Industrial park investment attracting information processing method, system and device based on e-commerce big data and medium

Abstract

The invention provides an industrial park investment attracting information processing method, system and device based on e-commerce big data and a medium, and belongs to the technical field of e-commerce big data processing. Performing standardization processing on the e-commerce data and the enterprise industry and commerce data to form an integrated data set; constructing an e-commerce enterprise feature project; identifying transaction enterprises by comparing monthly change information of the enterprises, and forming a transaction enterprise directory library; constructing an industrial park feature project based on the industrial park demand information; and obtaining matching degree scores of the enterprises and the park demands by comprehensively calculating enterprise scores, and generating an investment attraction recommendation enterprise list according to high-low ranking of the scores. According to the invention, from data collection and processing to enterprise feature analysis and transaction identification, and then to park feature construction and enterprise matching recommendation, comprehensive evaluation of e-commerce enterprises and accurate matching with park demands are realized, and the precision, efficiency and success rate of industrial park investment attraction are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of e-commerce big data processing, and specifically relates to an industrial park investment promotion information processing method, system, equipment and medium based on e-commerce big data. Background Art

[0002] In the field of industrial park investment promotion, traditional methods of processing investment promotion information primarily rely on information proactively submitted by enterprises, offline research conducted by investment promotion personnel, and a limited amount of publicly available data. This approach has numerous limitations. For one thing, the information source is narrow. Relying solely on enterprise self-reporting and limited offline research makes it difficult to comprehensively and accurately obtain key information such as a company's operating conditions and market potential. This results in investors' limited understanding of the company, which can lead to missed opportunities for high-quality investment targets or the introduction of companies that are not well-suited to the park's development.

[0003] With the booming development of e-commerce, the number of e-commerce companies has increased dramatically. The massive amount of data generated by this data contains a wealth of business information, providing new data sources and insights for industrial park investment promotion. However, relevant industrial park investment promotion information processing technologies still face many challenges when dealing with e-commerce big data. In terms of data acquisition and processing, different e-commerce platforms and industrial and commercial data sources have different data formats, encodings, and standards, making data integration difficult. Furthermore, there is a lack of effective data cleaning and standardization methods, resulting in inconsistent data quality and making it unsuitable for direct investment promotion analysis.

[0004] It is difficult to accurately match the park's investment needs with the characteristics of enterprises. The park lacks clear quantitative standards for its own needs, and the enterprise evaluation indicators are single, which cannot fully consider the fit between the park's development strategy, industrial planning and enterprises. This leads to a lack of coordination between the introduction of enterprises and the development of the park, resulting in low accuracy in industrial park investment promotion and an inability to meet usage needs. Summary of the Invention

[0005] The present invention provides an industrial park investment promotion information processing method based on e-commerce big data. The method establishes an e-commerce enterprise directory and draws a panoramic portrait, uses an intelligent algorithm to achieve accurate recommendation of target enterprises for industrial park investment promotion, realizes a comprehensive evaluation of e-commerce enterprises and accurately matches them with the needs of the park, and effectively improves the accuracy, efficiency and success rate of industrial park investment promotion.

[0006] Methods include: S101: Obtain e-commerce data and business data; the e-commerce data includes the store's operating company information, location information, product shipping location information, and product sales information; the business data includes the company name, unified social credit code, establishment time, registered capital, number of employees, company type, residence, mailing address, and legal representative information; S102: Standardize the e-commerce data and the enterprise business data, and associate the data with the store ID and the unified social credit code to form an integrated data set; S103: Obtaining basic information characteristics, regional characteristics, industry characteristics, and park characteristics of the enterprise, and constructing e-commerce enterprise feature engineering based on the integrated data set; S104: Based on the e-commerce enterprise feature engineering, by comparing the monthly change information of enterprises, identifying enterprises that have undergone changes in enterprise, enterprise address, or legal representative, and forming a directory of changed enterprises; S105: Constructing an industrial park feature engineering based on the industrial park demand information, generating regional characteristics, industrial characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converting them into quantifiable matching model parameters; S106: Based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering, the matching scores between the enterprises and the park needs are obtained by comprehensively calculating the enterprise scores, and a list of recommended enterprises for investment promotion is generated according to the ranking of the scores.

[0007] It should be further explained that the steps for obtaining the matching score between the enterprise and the park's needs by comprehensively calculating the enterprise score include: According to the entropy method, the basic information characteristics, regional characteristics, industry characteristics, sales scale characteristics, and market competitiveness characteristics of the enterprise are assigned corresponding weights, and the corresponding subordinate indicators are assigned corresponding weights; Arrange the collected data of each subordinate indicator according to individual enterprises and construct a data matrix; Assuming there are n enterprises and m subordinate indicators, the data matrix is: X=(x ij ) n×m in, Indicates the value of the jth subordinate indicator of the i-th enterprise.

[0008] It should be further explained that the range standardization method is used to standardize the data in the data matrix. The standardization formula of the positive indicator is: =

[0009] in, is the normalized value, It is the element in the original data matrix, which realizes the conversion of the original data Map to within the interval; The proportion of the indicators is calculated based on the following formula, and the standardized data is converted into proportion form in order to calculate the information entropy; =

[0010] in, It represents the proportion of the jth indicator of the i-th enterprise in all indicators; The weight matrix is ​​as follows: P=(p ij ) n×m Calculate the information entropy of each e-commerce company : =-k

[0011] Among them, n is the number of e-commerce companies, k= ; The value range of information entropy is The interval reflects the degree of variation of the indicator.

[0012] It should be further explained that step S103 specifically includes: extracting various types of original data of the enterprise from the integrated data set, and supplementing the collection of the enterprise's basic information with information such as intellectual property rights, qualifications and honors by connecting to the intellectual property database and industry qualification certification platform; In terms of the characteristics of the industry to which it belongs, we combine the analysis of industry experts and the white paper on industrial development to judge the development status of the company in the emerging industry and its position in the industrial chain. According to pre-set rules and standards, we classify and organize the extracted and supplemented data and convert them into feature labels.

[0013] Integrate the feature labels of each dimension to form the feature engineering of e-commerce enterprises, and establish the correlation between the feature labels.

[0014] It should be further explained that step S104 also includes: extracting enterprise operating information based on the enterprise monthly data update, and comparing it with the enterprise operating information in historical records to identify abnormal characteristics; Combining industry policy keywords with the company's main business tags, a policy fit score is generated to assess the matching degree between the changing companies and the industrial direction of the park; The change records of legal representatives of affiliated enterprises and market supervision credit files are used to generate compliance risk scores, and differentiated investment promotion suggestions are pushed based on the scoring results.

[0015] It should be further explained that step S105 also includes: Analyze park investment policy documents, extract parameters such as land use scale, environmental protection level, and industrial synergy, and convert them into quantifiable indicators through natural language processing technology; Establish a semantic mapping relationship between demand characteristics and e-commerce enterprise characteristics. When an announcement of regional industrial structure adjustment is detected, adjust the matching weight of the associated indicators; perform spatiotemporal consistency verification and information compliance verification on enterprise characteristics and park demand parameters, and generate a matching report.

[0016] It is further necessary to explain that in the method, a knowledge base of investment attraction feedback is constructed, the business data of enterprises after they settle in the park and the evaluation records of investment attraction personnel are collected, and a feature validity evaluation model is established; Establish a regional industrial ecological simulation method to convert infrastructure parameters such as the transportation network and energy supply around the park into matching constraints; through spatiotemporal correlation analysis, verify the fit between the historical operating trajectory of the enterprise and the park development plan.

[0017] This application also provides an industrial park investment information processing system based on e-commerce big data, the system comprising: Data collection module, used to obtain e-commerce data and corporate industrial and commercial data; A data standardization and integration module is used to standardize the e-commerce data and enterprise industrial and commercial data, and associate the data with the unified social credit code through the store ID to form an integrated data set; An e-commerce enterprise feature construction module is used to obtain enterprise basic information features, regional features, industry features and park features, and to construct an e-commerce enterprise feature engineering based on the integrated data set; The module for identifying and building a list of companies that have changed, or whose domiciles have changed, or whose legal representatives have changed, is based on the e-commerce company feature engineering and compares the companies' monthly change information to identify those companies that have changed, or whose domiciles have changed, and forms a list of companies that have changed; A park feature engineering construction module constructs an industrial park feature engineering based on industrial park demand information, generates regional characteristics, industry characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converts them into quantifiable matching model parameters; The enterprise matching and recommendation list generation module is based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering. It obtains the matching score between the enterprise and the park demand by comprehensively calculating the enterprise score, and generates a list of recommended enterprises for investment promotion according to the ranking of the scores.

[0018] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for processing industrial park investment promotion information based on e-commerce big data when executing the program.

[0019] According to another embodiment of the present application, a storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the industrial park investment information processing method based on e-commerce big data are implemented.

[0020] It can be seen from the above technical solutions that the present invention has the following advantages: The industrial park investment promotion information processing method provided in this application collects e-commerce data and business data from mainstream e-commerce platforms, comprehensively covering key data such as business operations, registration, and sales. It standardizes and integrates heterogeneous data obtained from different channels, unifies data formats and encodings, eliminates data discrepancies, and constructs a structured, enterprise-centric data set, improving data quality and usability. It supplements information such as corporate intellectual property rights, qualifications, and honors, combines professional analysis to determine the company's position in emerging industries and industrial chains, and converts these into feature tags, enabling a more comprehensive and accurate portrayal of the company. It compares changes in key corporate information on a monthly basis to promptly identify changes in the company's operating entity, location, residence, legal representative, and other aspects, thereby improving the targeting of investment promotion. Feature engineering is constructed based on park needs, converting investment promotion policies and industrial planning into quantifiable model parameters. This clarifies park investment promotion standards and requirements, accurately aligning park characteristics with enterprise characteristics, and ensuring that the introduced enterprises are highly aligned with the park's development strategy. Scientific methods such as the entropy method are used to calculate the matching score between enterprises and park needs. Taking into account the multi-dimensional characteristics of enterprises, a recommendation list is generated based on the ranking of scores, and a dynamic tracking mechanism is established. It can provide accurate investment recommendations for the industrial park and improve the success rate of investment attraction. It can achieve a comprehensive assessment of e-commerce companies and accurately match them with the needs of the industrial park, effectively improving the accuracy, efficiency and success rate of investment attraction in the industrial park. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 This is a flow chart of the industrial park investment information processing method based on e-commerce big data; Figure 2 This is a schematic diagram of the industrial park investment information processing system based on e-commerce big data; Figure 3 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0023] The industrial park investment promotion information processing method based on e-commerce big data provided in this application aims to fully tap the potential value of e-commerce big data, establish an e-commerce enterprise directory and draw a panoramic portrait, and use intelligent algorithms to achieve accurate recommendations and dynamic early warning reminders for target enterprises for industrial park investment promotion, thereby overcoming the problems of insufficient accuracy and low efficiency of traditional investment promotion methods, and realizing accurate, efficient and intelligent investment promotion work.

[0024] The following describes in detail the specific steps of the method for processing industrial park investment information based on e-commerce big data involved in this application. For the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are provided to facilitate a thorough understanding of the embodiments of this application. However, it should be clear to those skilled in the art that this application can also be implemented in other embodiments without these specific details.

[0025] It should be understood that when used in this specification, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their collections. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0026] The phrases "one embodiment" or "some embodiments" described in this application mean that the specific features, structures, or characteristics described in the embodiment are included in one or more embodiments of the application. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. that appear in different places in this application do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized.

[0027] In embodiments of the present invention, computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or power server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (exemplarily via the Internet using an Internet service provider).

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] See also Figure 1 FIG. 1 is a flow chart of a method for processing industrial park investment information based on e-commerce big data in a specific embodiment, the method comprising: S101: Obtain e-commerce data and corporate business data; the e-commerce data includes the store's operating company information, location information, product shipping location information and product sales information; the corporate business data includes the company name, unified social credit code, establishment time, registered capital, number of employees, company type, residence, mailing address, and legal representative information.

[0030] In some embodiments, e-commerce data is collected from mainstream e-commerce platforms such as Tmall, JD.com, Taobao, and Doudian. This includes information on store operators, including the store name, ID, operating company information, and unified social credit code. The data also includes store location information, including the store name, ID, and specific location. The data also includes product shipping information, including a list of products currently on sale and the shipping location of each product. Furthermore, product sales information, such as product name, price, and sales volume, is collected. Business industrial and commercial data is obtained from public information published by the Market Supervision Bureau and includes information such as the company name, unified social credit code, establishment date, registered capital, number of employees, company type, address, mailing address, and legal representative. Optionally, public data can be captured in a targeted manner using web crawler technology according to established rules and permissions.

[0031] S102: Standardize the e-commerce data and the enterprise business data, and associate the data with the unified social credit code through the store ID to form an integrated data set.

[0032] In some embodiments, collected e-commerce data and enterprise industrial and commercial data are standardized to unify differences in format, coding, and data structure across different channels, such as standardizing date formats, currency units, and commodity classification codes. Subsequently, store-related data within the e-commerce data is linked using store IDs, and e-commerce data and enterprise industrial and commercial data are linked using unified social credit codes, integrating the scattered data into a complete, enterprise-centric data set. It should be noted that according to pre-set data standards and association rules, the original data is formatted and matched, data heterogeneity is eliminated, a structured data system is built, seamless connection and unified management of data are achieved, and data quality and availability are improved.

[0033] S103: Obtain enterprise basic information characteristics, regional characteristics, industry characteristics and park characteristics, and construct e-commerce enterprise feature engineering based on the integrated data set.

[0034] In some embodiments, feature information is obtained from dimensions such as basic enterprise information, region, industry, sales scale, and market competitiveness. Basic enterprise information features include registered capital scale segments, establishment time scale segments, employee size segments, and enterprise type; regional features include the province, city, district, or county where the enterprise is located; industry features form industry classification labels based on national economic industry classification standards; sales scale features are divided into sales scale ranges and sales growth rate ranges; market competitiveness features are calculated by calculating the proportion of the enterprise's sales scale in the overall sales scale of the category to form market share and ranking labels, and combined with the integrated data set to construct e-commerce enterprise feature engineering. The constructed e-commerce enterprise feature engineering can clearly present the comprehensive strength, development potential and market positioning of the enterprise, and provide accurate enterprise feature basis for identifying abnormal enterprises and matching them with the needs of the park.

[0035] S104: Based on the e-commerce enterprise feature engineering, by comparing the monthly change information of the enterprises, identify the changed enterprises with changes in enterprise, enterprise address or legal representative, and form a directory of changed enterprises.

[0036] In some embodiments, data collection, updating, and processing are performed on a monthly basis. The data is compared to determine if any three or two of the following information are inconsistent: the store business's registered location, store location, and primary shipping location for the month; if the business entity has changed, the store's location and product shipping location are compared; if there are any changes, the business's domicile and mailing address are compared; and if there are any inconsistencies, the legal representative information is compared between the previous and next two months. If there are any changes, these businesses are considered to have changed and are included in the list of changed businesses. By setting clear criteria for judging changes, we conduct periodic comparative analysis of key corporate information, capture changes in corporate operating status, address, personnel, etc., and screen out companies with potential change needs. This embodiment can also integrate data sets that already aggregate e-commerce data and business data. By establishing data interfaces with professional intellectual property databases and industry qualification certification platforms, utilizing data transmission protocols and security verification mechanisms, and based on unique identifiers such as the company's unified social credit code, detailed information on a company's intellectual property holdings, qualification certifications, and honors can be obtained. This process deeply mines and supplements basic corporate data, improving the company's information dimensions and providing a more comprehensive data foundation for subsequent feature analysis. By leveraging industry experts and authoritative data to determine a company's industrial characteristics, the analysis is more professional and accurate, avoiding bias caused by single-data analysis. Converting data into feature tags standardizes and structures corporate industry information, facilitating rapid matching and comparison with industrial park investment needs. Feature tags across multiple dimensions, such as basic corporate information, region, industry, sales scale, and market competitiveness, are aggregated and integrated according to a unified architecture and logic. Correlations are established by analyzing the inherent connections between the corporate information represented by each feature tag. For example, a company's registered capital and employee size may be positively correlated with its sales scale and market competitiveness. The industrial policies and resource advantages of a company's region may also influence its industrial development direction. By exploring and sorting out these relationships, we construct a comprehensive, systematic, and internally logical e-commerce enterprise feature engineering, which makes the enterprise characteristics appear holistic and relevant, and can portray the enterprise portrait in a more three-dimensional way.

[0037] Optionally, step S104 also includes: extracting business information based on the monthly data update of the enterprise, and comparing it with the business information of the enterprise in historical records to identify abnormal characteristics; combining industrial policy keywords with the main business labels of the enterprise to generate a policy fit score, and evaluate the matching degree between the abnormal enterprise and the industrial direction of the park; linking the legal representative change record of the associated enterprise with the market supervision credit file to generate a compliance risk score, and push differentiated investment promotion suggestions based on the score results.

[0038] S105: Constructing an industrial park feature engineering based on the industrial park demand information, generating regional characteristics, industrial characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converting them into quantifiable matching model parameters.

[0039] In some embodiments, industrial park feature engineering is constructed based on the enterprise feature engineering dimension. Regional features record the province, city, district, and county where the enterprise is located. Industry features form industry classification labels based on national economic industry classification standards. Park demand features structure key information such as the scale requirements (e.g., annual sales, registered capital) and industry influence requirements (e.g., whether the enterprise is a well-known brand) of the investment attraction enterprise, converting them into quantifiable and matching park demand model parameters. This embodiment can, based on the industrial park's development positioning and investment needs, sort out the park's own regional advantages, industrial foundation, and investment expectations, integrate and quantify this information, and construct a park characteristic system corresponding to the enterprise characteristic engineering, forming model parameters that can be used for matching. Establishing a standardized park characteristic engineering provides clear standards and basis for the precise matching of enterprises and parks, ensuring that the introduced enterprises are highly aligned with the park's development strategy.

[0040] As an optional method, step S105 also includes: parsing the park investment policy documents, extracting land use scale, environmental protection level, and industrial synergy parameters, and converting them into quantifiable indicators through natural language processing technology; establishing a semantic mapping relationship between demand characteristics and e-commerce enterprise characteristics, and adjusting the matching weights of related indicators when a regional industrial structure adjustment announcement is detected; performing spatiotemporal consistency verification and information compliance verification on enterprise characteristics and park demand parameters, and generating a matching report.

[0041] It can be seen that this embodiment is based on natural language processing technology that can understand the semantics and logic of human language. Through text analysis of investment policy documents, it extracts key policy information and converts it into structured data that can be recognized and processed by computers. By using pre-set rules and algorithms, vague natural language expressions are converted into clear quantitative indicators, so that policy requirements can be integrated into the park feature engineering and become specific standards for matching enterprises with parks. By establishing a mapping relationship between demand characteristics and enterprise characteristics based on semantic analysis, the potential logical connection between the two can be excavated, making the matching of enterprises and parks more scientific and reasonable. By real-time monitoring of regional industrial structure adjustment information, the impact of external environmental changes on the park's investment demand can be captured in a timely manner, and the indicator matching weights can be dynamically adjusted to ensure that investment promotion work can adapt to industrial development trends. The spatiotemporal consistency check of this embodiment compares the development plans and layouts of the enterprise and the park in terms of time and space to evaluate the degree of compatibility between the two, thereby ensuring that the enterprise can develop in a suitable time and space environment after its establishment.

[0042] S106: Based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering, the matching scores between the enterprises and the park needs are obtained by comprehensively calculating the enterprise scores, and a list of recommended enterprises for investment promotion is generated according to the ranking of the scores.

[0043] In some embodiments, based on e-commerce enterprise feature engineering, a database of changing enterprise directories, and park feature engineering, a comprehensive consideration of factors such as enterprise characteristics across various dimensions, development potential, strategic alignment with the park, and policy compatibility is used to calculate a match score between the enterprise and the park's needs. Enterprises are ranked based on these scores, generating a list of recommended enterprises for investment promotion. A dynamic tracking mechanism is also established to regularly update enterprise match scores and the order of recommendation. This embodiment uses a comprehensive evaluation method to conduct a multi-dimensional comparative analysis of enterprise characteristics and park needs. By setting weights and scoring rules, the degree of matching between enterprises and parks is quantified to determine the priority of enterprises in investment recommendations. The method of this embodiment further includes constructing a knowledge base for investment promotion feedback, collecting the operating data of enterprises after they settle in the park and the evaluation records of investment promotion personnel, and establishing a feature effectiveness evaluation model; establishing a regional industrial ecology simulation method, converting infrastructure parameters such as the transportation network and energy supply around the park into matching constraints; and verifying the fit between the historical operating trajectory of the enterprise and the park development plan through spatiotemporal correlation analysis.

[0044] Specifically, after a company successfully settles in an industrial park, its operating data, including sales, profits, market share, product innovation achievements, and other information, will be continuously collected to form a corporate operating data archive. At the same time, investment promotion personnel will be organized to regularly evaluate the settled companies, recording the company's development status within the park, its collaboration with the park's industries, and its contribution to the park's development, forming an investment promotion personnel evaluation record. These data and records will be integrated and stored to construct an investment promotion feedback knowledge base. Based on this knowledge base, a feature effectiveness evaluation model will be established to compare the development status of the company before settlement based on feature engineering predictions with the actual operating data after settlement. The impact of each feature indicator on the company's development and its compatibility with the park will be analyzed to determine the effectiveness of feature engineering. This example conducts a detailed survey of the transportation network surrounding the industrial park, capturing parameters such as the layout of highway, rail, and air routes, transport capacity, and the location of transportation hubs. Energy supply is also investigated, including parameters such as the total supply, stability, and price of electricity, natural gas, and water resources. Furthermore, information is collected regarding supporting industrial facilities, scientific research institutions, and educational resources surrounding the industrial park. Using geographic information systems (GIS) and data analysis techniques, these infrastructure parameters and related information are integrated and simulated to construct a regional industrial ecosystem model. Within this model, various infrastructure parameters are converted into matching constraints for enterprise location. For example, areas with limited transportation restrict logistics and transportation businesses, while insufficient energy supply limits energy-intensive enterprises. Leveraging spatiotemporal data analysis techniques, we overcome the temporal and spatial limitations of traditional data processing and incorporate the dynamics of business operations and park development into our analysis. By comparing and correlating the historical operational trajectory of businesses with park development plans across time and space, we assess potential areas of convergence and conflict between the two, providing a more comprehensive and in-depth basis for investment decisions. This ensures that established businesses are integrated into the park's development plan, enabling industrial collaboration and resource sharing, and promoting the park's orderly development in accordance with its planned objectives.

[0045] On the basis of the above embodiment, in order to further improve the reliability of the industrial park investment information processing method based on e-commerce big data provided by the above embodiment, the following are specific steps that can be implemented.

[0046] S201: Collect e-commerce data and corporate business data.

[0047] S202: Perform unified format conversion and standardization on the collected raw e-commerce big data, such as standardizing the date format, currency unit, and product classification code on different e-commerce platforms.

[0048] Based on the sales information of store products, the sales data of the store and the company are aggregated in layers.

[0049] Store-related data within e-commerce data is linked using the store ID as a unique identifier. Using the unified social credit code as a unique identifier, e-commerce data and corporate business data are linked to form a complete, enterprise-centric data set, laying the foundation for subsequent in-depth analysis of corporate characteristics and precise matching.

[0050] S203: Build an e-commerce enterprise feature engineering module.

[0051] This embodiment focuses on the goal of accurate recommendation and establishes a feature engineering for e-commerce enterprises, including enterprise basic information characteristics, regional characteristics, industry characteristics, sales scale characteristics, market competitiveness characteristics, etc.

[0052] The basic information characteristics of an enterprise include the enterprise's registered capital scale segment, the enterprise's establishment time scale segment, the enterprise's employee scale segment, the enterprise type, etc. Regional characteristics refer to the enterprise's location information, including province, city, district and county. The industry characteristics are based on the national economic industry classification standards or other industry classification standards to form the industry classification labels of each standard of the enterprise, such as national economic industry categories, national economic industry categories, general industry classifications, and main business of the enterprise. The sales scale characteristics are based on the enterprise's sales scale segment, divided by sales scale intervals and sales growth rate intervals, reflecting the overall strength and growth trend of the enterprise. The market competitiveness characteristics are based on the calculation of the proportion of the enterprise's sales scale in the overall sales scale of a certain category to form market share and ranking labels.

[0053] S204: Build a directory database of e-commerce companies with changes.

[0054] This embodiment collects, updates, and processes the above data on a monthly basis, specifically including: Compare the store operating company information, store location information, and store merchandise shipping information collected this month. By comparing the three pieces of information, namely, the store operating company's registered place, the store's location, and the store's main shipping location for the month (calculated by the shipping location of the merchandise with the largest sales volume), any company with three or two inconsistent pieces of information will be deemed to be an abnormal e-commerce company and may become a target enterprise for investment promotion in a certain park.

[0055] By comparing the store operating enterprise information collected this month with the store operating enterprise information collected last month of this year, if the operating enterprise of the same store in the two months is inconsistent, it will be regarded as an abnormal e-commerce enterprise, that is, the enterprise has undergone a change in the operating entity and may become a target enterprise for investment promotion in a certain park.

[0056] By comparing the store location information and store product shipping information collected this month with the store location information and store product shipping information collected last month, if the information of the two months is inconsistent, it will be regarded as an abnormal e-commerce enterprise, that is, the enterprise's place of business may have changed, and it may become a target enterprise for investment promotion in a certain park.

[0057] By comparing the collected corporate addresses and correspondence addresses, if the corporate address and the correspondence address in the latest annual report of the same company are inconsistent, it will be regarded as an abnormal e-commerce company, that is, the corporate address has changed, and it may become a target enterprise for investment promotion in a certain park.

[0058] By comparing the collected legal representative information, if the information of the same enterprise is inconsistent between the previous and subsequent months, it will be regarded as an abnormal e-commerce enterprise, that is, the main personnel of the enterprise have changed, and it may become a target enterprise for investment promotion in a certain park.

[0059] S205: Construct characteristic engineering of industrial parks.

[0060] This embodiment establishes an industrial park feature engineering based on the dimensions of enterprise feature engineering, including regional characteristics, industry characteristics, and park demand characteristics.

[0061] Regional characteristics refer to the company's location, including province, city, district, and county, which aligns with the characteristics of e-commerce companies. Industry characteristics, based on national economic industry classification standards or other industry classification standards, create standardized industry classification labels for each company, such as national economic industry category, major national economic industry category, general industry classification, and main business, which align with the characteristics of e-commerce companies. Park demand characteristics encompass key information such as the desired goals for the company seeking investment (including company size requirements, such as annual sales and registered capital; industry influence requirements, such as whether the company is a well-known brand). This information is structured and converted into a park demand model that intelligent algorithms can identify and calculate. For example, the park demand model emphasizes the inclusion of companies with environmentally friendly products and a high market share. The system quantitatively compares the environmental attributes and market share indicators of each company's profile, screening out those that meet the requirements and recommending them to the park.

[0062] S206: Build a recommended enterprise model.

[0063] First, collect sample data related to each subordinate indicator. For example, for the "Years of Establishment" indicator under "Basic Enterprise Information Characteristics," collect the establishment date data of all the companies to be evaluated; for the "Annual Sales Volume" indicator under "Sales Scale Characteristics," obtain the actual sales figures for each company in the past year.

[0064] According to the entropy method, corresponding weights are assigned to the company's basic information characteristics, regional characteristics, industry characteristics, sales scale characteristics, and market competitiveness characteristics, and corresponding weights are also assigned to the corresponding subordinate indicators. The information entropy of each indicator reflects the amount of information it provides. The smaller the information entropy, the greater the degree of variation of the indicator, the more information it provides, and the corresponding weight is larger. Conversely, the weight is smaller.

[0065] Arrange the collected data of each subordinate indicator according to the individual enterprise and construct a data matrix. Assuming there are n enterprises and m subordinate indicators, then the data matrix X=(x ij ) n×m in, Indicates the value of the jth subordinate indicator of the i-th enterprise.

[0066] The dimensions and magnitudes of the subordinate indicators in this embodiment are different. In order to eliminate the influence of these differences on the weight calculation, the range normalization method is used to normalize the data. The normalization formula of the positive indicator is: =

[0067] in, is the normalized value, It is the element in the original data matrix, which realizes the conversion of the original data Map to Within the interval, the numerical range is unified.

[0068] Calculate the proportion of the indicators and convert the standardized data into proportion form in order to calculate the information entropy.

[0069] =

[0070] in, It represents the proportion of the jth indicator of the i-th enterprise in all indicators.

[0071] The weight matrix is ​​as follows: P=(p ij ) n×m Calculate information entropy. Calculate the information entropy of each e-commerce company.

[0072] =-k

[0073] Among them, n is the number of e-commerce companies, k=

[0074] The value range of information entropy is The range reflects the degree of variation of the indicator. The larger the value, the smaller the degree of variation of the indicator and the less information it provides. Conversely, the smaller the value, the greater the degree of variation and the richer the information.

[0075] S207: Calculate the enterprise score comprehensively.

[0076] By calculating the matching scores between each enterprise in the directory and the needs of the park, the enterprises are sorted and screened according to the scores, and the potential target enterprises with the highest likelihood of settlement and high degree of fit are accurately recommended to the park.

[0077] Based on the weights of each indicator determined by the entropy method and combined with the standardized indicator data, the individual scores corresponding to each indicator are calculated. Similarly, the individual scores of the company under all the profile indicator dimensions are calculated.

[0078] The individual scores of the sub-indicators under each first-level indicator are aggregated to obtain a comprehensive score for each first-level indicator. For example, the individual scores of the sub-indicators under the enterprise's basic information characteristics are added together to obtain the enterprise's comprehensive score for the "enterprise basic information characteristics" dimension. The comprehensive scores of all first-level indicators are then weighted and summed according to their respective weights to obtain the enterprise's overall composite score. This overall composite score can, to a certain extent, reflect the enterprise's overall strength or its degree of compatibility with specific evaluation objectives (such as the investment needs of an industrial park).

[0079] S208: Execute the visualization process to present the enterprise portrait.

[0080] Choose appropriate visualization methods to build a clear corporate portrait content structure. Visualizations include: Company Profile: This includes basic information such as company name, nature of business, year of establishment, and registered address, giving users a preliminary, holistic understanding of the company. Conduct detailed analysis around each primary indicator. For example, the "Industry Characteristics" section details dimensions such as industry development stage, industry relevance, industry technological innovation, and market demand trends. Combined with charts and text, this section explains the characteristics of the industry in which the company operates, its position within the industry, and its development potential.

[0081] By displaying and analyzing relevant indicators such as sales scale characteristics and market competitiveness characteristics, the company's operating results, market competitive advantages, and sustainable development capabilities are presented. For example, indicators such as annual sales and market share are displayed, and the company's operating strength reflected behind them is analyzed.

[0082] Based on the analysis of the previous dimensions and the overall comprehensive score, a comprehensive evaluation summary is given to the enterprise, pointing out key points such as the enterprise's strengths, weaknesses, and the degree of matching with specific scenarios (such as the demand characteristics of industrial parks), providing an intuitive reference for subsequent decision-making (such as whether to list the enterprise as a key target for investment promotion, etc.).

[0083] This embodiment also categorizes and summarizes the e-commerce companies that have changed, and issues early warning information to the park in a timely manner, assisting the park management to adjust the investment promotion strategy, optimize the cooperation plan or re-evaluate the target companies in advance, thereby effectively avoiding potential risks and ensuring the scientific nature and timeliness of investment promotion decisions.

[0084] This embodiment establishes a directory of e-commerce companies and creates panoramic portraits, using intelligent algorithms to accurately recommend target companies for industrial park investment promotion, overcoming the inaccuracy and inefficiency of traditional investment promotion methods. By establishing a directory of e-commerce companies with changes, timely identification and early warning of changes in e-commerce companies based on e-commerce big data allows the park to dynamically monitor the companies related to its investment promotion targets, allowing it to adjust investment promotion strategies, optimize cooperation plans, or re-evaluate target companies in advance, effectively avoiding potential risks and ensuring the scientific and timely nature of investment promotion decisions.

[0085] The following is an embodiment of the industrial park investment promotion information processing system based on e-commerce big data provided by the embodiments of the present disclosure. This system and the industrial park investment promotion information processing methods based on e-commerce big data in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the industrial park investment promotion information processing system based on e-commerce big data, please refer to the embodiment of the above-mentioned industrial park investment promotion information processing method based on e-commerce big data.

[0086] like Figure 2 As shown, the system includes: a data acquisition module for acquiring e-commerce data and enterprise industrial and commercial data; A data standardization and integration module is used to standardize the e-commerce data and enterprise industrial and commercial data, and associate the data with the unified social credit code through the store ID to form an integrated data set; An e-commerce enterprise feature construction module is used to obtain enterprise basic information features, regional features, industry features and park features, and to construct an e-commerce enterprise feature engineering based on the integrated data set; The module for identifying and building a list of companies that have changed, or whose domiciles have changed, or whose legal representatives have changed, is based on the e-commerce company feature engineering and compares the companies' monthly change information to identify those companies that have changed, or whose domiciles have changed, and forms a list of companies that have changed; A park feature engineering construction module constructs an industrial park feature engineering based on industrial park demand information, generates regional characteristics, industry characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converts them into quantifiable matching model parameters; The enterprise matching and recommendation list generation module is based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering. It obtains the matching score between the enterprise and the park demand by comprehensively calculating the enterprise score, and generates a list of recommended enterprises for investment promotion according to the ranking of the scores.

[0087] like Figure 3As shown, the present application also provides an electronic device, including a display module 103, a memory 102, a processor 101, and a computer program stored in the memory and executable on the processor 101. When the processor 101 executes the program, it implements the steps of a method for processing industrial park investment information based on e-commerce big data.

[0088] In the embodiments of the present invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or claimed herein.

[0089] In the embodiment of the present application, the processor 101 can be implemented by using at least one of a special purpose integrated circuit, a programmable logic device, a field programmable gate array, a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, such an embodiment can be implemented in a controller. For software implementation, an embodiment such as a process or function can be implemented with a separate software module that allows the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.

[0090] The display module 103 is used to display information input by the user or information provided to the user. The display module 103 may include a display panel, which may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.

[0091] The memory 102 can be used to store software programs and various data. The memory 102 can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0092] The present application also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for processing industrial park investment information based on e-commerce big data.

[0093] The storage medium can be any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0094] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing industrial park investment information based on e-commerce big data, characterized in that: Methods include: S101: Obtain e-commerce data and enterprise business data; S102: Standardize the e-commerce data and the enterprise business data, and associate the data with the store ID and the unified social credit code to form an integrated data set; S103: Obtaining basic information characteristics, regional characteristics, industry characteristics, and park characteristics of the enterprise, and constructing e-commerce enterprise feature engineering based on the integrated data set; S104: Based on the e-commerce enterprise feature engineering, by comparing the monthly change information of enterprises, identifying enterprises that have undergone changes in enterprise, enterprise address, or legal representative, and forming a directory of changed enterprises; S105: Constructing an industrial park feature engineering based on the industrial park demand information, generating regional characteristics, industrial characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converting them into quantifiable matching model parameters; S106: Based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering, the matching scores between the enterprises and the park needs are obtained by comprehensively calculating the enterprise scores, and a list of recommended enterprises for investment promotion is generated according to the ranking of the scores.

2. The method for processing industrial park investment information based on e-commerce big data according to claim 1 is characterized in that: Steps: The method of obtaining the matching score between the enterprise and the park needs by comprehensively calculating the enterprise score includes: According to the entropy method, the basic information characteristics, regional characteristics, industry characteristics, sales scale characteristics, and market competitiveness characteristics of the enterprise are assigned corresponding weights, and the corresponding subordinate indicators are assigned corresponding weights; Arrange the collected data of each subordinate indicator according to individual enterprises and construct a data matrix; Assuming there are n enterprises and m subordinate indicators, the data matrix is: X=(x ij ) n×m in, Indicates the value of the jth subordinate indicator of the i-th enterprise.

3. The method for processing industrial park investment information based on e-commerce big data according to claim 2 is characterized in that: The data in the data matrix are standardized using the range standardization method. The standardization formula for the positive indicator is: = in, is the normalized value, It is the element in the original data matrix, which realizes the conversion of the original data Map to within the interval; The proportion of the indicators is calculated based on the following formula, and the standardized data is converted into proportion form in order to calculate the information entropy; = in, It represents the proportion of the jth indicator of the i-th enterprise in all indicators; The weight matrix is ​​as follows: P=(p ij ) n×m Calculate the information entropy of each e-commerce company : =-k Among them, n is the number of e-commerce companies, k= ; The value range of information entropy is The interval reflects the degree of variation of the indicator.

4. The method for processing industrial park investment information based on e-commerce big data according to claim 1 is characterized in that: Step S103 specifically includes: extracting various types of original data of the enterprise from the integrated data set, and supplementing the collection of the enterprise's basic information with information such as intellectual property rights, qualifications and honors by connecting to the intellectual property database and industry qualification certification platform; In terms of industry characteristics, we combine industry expert analysis and industry development white papers to determine the company's development status in emerging industries and its position in the industry chain. We then classify and organize the extracted and supplemented data according to pre-set rules and standards, and convert them into feature labels. Integrate the feature labels of each dimension to form the feature engineering of e-commerce enterprises, and establish the correlation between the feature labels.

5. The method for processing industrial park investment information based on e-commerce big data according to claim 1 is characterized in that: Step S104 also includes: extracting business operation information based on the monthly data update of the enterprise, and comparing it with the business operation information in the historical records to identify abnormal characteristics; Combining industry policy keywords with the company's main business tags, a policy fit score is generated to assess the matching degree between the changing companies and the industrial direction of the park; The change records of legal representatives of affiliated enterprises and market supervision credit files are used to generate compliance risk scores, and differentiated investment promotion suggestions are pushed based on the scoring results.

6. The method for processing industrial park investment information based on e-commerce big data according to claim 1 is characterized in that: Step S105 further includes: Analyze park investment policy documents, extract parameters such as land use scale, environmental protection level, and industrial synergy, and convert them into quantifiable indicators through natural language processing technology; Establish a semantic mapping relationship between demand characteristics and e-commerce enterprise characteristics. When an announcement of regional industrial structure adjustment is detected, adjust the matching weight of the associated indicators; perform spatiotemporal consistency verification and information compliance verification on enterprise characteristics and park demand parameters, and generate a matching report.

7. The method for processing industrial park investment information based on e-commerce big data according to claim 1 is characterized in that: In the method, a knowledge base of investment attraction feedback is constructed, the business data of enterprises after they settle in the park and the evaluation records of investment attraction personnel are collected, and a feature validity evaluation model is established; Establish a regional industrial ecological simulation method to convert infrastructure parameters such as the transportation network and energy supply around the park into matching constraints; through spatiotemporal correlation analysis, verify the fit between the historical operating trajectory of the enterprise and the park development plan.

8. An industrial park investment information processing system based on e-commerce big data, characterized by: The system is used to implement the industrial park investment information processing method based on e-commerce big data as described in any one of claims 1 to 7; the system includes: Data collection module, used to obtain e-commerce data and corporate industrial and commercial data; A data standardization and integration module is used to standardize the e-commerce data and enterprise industrial and commercial data, and associate the data with the unified social credit code through the store ID to form an integrated data set; An e-commerce enterprise feature construction module is used to obtain enterprise basic information features, regional features, industry features and park features, and to construct an e-commerce enterprise feature engineering based on the integrated data set; The module for identifying and building a list of companies that have changed, or whose domiciles have changed, or whose legal representatives have changed, is based on the e-commerce company feature engineering and compares the companies' monthly change information to identify those companies that have changed, or whose domiciles have changed, and forms a list of companies that have changed; A park feature engineering construction module constructs an industrial park feature engineering based on industrial park demand information, generates regional characteristics, industry characteristics, and park demand characteristics corresponding to the e-commerce enterprise feature engineering, and converts them into quantifiable matching model parameters; The enterprise matching and recommendation list generation module is based on the e-commerce enterprise feature engineering, the changed enterprise directory database and the park feature engineering. It obtains the matching score between the enterprise and the park demand by comprehensively calculating the enterprise score, and generates a list of recommended enterprises for investment promotion according to the ranking of the scores.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the industrial park investment information processing method based on e-commerce big data as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for processing industrial park investment information based on e-commerce big data as described in any one of claims 1 to 7 are implemented.

Images