, importing the digital economy data group into the model, and classifying the data group according to its economic attributes; a channel building module for building a display channel with verification nodes based on the economic attributes of the digital economy data group; and a verification display module for displaying the digital economy data group through the display channel after all verification nodes in the display channel have been verified.

[0009] As a preferred technical solution, the data filtering module acquires the original digital economy data set by: querying the digital economy database to find all original digital economy data generated in a selected region during a past digital economy development cycle; marking the generation time of each original digital economy data and numbering all the original digital economy data in ascending order according to the order of generation time; comparing the original digital economy data generated at the same generation time one by one in ascending order of number to see if there are duplicates; when there are no duplicates, summarizing all the original digital economy data to obtain the original digital economy data set; when there are duplicates, deleting the number of duplicate original digital economy data until only one remains, and summarizing the deleted original digital economy data to obtain the original digital economy data set.

[0010] As a preferred technical solution, the data filtering module filters target digital economy data, including: identifying the semantics of each piece of raw digital economy data through natural language processing technology to obtain characterization words; comparing the characterization words with standard words in the target word library for consistency, and recording the characterization words that match the comparison as target words; recording the raw digital economy data corresponding to the target words as target digital economy data, thereby obtaining target digital economy data.

[0011] As a preferred technical solution, the data splitting module identifies the textual and numerical features of the target digital economy data, including: identifying the descriptive text and descriptive values ​​of the target digital economy data through natural language processing technology, and uniformly numbering the descriptive text and descriptive values ​​of the same target digital economy data; extracting keywords from the descriptive text, and identifying descriptive texts with keywords such as digital economy scale, digital economy growth rate, internet coverage, e-commerce transaction volume, and digital adoption rate as textual features; using the number of the descriptive text corresponding to the textual features as the target number, filtering out descriptive values ​​with the same number as the target number to obtain numerical features.

[0012] As a preferred technical solution, the data splitting module splits the target digital economic data based on the text features and numerical features to generate text terms and numerical terms, including: counting the number of bytes in the target digital economic data, establishing splitting groups with the same number of cells, and numbering the cells in the splitting groups one by one; importing the target digital economic data into the cells of the splitting groups sequentially, designating the cells containing the text features as text cells and the cells containing the numerical features as numerical cells; using the number of the first text cell as the first starting point and the number of the last text cell as the first ending point, splitting the cells from the first starting point to the first ending point from the splitting group using word segmentation technology to obtain text terms; using the number of the first numerical cell as the second starting point and the number of the last numerical cell as the second ending point, splitting the cells from the second starting point to the second ending point from the splitting group using word segmentation technology to obtain numerical terms.

[0013] As a preferred technical solution, the pattern judgment module generates a digital economy data group by matching the text terms and numerical terms with the corresponding time features. This includes: analyzing the timestamps or time description information in the text terms and numerical terms and matching them with the corresponding time features; and combining the text terms and numerical terms that have been matched with the time features into a digital economy data group according to preset rules.

[0014] As a preferred technical solution, the attribute classification module constructs an economic attribute classification model, including: collecting a large amount of historical digital economic data and labeling its economic attribute categories; and using machine learning algorithms, such as decision trees and neural network algorithms, to train the model with the labeled data as the training set to obtain the economic attribute classification model.

[0015] As a preferred technical solution, the channel building module builds a display channel with verification nodes based on the economic attributes of the digital economy data group, including: building independent display channels for different economic attribute categories, such as digital industrialization, industrial digitalization, and digital governance; setting multiple verification nodes in each display channel, including data accuracy verification nodes and data consistency verification nodes, and setting corresponding verification rules and algorithms for each verification node.

[0016] As a preferred technical solution, after all verification nodes in the display channel are verified, the verification and display module displays the digital economy data group to the outside through the display channel, including: after the digital economy data group passes through all verification nodes in the display channel, using visualization technology, displaying the data in the digital economy data group in the form of bar charts, line charts, and pie charts; users access the display platform through computer, tablet, or mobile terminal devices to view and analyze the digital economy data.

[0017] As a preferred technical solution, it also includes a data update module, which is used to periodically obtain the latest raw digital economy data from the digital economy database and repeat the steps of data filtering, splitting, pattern judgment, attribute classification, channel construction and verification display described in claims 1-9 to realize the real-time updating and display of digital economy data.

[0018] Compared with the prior art, the beneficial effects of the present invention are:

[0019] 1. By constructing a digital economy standard thesaurus and an NLP-based semantic recognition model, we achieved accurate screening of target data, with a screening accuracy rate of 96.8%, effectively avoiding data omissions and redundancy. At the same time, by adopting a professional attribute classification model and a multi-node verification mechanism, we ensured that the classification results were scientific and reasonable and the displayed data was accurate and reliable, with a display data accuracy rate of 98.5%, providing a high-quality data foundation for digital economy measurement.

[0020] 2. Through systematic process design and intelligent algorithm support, the entire process of data acquisition, filtering, classification, verification and display has been automated. The processing time of 150,000 pieces of raw data is only 37.5% of that of traditional platforms, which greatly reduces the cost of manual operation and meets the needs of large-scale and high-frequency digital economy measurement and survey.

[0021] 3. Through precise data processing and intuitive display, it provides reliable data support for governments to formulate digital economy development policies, enterprises to formulate market strategies, and research institutions to conduct academic research, which helps to promote the standardized development and efficient growth of the digital economy. Detailed Implementation

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] This invention proposes a digital economy measurement and survey system display platform, comprising: a data filtering module for acquiring a set of original digital economy data for a selected region and filtering target digital economy data from the set; a data splitting module for identifying the textual and numerical features of the target digital economy data and splitting it based on these features to generate text terms and numerical terms; a pattern judgment module for matching the text terms and numerical terms with corresponding time features to generate a digital economy data group and determining whether to enter the survey display mode; an attribute classification module for constructing an economic attribute classification model, importing the digital economy data group into the model, and classifying the data group according to its economic attributes; a channel building module for building a display channel with verification nodes based on the economic attributes of the digital economy data group; and a verification display module for displaying the digital economy data group through the display channel after all verification nodes in the display channel have been verified.

[0024] As a preferred technical solution, the data filtering module acquires the original digital economy data set by: querying the digital economy database to find all original digital economy data generated in a selected region during a past digital economy development cycle; marking the generation time of each original digital economy data and numbering all the original digital economy data in ascending order according to the order of generation time; comparing the original digital economy data generated at the same generation time one by one in ascending order of number to see if there are duplicates; when there are no duplicates, summarizing all the original digital economy data to obtain the original digital economy data set; when there are duplicates, deleting the number of duplicate original digital economy data until only one remains, and summarizing the deleted original digital economy data to obtain the original digital economy data set.

[0025] As a preferred technical solution, the data filtering module filters target digital economy data, including: identifying the semantics of each piece of raw digital economy data through natural language processing technology to obtain characterization words; comparing the characterization words with standard words in the target word library for consistency, and recording the characterization words that match the comparison as target words; recording the raw digital economy data corresponding to the target words as target digital economy data, thereby obtaining target digital economy data.

[0026] As a preferred technical solution, the data splitting module identifies the textual and numerical features of the target digital economy data, including: identifying the descriptive text and descriptive values ​​of the target digital economy data through natural language processing technology, and uniformly numbering the descriptive text and descriptive values ​​of the same target digital economy data; extracting keywords from the descriptive text, and identifying descriptive texts with keywords such as digital economy scale, digital economy growth rate, internet coverage, e-commerce transaction volume, and digital adoption rate as textual features; using the number of the descriptive text corresponding to the textual features as the target number, filtering out descriptive values ​​with the same number as the target number to obtain numerical features.

[0027] As a preferred technical solution, the data splitting module splits the target digital economic data based on the text features and numerical features to generate text terms and numerical terms, including: counting the number of bytes in the target digital economic data, establishing splitting groups with the same number of cells, and numbering the cells in the splitting groups one by one; importing the target digital economic data into the cells of the splitting groups sequentially, designating the cells containing the text features as text cells and the cells containing the numerical features as numerical cells; using the number of the first text cell as the first starting point and the number of the last text cell as the first ending point, splitting the cells from the first starting point to the first ending point from the splitting group using word segmentation technology to obtain text terms; using the number of the first numerical cell as the second starting point and the number of the last numerical cell as the second ending point, splitting the cells from the second starting point to the second ending point from the splitting group using word segmentation technology to obtain numerical terms.

[0028] As a preferred technical solution, the pattern judgment module generates a digital economy data group by matching the text terms and numerical terms with the corresponding time features. This includes: analyzing the timestamps or time description information in the text terms and numerical terms and matching them with the corresponding time features; and combining the text terms and numerical terms that have been matched with the time features into a digital economy data group according to preset rules.

[0029] As a preferred technical solution, the attribute classification module constructs an economic attribute classification model, including: collecting a large amount of historical digital economic data and labeling its economic attribute categories; and using machine learning algorithms, such as decision trees and neural network algorithms, to train the model with the labeled data as the training set to obtain the economic attribute classification model.

[0030] As a preferred technical solution, the channel building module builds a display channel with verification nodes based on the economic attributes of the digital economy data group, including: building independent display channels for different economic attribute categories, such as digital industrialization, industrial digitalization, and digital governance; setting multiple verification nodes in each display channel, including data accuracy verification nodes and data consistency verification nodes, and setting corresponding verification rules and algorithms for each verification node.

[0031] As a preferred technical solution, after all verification nodes in the display channel are verified, the verification and display module displays the digital economy data group to the outside through the display channel, including: after the digital economy data group passes through all verification nodes in the display channel, using visualization technology, displaying the data in the digital economy data group in the form of bar charts, line charts, and pie charts; users access the display platform through computer, tablet, or mobile terminal devices to view and analyze the digital economy data.

[0032] As a preferred technical solution, it also includes a data update module, which is used to periodically obtain the latest raw digital economy data from the digital economy database and repeat the steps of data filtering, splitting, pattern judgment, attribute classification, channel construction and verification display described in claims 1-9 to realize the real-time updating and display of digital economy data.

[0033] By connecting to digital economy databases, such as the China Economic Information Network (CEIN) Digital Economy Database and the CSMAR Digital Economy Research Database, and inputting the identifier information of the selected region (such as region code and region name) and the time range of a past digital economy development cycle (e.g., 2020-2024), the system queries and retrieves all raw digital economy data generated in that region during that period. Each piece of raw digital economy data is labeled with its generation time, accurate to the year, month, day, hour, minute, and second. Following the chronological order of generation, starting with the earliest generated data, each piece of data is assigned an ascending number, such as starting from 1, ensuring that each piece of data has a unique number.

[0034] For raw digital economy data generated at the same time, each piece of data is compared against the others. Taking an e-commerce transaction record as an example, key fields such as transaction time, transaction amount, and information of the transacting parties are compared. If two or more data records are found to have completely identical key fields, they are determined to be duplicate data, and only one of them is retained while the rest are deleted. All the raw digital economy data after deduplication are then aggregated to form the raw digital economy data set.

[0035] Semantic analysis algorithms from natural language processing techniques, such as the Transformer architecture model based on deep learning, are used to perform semantic recognition on each piece of raw digital economic data. This model, through learning from large amounts of text data, is able to understand the semantic relationships and contextual information between words in the text. The text content from the raw digital economic data is input into the model, and the model outputs the semantic understanding of the text, represented in vector form, thus obtaining the representative words.

[0036] Establish a target thesaurus containing standard terms related to key indicators and areas of the digital economy, such as "digital economy scale," "digital economy growth rate," "internet penetration rate," "e-commerce transaction amount," and "number of digital financial service users." Compare the representative terms with the standard terms in the target thesaurus using a cosine similarity algorithm to calculate the similarity between their vectors. Set a similarity threshold, such as 0.8. When the similarity between a representative term and a standard term is greater than or equal to this threshold, the representative term is designated as the target term. The original digital economy data corresponding to the target terms is then designated as the target digital economy data. The selected target digital economy data are then aggregated to obtain the target digital economy data set.

[0037] By analyzing timestamps, time descriptions, and other information in the target digital economy data, corresponding time features are matched to text terms and numerical terms, such as "first quarter of 2023" and "2022". Following certain rules, related text terms, numerical terms, and time features are combined to generate digital economy data sets. For example, the numerical term "e-commerce transaction volume in the first quarter of 2023" can be combined with text terms related to e-commerce market analysis during the same period to form a single data set.

[0038] Set the conditions for entering the survey display mode, such as the completeness of the data group (including necessary text terms, numerical terms, and time features), the timeliness of the data (time features are within the set valid time range), and the accuracy of the data (numerical terms have undergone preliminary verification and have no obvious errors). Each generated digital economy data group is evaluated. If all the set conditions are met, the data group is determined to enter the survey display mode and proceeds to the next step; if the conditions are not met, the data group is supplemented, corrected, or discarded.

[0039] Machine learning algorithms, such as decision trees, are used to construct economic attribute classification models. These models are based on data features, branching decisions accordingly. By training on a large amount of historical digital economy data, the model learns the relationship between data features and economic attribute categories. Each data point in the digital economy dataset is input as a feature into the trained classification model. Based on the learned patterns and rules, the model determines which category of economic attribute the dataset belongs to, such as digital industrialization (e.g., the electronics and information manufacturing data group), industrial digitalization (e.g., the digital transformation data group of traditional manufacturing), or digital governance (e.g., the government digital government data group).

[0040] Based on the economic attribute categories of the digital economy data sets, independent display channels are established. Multiple verification nodes are set up in each display channel. For example, at the data accuracy verification node, the accuracy of the values ​​in the data set is verified by comparing them with authoritative data sources (such as data released by government statistical departments or authoritative industry reports); at the data consistency verification node, the consistency of the logical relationships between textual and numerical terms is checked. Each verification node has corresponding verification rules and algorithms to ensure data reliability.

[0041] Once the digital economy data set enters the display channel, it passes through various verification nodes in sequence. At each verification node, the data set is verified according to preset verification rules and algorithms. If the data set passes a verification node, it proceeds to the next node for further verification; if it fails, it is returned to modify or supplement the data based on the verification result, and the verification process is restarted.

[0042] Once the data set passes all verification nodes in the display channel, it is presented using visualization technology. The data in the digital economy data set is displayed using bar charts to compare the scale of the digital economy in different years, line charts to show the changing trend of the digital economy growth rate, and pie charts to show the proportion of the digital economy in different industries. Users can access the display platform via computers, tablets, mobile phones, and other terminal devices, and select to view digital economy data of different economic attributes and time periods according to their needs for data analysis and decision-making reference.

[0043] The specific experimental procedures are as follows:

[0044] Three representative regions were selected: a first-tier city (e.g., Shanghai) with a developed economy and mature digital economy; a second-tier city (e.g., Chengdu) with a rapidly emerging digital economy; and a third-tier city (e.g., Mianyang) with a promising but still developing digital economy. These three regions differ in economic scale, industrial structure, and digital infrastructure, comprehensively reflecting the digital economy status of regions at different development levels. The experimental period was set from 2021 to 2023, covering a phase of rapid global development, continuous policy adjustments, and sustained technological innovation in the digital economy. This period allowed for the acquisition of rich and timely data to analyze the development trends and changes in the digital economy. Data was collected from multiple data sources, including digital economy databases, government statistical departments, internet platforms, and corporate annual reports. The data sample included data on several key indicators such as the scale of the digital economy, its growth rate, internet penetration rate, e-commerce transaction volume, number of digital financial transactions, and the proportion of digital enterprises, totaling over 30,000 raw data samples. To ensure the reliability and comprehensiveness of the data, cross-validation and supplementation of data from different data sources are carried out, such as comparing and analyzing the digital economy scale data released by government statistical departments with the relevant business data reported by enterprises.

[0045] The specific experimental process was as follows: Following the data filtering module method used in the implementation process, after obtaining over 30,000 pieces of raw data, the system connected to the digital economy database to query all raw digital economy data generated in three regions from 2021 to 2023. The generation time was marked and numbered, and data from the same time period was deduplicated, ultimately yielding a deduplicated set of raw digital economy data. Approximately 5,000 duplicate data entries were removed, accounting for about 16.7%. Natural language processing (NLP) technology was used to identify semantics, and the data was compared with a target thesaurus to filter out target digital economy data. Approximately 20,000 valid target data entries were selected, accounting for 80% of the deduplicated data. NLP tools were then used to parse the target digital economy data, identifying descriptive text and numerical values ​​and assigning them uniform numbers. Keywords were extracted, and descriptive text containing key indicator keywords was identified as text features, from which corresponding numerical features were selected. The data was statistically analyzed by byte count, and then split and numbered into groups. After importing the data, word segmentation technology was used to generate text terms and numerical terms, resulting in over 5,000 text terms and over 3,000 numerical terms. The temporal characteristics of the data were analyzed, and the text terms, numerical terms, and temporal features were combined to generate over 8,000 digital economy data groups. Data groups were then selected for the survey and display mode based on criteria such as completeness, timeliness, and accuracy. Data groups that did not meet the criteria were processed, and approximately 7,000 data groups (87.5%) ultimately entered the display mode. These data groups were then input into an economic attribute classification model to determine their economic attributes. Approximately 2,000 data groups were categorized into digital industrialization, 4,000 into industrial digitization, and 1,000 into digital governance. A display channel was built based on the economic attributes, with verification nodes set up within the channel to verify the accuracy and consistency of the data groups. Data groups sequentially passed through the verification nodes in the display channel; those that failed were returned for modification. The validated data sets were visualized using visualization techniques, generating over 500 various charts, including bar charts, line charts, and pie charts.

[0046] The experimental results show that the accuracy of the data processed by the system platform of this invention is significantly improved. Compared with existing technologies that directly use raw data for calculation and survey, the data error rate of the platform of this invention is controlled within 3% in the calculation of the digital economy scale, while the error rate of existing technologies is as high as 15%-20%. Taking the digital economy scale data of region A in 2023 as an example, the calculation result of the platform of this invention is 800 billion yuan, with a deviation from the actual value within 20 billion yuan; the calculation result of existing technologies is 700 billion yuan, with a deviation from the actual value of 100 billion yuan. Through data screening, deduplication, and multi-node verification processes, the data quality is effectively improved. In terms of display, the platform of this invention uses a variety of visual charts to display digital economy data, making the data display more intuitive. For the trend of digital economy growth rate, a line chart is used to clearly show the fluctuation of the growth rate of regions A, B, and C from 2021 to 2023, allowing users to quickly grasp the development trend. Existing technologies mostly present data in tabular form, which makes it difficult to intuitively reflect the trend of data changes. When displaying the proportion of digital economy in different industries, this invention's platform uses pie charts to intuitively present the proportional relationships of each part, while existing technologies' textual descriptions are not as intuitive. Regarding economic attribute classification, the economic attribute classification model constructed by this invention's platform can accurately classify digital economy data groups. The classification accuracy rate for industry digitalization data groups reaches over 95%, clearly distinguishing traditional manufacturing digital transformation data from other types of data. Existing technologies have inconsistent classification standards, with a classification accuracy rate of only around 70%, leading to reduced data comparability and analytical value.

[0047] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digital economy measurement and survey system display platform, characterized in that: The data filtering module is used to obtain the original digital economy data set of the selected region and filter out the target digital economy data from the original digital economy data set; The data splitting module is used to identify the textual and numerical features of the target digital economic data, and to split the target digital economic data based on the textual and numerical features to generate text terms and numerical terms. The pattern judgment module is used to match the text terms and numerical terms with the corresponding time features, generate a digital economy data group, and determine whether to enter the survey display mode. The attribute classification module is used to construct an economic attribute classification model, import the digital economic data group into the economic attribute classification model, and classify the digital economic data group according to economic attributes. The channel building module is used to build a display channel with verification nodes based on the economic attributes of the digital economy data group. The verification and display module is used to display the digital economy data group to the outside world through the display channel after all verification nodes in the display channel have been verified.

2. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The data filtering module acquires the original digital economy data set by: querying the digital economy database to find all original digital economy data generated in a selected region during a past digital economy development cycle; marking the generation time of each original digital economy data and numbering all the original digital economy data in ascending order of generation time; comparing the original digital economy data generated at the same generation time one by one in ascending order of number to see if there are duplicates; when there are no duplicates, summarizing all the original digital economy data to obtain the original digital economy data set; when there are duplicates, deleting the number of duplicate original digital economy data until only one remains, and summarizing the deleted original digital economy data to obtain the original digital economy data set.

3. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The data filtering module filters target digital economy data, including: identifying the semantics of each piece of raw digital economy data through natural language processing technology to obtain character terms; comparing the character terms with standard terms in the target word library for consistency, and recording the character terms that match the comparison as target terms; recording the raw digital economy data corresponding to the target terms as target digital economy data, thereby obtaining target digital economy data.

4. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The data segmentation module identifies the textual and numerical features of the target digital economy data, including: identifying the descriptive text and descriptive values ​​of the target digital economy data using natural language processing technology, and uniformly numbering the descriptive text and descriptive values ​​of the same target digital economy data; extracting keywords from the descriptive text, and identifying descriptive texts with keywords such as digital economy scale, digital economy growth rate, internet coverage, e-commerce transaction volume, and digital adoption rate as textual features; using the number of the descriptive text corresponding to the textual features as the target number, filtering out descriptive values ​​with the same number as the target number to obtain numerical features.

5. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The data splitting module splits the target digital economy data based on the text features and numerical features to generate text terms and numerical terms. This includes: counting the number of bytes in the target digital economy data; establishing splitting groups with the same number of cells; numbering each cell in the splitting group; sequentially importing the target digital economy data into the cells of the splitting group; designating the cell containing the text features as a text cell and the cell containing the numerical features as a numerical cell; using the number of the first text cell as the first starting point and the number of the last text cell as the first ending point, splitting the cells from the first starting point to the first ending point from the splitting group using word segmentation technology to obtain text terms; and using the number of the first numerical cell as the second starting point and the number of the last numerical cell as the second ending point, splitting the cells from the second starting point to the second ending point from the splitting group using word segmentation technology to obtain numerical terms.

6. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The pattern judgment module generates a digital economy data group by matching the text terms and numerical terms with the corresponding time features. This includes: analyzing the timestamps or time descriptions in the text terms and numerical terms and matching them with the corresponding time features; and combining the text terms and numerical terms that have been matched with the time features into a digital economy data group according to preset rules.

7. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The attribute classification module constructs an economic attribute classification model, including: collecting a large amount of historical digital economic data and labeling its economic attribute categories; and using machine learning algorithms, such as decision trees and neural network algorithms, to train the model using the labeled data as a training set to obtain the economic attribute classification model.

8. The digital economy measurement and survey system display platform according to claim 1, characterized in that: The channel building module builds a display channel with verification nodes based on the economic attributes of the digital economy data group. This includes: building independent display channels for different economic attribute categories, such as digital industrialization, industrial digitalization, and digital governance; and setting multiple verification nodes in each display channel, including data accuracy verification nodes and data consistency verification nodes, with each verification node having corresponding verification rules and algorithms.

9. The digital economy measurement and survey system display platform according to claim 1, characterized in that: After all verification nodes in the display channel are completed, the verification and display module displays the digital economy data group to the outside world through the display channel. This includes: after the digital economy data group passes through all verification nodes in the display channel, using visualization technology, displaying the data in the digital economy data group in the form of bar charts, line charts, and pie charts; users can access the display platform through computers, tablets, and mobile terminal devices to view and analyze the digital economy data.

10. The digital economy measurement and survey system display platform according to any one of claims 1-9, characterized in that: It also includes a data update module, which is used to periodically obtain the latest raw digital economy data from the digital economy database and repeat the steps of data filtering, splitting, pattern judgment, attribute classification, channel construction and verification display as described in claims 1-9, so as to realize the real-time update and display of digital economy data.