Intelligent tag-based management method and system for maritime-related enterprises

Abstract

The application relates to the technical field of enterprise management systems, and provides a marine-related enterprise management method and system based on intelligent labels. A data source of an enterprise to be processed is acquired; based on a preset template file, the data source is normalized to generate standard data; based on a keyword in the standard data, label information corresponding to the enterprise to be processed is determined, and whether the enterprise to be processed is a marine-related enterprise is judged according to the label information; if the enterprise to be processed is not marine-related, the label information and public information of the enterprise to be processed are matched to judge whether the enterprise to be processed is a marine-related enterprise; and a unit directory of marine economic activities is generated based on the marine-related enterprises to construct an enterprise identification library. Through the generation of labels based on keywords and secondary verification, the accuracy of the determination of marine-related enterprises is improved, a dynamically updated unit directory of marine economic activities is finally constructed, the accuracy and efficiency of enterprise management are improved, and structured and high-credibility enterprise identification support is provided for marine economic governance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of enterprise management system, in particular to a marine-related enterprise management method and system based on intelligent tags. BACKGROUND

[0002] Under the background of steady promotion of marine economy development, classified management of marine economic activity business subjects is a relevant work arrangement that needs to be implemented. This work is conducive to optimizing the construction of marine unit directory, understanding the operation of marine economic activity business subjects, and is of great significance for marine economic investigation and monitoring and evaluation.

[0003] In the past construction process of marine economic activity unit directory library, the sharing of market subject information base needs to go through multi-party data coordination and docking, which has problems such as long work flow and low efficiency, and the finally generated marine economic activity unit directory library is not comprehensive and accurate. SUMMARY

[0004] The present application provides a marine-related enterprise management method and system based on intelligent tags, which can at least solve the problem of the marine economic activity unit directory library not being comprehensive and accurate to some extent.

[0005] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0006] According to one aspect of the present application, a marine-related enterprise management method based on intelligent tags is provided, comprising: acquiring a data source of an enterprise to be processed; wherein the data source includes business scope, industry code, registration information and public information; based on a preset template file, normalizing the data source to generate standard data; based on the keywords in the standard data, determining the label information corresponding to the enterprise to be processed, and judging whether the enterprise to be processed belongs to a marine-related enterprise according to the label information; if the enterprise to be processed is not marine-related, matching the label information of the enterprise to be processed and the public information to judge whether the enterprise to be processed belongs to a marine-related enterprise; based on the marine-related enterprise, generating a unit directory of marine economic activities to build an enterprise identification library through the unit directory.

[0007] In the present application, based on the foregoing scheme, the normalization processing of the data source based on the preset template file to generate standard data comprises: based on the preset template file, identifying the data type and keywords of the data source; counting the text length of each data type data in the data source and the word frequency of the keywords; based on the text length corresponding to the data type and the word frequency of the keywords, generating dynamic parameters; and normalizing the data source through the dynamic parameters to generate standard data.

[0008] In the present application, based on the foregoing scheme, the dynamic parameter is generated based on the text length corresponding to the data type and the keyword frequency, comprising: determining the information parameter corresponding to the data source based on the data content of the data source; generating a dynamic parameter according to the information parameter corresponding to the data source, the text length corresponding to the data type and the keyword frequency.

[0009] In the present application, based on the foregoing scheme, the dynamic parameter is generated according to the information parameter corresponding to the data source, the text length corresponding to the data type and the keyword frequency, comprising: generating a dynamic parameter according to the information parameter corresponding to the data source, the text length corresponding to the data type and the keyword frequency For:

[0010] ,

[0011] Among them, the information parameter of the data source , respectively represent the adjustment factor of the information parameter and the text length , i and j respectively represent the data identification of the data source, n representing the total amount of data in the data source.

[0012] In the present application, based on the foregoing scheme, the label information corresponding to the to-be-processed enterprise is determined based on the keyword in the standard data, and it is judged whether the to-be-processed enterprise belongs to the sea-related enterprise according to the label information, comprising: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing between the business scope and the registration information, and determining the first sea-related level and the second sea-related level according to the generated comparison result; based on the combination code, the first sea-related level and the second sea-related level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to the sea-related enterprise according to the comparison result.

[0013] In the present application, based on the foregoing scheme, the combination code is generated by matching the business scope and the industry code in the standard data based on the preset matching relationship, comprising: determining the first identification corresponding to the business scope in the standard data based on the preset business scope corresponding relationship; determining the second identification corresponding to the industry code in the standard data based on the preset industry code corresponding relationship; combining the first identification and the second identification to generate a combination code.

[0014] In the present application, based on the foregoing scheme, the method further comprises: determining a third identifier corresponding to the industry name in the standard data based on a preset industry name correspondence relationship; and combining the first identifier, the second identifier, and the third identifier to generate a combined code.

[0015] In the present application, based on the foregoing scheme, the matching of the label information of the to-be-processed enterprise and the public information based on the preset database to determine whether the to-be-processed enterprise belongs to a marine-related enterprise comprises: matching the label information of the to-be-processed enterprise and the public information based on the preset database to determine a marine-related parameter; and if the marine-related parameter is greater than or equal to a preset marine-related threshold, determining that the to-be-processed enterprise is marine-related.

[0016] In the present application, based on the foregoing scheme, the generating of a unit list of marine economic activities based on the marine-related enterprise to build an enterprise identification library through the unit list comprises: generating an enterprise parameter based on the marine-related parameter and a determination time stamp of the marine-related enterprise; and ranking the marine-related enterprise according to the enterprise parameter to generate a unit list to build an enterprise identification library based on the unit list.

[0017] According to an aspect of the present application, a marine-related enterprise management system based on an intelligent label is provided, comprising:

[0018] An acquisition unit is configured to acquire a data source of a to-be-processed enterprise; wherein the data source comprises a business scope, an industry code, registration information, and public information;

[0019] A data unit is configured to perform normalization processing on the data source based on a preset template file to generate standard data;

[0020] A label unit is configured to determine label information corresponding to the to-be-processed enterprise based on a keyword in the standard data, and determine whether the to-be-processed enterprise is a marine-related enterprise according to the label information;

[0021] An information unit is configured to, if the to-be-processed enterprise is not marine-related, match the label information of the to-be-processed enterprise and the public information to determine whether the to-be-processed enterprise is a marine-related enterprise;

[0022] A construction unit is configured to generate a unit list of marine economic activities based on the marine-related enterprise to build an enterprise identification library through the unit list.

[0023] According to an aspect of the present application, a computer readable medium having a computer program stored thereon is provided, wherein the computer program is executed by a processor to implement the marine-related enterprise management method based on an intelligent label as described in the above embodiments.

[0024] According to an aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the intelligent tag-based marine-related enterprise management method as described in the above embodiments.

[0025] According to an aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device performs the intelligent tag-based marine-related enterprise management method provided in the various optional implementation manners described above.

[0026] The technical scheme of the present application obtains a data source of an enterprise to be processed; performs normalization processing on the data source based on a preset template file to generate standard data; determines label information corresponding to the enterprise to be processed based on a keyword in the standard data, and determines whether the enterprise to be processed is a marine-related enterprise according to the label information; if the enterprise to be processed is not marine-related, matches the label information of the enterprise to be processed with the public information to determine whether the enterprise to be processed is a marine-related enterprise; and generates a unit directory of marine economic activities based on the marine-related enterprise, so as to construct an enterprise identification library through the unit directory. The standard data is generated through the integration of multiple data sources and normalization processing, so as to ensure data consistency; the label is generated based on the keyword and is verified again, so as to improve the accuracy of marine-related enterprise determination; and finally, a dynamically updated unit directory of marine economic activities is constructed, so as to realize real-time management and identification of marine-related enterprises. The accuracy and efficiency of enterprise management are improved, and structured and high-credibility enterprise identification support is provided for marine economic governance.

[0027] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application. BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. It is apparent that the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0029] Figure 1 A flowchart of an intelligent tag-based marine-related enterprise management method in one embodiment of the present application is schematically shown.

[0030] Figure 2 A flow chart illustrating the generation of standard data in one embodiment of the present application is shown.

[0031] Figure 3 A schematic diagram of an intelligent tag-based marine-related enterprise management system in one embodiment of the present application is shown.

[0032] Figure 4 A structural schematic diagram of a computer system of an electronic device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0033] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the inventive aspects to those skilled in the art. Like reference numerals may refer to like elements throughout.

[0034] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the

[0035] The block diagrams in the drawings show only the functionality of the features and can not imply a necessity of any particular physical or architectural arrangement. That is, the functionality of the features can be implemented in software, hardware, or a combination thereof, and can be implemented in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0036] The flow diagrams shown in the drawings are merely examples of possible flow diagrams and are not necessarily meant to include all of the content and operations / steps, nor are they necessarily meant to be performed in the order described. For example, some operations / steps can be broken down further, while some operations / steps can be combined or partially combined, and thus the actual order of performance can vary depending on the actual situation.

[0037] The implementation details of the technical solutions of the present application are described in detail as follows:

[0038] Figure 1 A flow chart of an intelligent tag-based marine-related enterprise management method according to one embodiment of the present application is shown. Referring to Figure 1 As shown, the intelligent tag-based marine-related enterprise management method includes at least steps S110 to S150, which are described in detail as follows:

[0039] S110, acquire a data source of the enterprise to be processed; wherein the data source comprises a business scope, an industry code, registration information, and public information.

[0040] In an embodiment of the present application, the data source of the enterprise to be processed needs to cover multi-dimensional information to ensure the accuracy of classification. Among them, the business scope is a direct description of the core business of the enterprise, which can be obtained through the business registration file or the official website of the enterprise; the industry code is based on the code in the "National Economic Industry Classification", which is used to standardize the industry to which the enterprise belongs; the registration information includes the basic attributes such as enterprise name, legal representative, establishment time and registered capital, which are obtained through official channels such as enterprise credit information public system; the public information covers unstructured data such as news reports, court announcements, bidding records and social media information, reflecting the enterprise dynamics and social evaluation.

[0041] In an embodiment of the present application, on the basis of strictly complying with the website agreement and data security regulations, combined with legal channels and technical tools for data collection, for example, official databases such as enterprise credit information public system provide authoritative registration information and industry codes; third-party data service providers integrate multi-source data to supplement business scope and associated enterprise information; network crawler technology can be used to capture official website, news website and other public information. For unstructured data, natural language processing technology is used to extract key information, such as identifying enterprise cooperation dynamics or risk events from news.

[0042] Optionally, the original data has inconsistent formats, redundancies or missing problems, which need to be processed through cleaning and standardization to improve usability. For example, the coding format of the industry code is unified, the wrong words or ambiguous descriptions in the business scope are corrected, and the duplicate records in the basic information of the enterprise are removed. The integration stage needs to establish the association relationship, map the registration information, industry code and dynamic data in the public information to the same enterprise subject, and form a structured data set. This process ensures that the subsequent analysis is based on accurate and complete data basis, and avoids classification bias caused by data quality problems.

[0043] The above process constructs a complete data basis for enterprise portrait by collecting multi-dimensional data such as business scope, industry code, registration information and public information, avoiding one-sidedness of single data source.

[0044] S120, based on a preset template file, normalizing the data source to generate standard data.

[0045] In one embodiment of this application, when normalizing the data source based on a preset template file, the data structure and field specifications defined in the template are first parsed. For example, the industry code is unified to the standard code of the "National Economic Industry Classification", the keyword description of the business scope is standardized, and the date and format of the registration information are standardized. Then, the original data is mapped to the corresponding fields of the template. Redundant or erroneous information, such as duplicate enterprise records and incorrect industry codes, is removed through data cleaning. Missing values, such as undisclosed registered capital, are filled in. Key features of unstructured public information are extracted and classified. Finally, all processed data are integrated to generate a standard dataset that meets the template requirements, ensuring that data from different sources and formats are presented under a unified framework, providing a structured and highly consistent input foundation for subsequent analysis.

[0046] In one embodiment of this application, the data source is normalized based on a preset template file to generate standard data, including:

[0047] Based on a preset template file, the data type and keywords of the data source are identified;

[0048] Calculate the text length of each data type in the data source, and calculate the word frequency of keywords in the data source;

[0049] Based on the text length corresponding to the data type and the word frequency of the keywords, dynamic parameters are generated;

[0050] The data source is normalized using the dynamic parameters to generate standard data.

[0051] In one embodiment of this application, the data type and keywords of the data source are identified based on a preset template file. The data type includes structured data (such as industry codes) and unstructured data (such as publicly available information).

[0052] In one embodiment of this application, the text length of each data type in the data source is counted, and the word frequency of keywords in the data source is counted. Specifically, the keyword frequency is counted for each data source (such as business scope text), the text length is counted for unstructured data, such as news text, and the number of records, such as the number of digits in the code, is counted for structured data, such as industry codes.

[0053] In one embodiment of this application, dynamic parameters are generated based on the text length corresponding to the data type and the word frequency of the keywords. for:

[0054] ,

[0055] in, Indicates data source Information parameters, respectively represent the adjustment factor of the information parameter and the text length respectively represent the data identification of the data source, i and j respectively represent the data identification of the data source, n represent the total amount of data in the data source.

[0056] In an embodiment of the present application, the data source is normalized by the dynamic parameter, and the data of multiple sources is dynamically weighted and fused based on the dynamic parameter to generate structured data in a unified format as standard data.

[0057] In an embodiment of the present application, through dynamic weight distribution, data sources with large information amount and rich content, such as detailed annual report texts, are preferentially used, and the interference of low-quality data (such as short news clips) is reduced. On the other hand, when different data sources describe the same enterprise inconsistently, such as the conflict between the business scope text and the industry code, the source with higher credibility is determined through weight distribution.

[0058] For example, if the keyword "marine engineering" appears frequently and the text length is long in the enterprise annual report, the dynamic parameter corresponding to the annual report is higher, and this data source is given greater weight in label generation. Through the above process, scientific fusion of multi-source data is realized, data quality is ensured, the accuracy and comprehensiveness of label information are improved, and a reliable data foundation is laid for subsequent determination of marine-related enterprises.

[0059] The above process generates dynamic parameters based on preset templates to identify data types and keywords, and counts text lengths and word frequencies, which can adapt to format differences of different data sources, such as weight balance of long text description and short code, and improve data consistency. For example, for "marine engineering" enterprises, the dynamic parameter can strengthen the weight of the industry code and weaken the interference of redundant general words.

[0060] S130, based on the keywords in the standard data, determining the label information corresponding to the enterprise to be processed, and judging whether the enterprise to be processed belongs to a marine-related enterprise according to the label information.

[0061] In an embodiment of the present application, first, a preset marine-related keyword library in the enterprise data is scanned, such as marine engineering, ship transportation or port services, etc., relevant words in the business scope, industry code and public information are extracted through natural language processing technology, and initial labels are generated. Then, according to the label weight, such as keyword appearance frequency and industry code matching degree, sorting is performed, if the number or weight of marine-related labels exceeds the preset threshold, it is determined as a marine-related enterprise, if there is a conflict of non-marine-related labels, it is determined through associated enterprise analysis or manual review assisted decision, finally the classification result is output and the label generation time is recorded to support dynamic update.

[0062] Specifically, in the embodiment, according to the construction idea of the basic unit name library of marine economic activities, combined with the registration and registration data of commercial subjects, a commercial subject identification logic system of marine economic activities is constructed from three dimensions of industry name items, business scope standard expression items and national economic industry code items.

[0063] As shown in Figure 2 In one embodiment of the present application, based on the keywords in the standard data, the label information corresponding to the to-be-processed enterprise is determined, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, comprising:

[0064] S210, based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code;

[0065] S220, comparing between the business scope and the registration information, determining a first marine-related level and a second marine-related level according to the generated comparison result;

[0066] S230, based on the combination code, the first marine-related level and the second marine-related level, generating the label information of the to-be-processed enterprise;

[0067] S240, comparing the label information with a preset label, judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0068] In one embodiment of the present application, in S210, based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code, comprising:

[0069] Based on the preset business scope corresponding relationship, the first identification corresponding to the business scope in the standard data is determined;

[0070] Based on the preset industry code corresponding relationship, the second identification corresponding to the industry code in the standard data is determined;

[0071] Combining the first identification and the second identification, a combination code is generated.

[0072] Specifically, in the embodiment, there are 2027 business scope standard expression items in the business scope standard management service platform. According to the direct identification, industry area identification, main business identification and investigation identification, the marine-related situation of each item in the "Business Scope Standard Expression Directory" is comprehensively judged and marked, and a business scope expression item and marine and related industry classification table is formed.

[0073] In the above manner, 80 "I-level" directly identified marine-related items, 86 "II-level" highly marine-related items, and 423 "III-level" possibly marine-related items are sorted out from the 2027 items of the business scope standard expression table. By matching the items in the above-mentioned "Business Scope Standard Expression Directory" with the corresponding level information with the business scope in the standard data, the first identifier corresponding to the business scope is finally determined.

[0074] Specifically, in the present embodiment, according to the "Marine and Related Industries Classification" (GB / T 20794-2021), 472 small-class national economic industry codes covered by marine economic activities are marked by levels. The second identifier is generated by the following process:

[0075] 1. For the marine industries that have been clearly identified in the national economic industry classification, i.e., only according to the unit's national economic industry classification, the marine attribute of the industry code can be determined, such as 18 directly identified industry codes, such as 0411 mariculture, 0421 marine fishing, 0712 offshore oil exploitation, and 0722 marine natural gas and combustible ice exploitation. Industry codes in the unit's national economic industry classification corresponding to marine industries and located in coastal areas are marked as "I-level" directly identified marine-related items;

[0076] 2. For the highly marine-related but further determined according to the main business of the industry code, such as 27 industry codes, such as 0541 fry and seedling field activities, 1361 aquatic product freezing processing, etc. Marked as "II-level" highly marine-related items;

[0077] 3. For other marine and related industry corresponding national economic industry codes, mark them as "III-level" possibly marine-related items.

[0078] Through the above process, 37 "I-level" directly identified marine-related items, 27 "II-level" highly marine-related items, and 408 "III-level" possibly marine-related items are sorted out from the 1383 national economic industry codes. By matching the level information of each item with the industry code in the standard data, the second identifier corresponding to the industry code is finally determined.

[0079] After generating the first identifier and the second identifier, the first identifier and the second identifier are combined to generate a combined code.

[0080] In an embodiment of the present application, the method further comprises:

[0081] determining a third identifier corresponding to the industry name in the standard data based on a preset industry name correspondence relationship;

[0082] The first identification, the second identification, and the third identification are combined to generate a combination code.

[0083] Specifically, in the embodiment, there are 12582 industry name entries in the business scope standard management service platform, which are marked according to the general marine economic activity unit registration unit name and industry coverage. Specifically, the third identification is generated by the following process classification:

[0084] 1. For keywords obviously having marine economic activity characteristics, such as containing “marine”, “ocean” or “ship”, etc., mark them as “level I” to directly identify the marine-related entries;

[0085] 2. For keywords that may have marine economic activity characteristics and need to be further identified, such as “underwater engineering service”, “fishery” or “wind power”, etc., mark them as “level II” to identify high marine-related entries;

[0086] 3. For keywords that cannot be directly determined whether they have marine economic activity characteristics, such as “instrument and meter technology” or “industry operation service”, etc., mark them as “level III” to identify possible marine-related entries.

[0087] From the 12582 industry name entries, 434 “level I” directly identified marine-related entries, 185 “level II” high marine-related entries, and 5093 “level III” possible marine-related entries are sorted out. Through the grade information of each entry corresponding to the above, the industry name corresponding to the third identification is matched with the standard data.

[0088] Optionally, the first identification, the second identification, and the third identification can also be combined to generate a combination code to more comprehensively describe the enterprise to be processed through a three-bit combination code.

[0089] The above process enhances the uniqueness and accuracy of the label through the multi-dimensional combination of the first identification corresponding to the business scope, the second identification corresponding to the industry code, and the third identification corresponding to the industry name. For example, a certain enterprise has an industry code of “pipeline engineering”, but its business scope includes “submarine pipeline laying”, and the combination code can be associated with the marine-related engineering field, solving the limitations of single field matching.

[0090] In S220, the business scope and the registration information are compared, and the first marine-related level and the second marine-related level are determined according to the generated comparison result. Specifically, the first marine-related level and the second marine-related level are determined by detecting the order of the expression entries of the business scope corresponding to the registration information of the enterprise, such as the first three or the last three. For example, if the second entry of the expression entries of the business scope corresponds to the registration information of the enterprise, the corresponding first marine-related level is “level II”.

[0091] The above process generates two levels by comparing the business scope and the registration information, cross- verifies the consistency of the actual business and the registration information of the enterprise, and reduces the risk of false registration. For example, the registration information is "pipeline installation", but the business scope contains "marine oil and gas pipeline". The level difference can trigger manual review.

[0092] After generating the combination code, the first marine-related level and the second marine-related level, the label information of the to-be-processed enterprise is generated based on the above information. Then, the label information is compared with the preset label, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result. The generated label is compared with the preset marine-related label library to realize automatic classification and improve the determination efficiency.

[0093] S140, if the to-be-processed enterprise is not marine-related, the label information of the to-be-processed enterprise and the public information are matched to determine whether the to-be-processed enterprise is a marine-related enterprise.

[0094] In an embodiment of the present application, for enterprises preliminarily determined as not marine-related, the label information (such as industry code, business scope keywords) and the public information (such as news, contract records or news data) are automatically extracted and cross-matched. Potential marine-related keywords such as "marine resource development", "marine transportation cooperation" and the like are identified through natural language processing technology. If the number or weight of the matched marine-related public information exceeds a preset threshold, or if evidence of recent addition of marine-related business of the enterprise is found, such as signing a marine project contract or participating in a port construction bid, the determination result is corrected to a marine-related enterprise, and the label information and the determination time stamp are updated simultaneously to ensure that the classification result is consistent with the actual operating state of the enterprise.

[0095] In an embodiment of the present application, the label information of the to-be-processed enterprise and the public information are matched based on a preset database to determine whether the to-be-processed enterprise is a marine-related enterprise, comprising:

[0096] The label information of the to-be-processed enterprise and the public information are matched based on a preset database to determine a marine-related parameter.

[0097] If the marine-related parameter is greater than or equal to a preset marine-related threshold, it is determined that the to-be-processed enterprise is marine-related.

[0098] In an embodiment of the present application, the label information includes a label corresponding to the to-be-processed enterprise and the membership degree of the label to the enterprise. The label information of the to-be-processed enterprise and the public information are matched to determine the marine-related parameter of the enterprise e as follows:

[0099] , ​

[0100] wherein, e and l respectively represent enterprise identification and label information, represent label information l membership of the enterprise; e respectively represent marine-related label set and non-marine-related label set; represent the difference between label timestamp and current time, represent the preset time decay coefficient.

[0101] In the above process, the membership quantifies the association strength between the enterprise and the label, avoiding errors caused by hard classification. At the same time, through the time decay factor, the weight of old labels can be automatically reduced to adapt to the dynamic changes of enterprise business. On the other hand, by reducing the weight of old labels over time, such as the "marine engineering" label 5 years ago, the dynamic changes of enterprise business are reflected.

[0102] In the embodiments of the present application, if the marine-related parameter is greater than or equal to the preset marine-related threshold, the enterprise is determined to be marine-related.

[0103] In addition, if the marine-related parameter is less than the marine-related threshold and greater than the non-marine-related threshold, manual review is triggered. If the marine-related parameter is less than the non-marine-related threshold, the enterprise is determined to be non-marine-related.

[0104] For example, assume that the label of an enterprise is as follows: marine-related labels include "marine engineering" ( =0.8, generated in 2020, =5), "shipbuilding" ( =0.6, generated in 2023, =2); non-marine-related labels include "software development" ( =0.7, generated in 2024, =1). If λ=0.2, the marine-related parameter is calculated to be 0.45. If the marine-related threshold and the non-marine-related threshold are 0.7 and 0.3 respectively, manual review is triggered.

[0105] It should be noted that if the review finds that the enterprise has transformed into a "marine engineering + software development" hybrid mode, the label information is corrected and recalculated. Through the above process, on the basis of judging whether the enterprise to be processed belongs to a marine-related enterprise, dynamic verification and correction of labels are realized, ensuring the accuracy and real-time performance of marine-related enterprise determination.

[0106] ​The above process is based on database matching label information and public information such as news and bidding data to calculate the marine-related parameters. By setting a threshold, the marine-related enterprise is determined, and the potential error of the initial label is solved. For example, a certain enterprise label is "non-marine-related", but the public information shows that it participates in "offshore wind power projects", which can be corrected by the marine-related parameters to determine the result and improve the accuracy of the determination result.

[0107] S150, generating a unit directory of marine economic activities based on the marine-related enterprises to build an enterprise identification library through the unit directory.

[0108] In an embodiment of the present application, based on the determined marine-related enterprise data, first, the core fields such as enterprise name, industry code, business scope, registration information and determination basis are summarized, and the records with missing or conflicting information are excluded through data verification, then classified and labeled according to the type of marine economic activities such as marine engineering, port services, marine logistics, etc., and associated with the region where the enterprise is located, the time of establishment, etc. Form a structured directory. Finally, the directory is imported into a special database, set a regular update rule such as monthly synchronization of the latest determination results, automatic correction of change information, and at the same time configure a permission management module to control the data access range, complete the initialization construction and continuous maintenance of the enterprise identification library.

[0109] In an embodiment of the present application, generating a unit directory of marine economic activities based on the marine-related enterprises to build an enterprise identification library, comprising:

[0110] Generating enterprise parameters based on the marine-related parameters and determination time stamps of the marine-related enterprises;

[0111] Ranking the marine-related enterprises according to the enterprise parameters to generate a unit directory to build an enterprise identification library based on the unit directory.

[0112] In an embodiment of the present application, generating enterprise parameters based on the marine-related parameters and determination time stamps of the marine-related enterprises For:

[0113] ,

[0114] Among them, A, B and C respectively represent the enterprise factors set by the business rules, respectively represent the marine-related parameters and the associated enterprise set of the marine-related enterprises, e represents the time decay coefficient, represents the current time and the time when the enterprise information was last updated.

[0115] ​In the above process, the intensity of the current marine-related activities of the enterprise is directly reflected by the self-confidence, the influence of the fluctuation of the single-point data of the average confidence of the associated enterprise is reflected by the stability of the associated enterprise, and the latest data is ensured to have a higher weight and the old data is decayed over time through the time decay effect.

[0116] In an embodiment of the present application, after generating the enterprise parameters, the marine-related enterprises are ranked according to the enterprise parameters, a unit directory is generated, and an enterprise identification library is constructed based on the unit directory.

[0117] The technical scheme of the present application obtains the data source of the enterprise to be processed, performs normalization processing on the data source based on a preset template file to generate standard data, determines the label information corresponding to the enterprise to be processed based on the keywords in the standard data, and judges whether the enterprise to be processed is a marine-related enterprise according to the label information. If the enterprise to be processed is not marine-related, the label information of the enterprise to be processed and the public information are matched to judge whether the enterprise to be processed is a marine-related enterprise. A unit directory of marine economic activities is generated based on the marine-related enterprises to construct an enterprise identification library through the unit directory. The standard data is generated by integrating multiple data sources through normalization processing to ensure data consistency. The keywords are used to generate labels and secondary verification to improve the accuracy of marine-related enterprise determination. Finally, a dynamically updated unit directory of marine economic activities is constructed to realize real-time management and identification of marine-related enterprises. The accuracy and efficiency of enterprise management are improved, and structured and high-credibility enterprise identification support is provided for marine economic governance.

[0118] The following describes an embodiment of the marine-related enterprise management system based on intelligent labels of the present application, which can be used to execute the marine-related enterprise management method based on intelligent labels in the above embodiments of the present application. It can be understood that the marine-related enterprise management system based on intelligent labels can be a computer program (including program code) running in a computer device, for example, the marine-related enterprise management system based on intelligent labels is an application software; the marine-related enterprise management system based on intelligent labels can be used to execute the corresponding steps in the method provided in the embodiments of the present application. For details not disclosed in the embodiment of the marine-related enterprise management system based on intelligent labels of the present application, please refer to the above embodiment of the marine-related enterprise management method based on intelligent labels of the present application.

[0119] Figure 3 A block diagram of the marine-related enterprise management system based on intelligent labels according to an embodiment of the present application is shown.

[0120] Referring to Figure 3 According to an embodiment of the marine-related enterprise management system based on intelligent labels of the present application, as shown in the figure, the marine-related enterprise management system based on intelligent labels comprises:

[0121] The acquisition unit 310 is used to acquire the data source of the enterprise to be processed; wherein, the data source includes business scope, industry code, registration information and public information;

[0122] Data unit 320 is used to normalize the data source based on a preset template file to generate standard data;

[0123] The tag unit 330 is used to determine the tag information corresponding to the enterprise to be processed based on the keywords in the standard data, and to determine whether the enterprise to be processed belongs to the marine-related enterprises based on the tag information.

[0124] Information unit 340 is used to match the tag information of the enterprise to be processed with the public information if the enterprise to be processed is not involved in the sea, and to determine whether the enterprise to be processed is an enterprise involved in the sea.

[0125] The construction unit 350 is used to generate a list of entities engaged in marine economic activities based on the marine-related enterprises, so as to construct an enterprise identification database through the list of entities.

[0126] In this application, based on the aforementioned scheme, the step of normalizing the data source based on a preset template file to generate standard data includes: identifying the data type and keywords of the data source based on the preset template file; calculating the text length of each data type in the data source and calculating the word frequency of the keywords in the data source; generating dynamic parameters based on the text length corresponding to the data type and the word frequency of the keywords; and normalizing the data source using the dynamic parameters to generate standard data.

[0127] In this application, based on the aforementioned scheme, the step of generating dynamic parameters based on the text length corresponding to the data type and the word frequency of the keywords includes: determining the information parameters corresponding to the data source based on the data content of the data source; and generating dynamic parameters according to the information parameters corresponding to the data source, the text length corresponding to the data type, and the word frequency of the keywords.

[0128] In this application, based on the aforementioned scheme, the step of generating dynamic parameters according to the information parameters corresponding to the data source, the text length corresponding to the data type, and the word frequency of the keywords includes: generating dynamic parameters according to the information parameters corresponding to the data source, the text length corresponding to the data type, and the word frequency of the keywords. for:

[0129] ,

[0130] in, Indicates data source Information parameters, Representing information parameters respectively and text length of the adjustment factor, i and j respectively represent the data identification of the data source, n represent the total amount of data in the data source.

[0131] In the present application, based on the foregoing scheme, the keyword in the standard data is used to determine the label information corresponding to the to-be-processed enterprise, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, which comprises: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing the business scope with the registration information, and determining the first marine level and the second marine level according to the generated comparison result; based on the combination code, the first marine level and the second marine level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0132] In the present application, based on the foregoing scheme, the keyword in the standard data is used to determine the label information corresponding to the to-be-processed enterprise, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, which comprises: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing the business scope with the registration information, and determining the first marine level and the second marine level according to the generated comparison result; based on the combination code, the first marine level and the second marine level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0133] In the present application, based on the foregoing scheme, the keyword in the standard data is used to determine the label information corresponding to the to-be-processed enterprise, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, which comprises: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing the business scope with the registration information, and determining the first marine level and the second marine level according to the generated comparison result; based on the combination code, the first marine level and the second marine level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0134] In the present application, based on the foregoing scheme, the keyword in the standard data is used to determine the label information corresponding to the to-be-processed enterprise, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, which comprises: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing the business scope with the registration information, and determining the first marine level and the second marine level according to the generated comparison result; based on the combination code, the first marine level and the second marine level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0135] In the present application, based on the foregoing scheme, the keyword in the standard data is used to determine the label information corresponding to the to-be-processed enterprise, and it is judged whether the to-be-processed enterprise belongs to a marine-related enterprise according to the label information, which comprises: based on the preset matching relationship, the business scope and the industry code in the standard data are matched respectively to generate a combination code; comparing the business scope with the registration information, and determining the first marine level and the second marine level according to the generated comparison result; based on the combination code, the first marine level and the second marine level, the label information of the to-be-processed enterprise is generated; comparing the label information with the preset label, and judging whether the to-be-processed enterprise belongs to a marine-related enterprise according to the comparison result.

[0136] The technical scheme of the present application obtains a data source of a to-be-processed enterprise; performs normalization processing on the data source based on a preset template file to generate standard data; determines label information corresponding to the to-be-processed enterprise based on a keyword in the standard data, and judges whether the to-be-processed enterprise belongs to a sea-related enterprise according to the label information; if the to-be-processed enterprise is not sea-related, matches the label information of the to-be-processed enterprise with the public information to judge whether the to-be-processed enterprise belongs to a sea-related enterprise; and generates a unit directory of marine economic activities based on the sea-related enterprise to build an enterprise identification library through the unit directory. The standard data is generated by integrating multiple data sources and performing normalization processing, ensuring data consistency; the keyword is used to generate a label and perform secondary verification, improving the accuracy of sea-related enterprise determination; and finally a dynamically updated unit directory of marine economic activities is built, realizing real-time management and identification of sea-related enterprises. The accuracy and efficiency of enterprise management are improved, and structured and high-credibility enterprise identification support is provided for marine economic governance.

[0137] Figure 4 A structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown.

[0138] It should be noted that the computer system of the electronic device in the present embodiment is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0139] The computer system in the present embodiment includes a central processing unit 401 which can perform various appropriate actions and processes according to programs stored in a read-only memory 402 or loaded into a random access memory 403 from a storage part 408, such as the intelligent label-based sea-related enterprise management method described in the above embodiments. Various programs and data required for system operation are also stored in the random access memory 403. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other through a bus 404. An input / output interface 405 is also connected to the bus 404.

[0140] The following components are connected to the input / output interface 405: an input portion 406 including input devices such as a keyboard and a mouse; an output portion 407 including output devices such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage portion 408 including a hard disk; and a communication portion 409 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as necessary. A removable media 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 410 as necessary, so that a computer program read therefrom is installed in the storage portion 408 as necessary.

[0141] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing computer programs for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication portion 409, and / or installed from the removable media 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0142] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer-readable signal medium can include a data signal carrying computer-readable computer programs in a baseband or as a part of a carrier wave. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, device or apparatus. The computer programs contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0143] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In the flowcharts or block diagrams, each block can represent a module, a program segment or a part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks represented in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0144] The units described in the embodiments of the present application can be implemented by software, or by hardware, or by a combination of software and hardware. The units described can also be located in a single processor. In some cases, the names of the units do not limit the units themselves.

[0145] According to an aspect of the present application, there is provided a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method provided in the various optional implementation manners described above.

[0146] As another aspect, the present application also provides a computer readable medium, which can be included in the electronic device described in the embodiments above, or can exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the method for marine-related enterprise management based on smart labels described in the embodiments above.

[0147] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, the division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units.

[0148] From the above description of the embodiments, those skilled in the art will readily appreciate that the example embodiments described herein can be implemented by software and / or by hardware coupled with software. Accordingly, the technical solutions of the embodiments of the present application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or network, and includes several instructions to make a computing device (which can be a personal computer, server, touch terminal, or network device, etc.) execute the methods according to the embodiments of the present application.

[0149] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice in the art to which the application pertains.

[0150] It is to be understood that the application is not limited to the precise construction already described above and shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should only be limited by the claims appended hereto.

Claims

1. A smart tag-based maritime business management method, characterized by, The method comprises the following steps: obtaining a data source of an enterprise to be processed, wherein the data source comprises a business scope, an industry code, registration information, and public information, and the public information comprises unstructured data reflecting enterprise dynamics and social evaluation; normalizing the data source based on a preset template file to generate standard data; determining label information corresponding to the enterprise to be processed based on a keyword in the standard data, and determining whether the enterprise to be processed is a marine-related enterprise according to the label information; if the enterprise to be processed is not marine-related, matching the label information corresponding to the enterprise to be processed and the public information based on a preset database to determine a marine-related parameter; if the marine-related parameter is greater than or equal to a preset marine-related threshold, determining that the enterprise to be processed is a marine-related enterprise; generating a unit directory of marine economic activities based on the marine-related enterprise to build an enterprise identification library through the unit directory.

2. The smart tag-based maritime business management method according to claim 1, characterized by, The method comprises the following steps: normalizing the data source based on a preset template file to generate standard data, comprising: identifying the data type and keyword of the data source based on the preset template file; counting the text length of each data type data in the data source and the word frequency of the keyword; generating a dynamic parameter based on the text length corresponding to the data type and the word frequency of the keyword; 3. The smart tag-based maritime business management method according to claim 1, characterized by, normalizing the data source based on the dynamic parameter to generate standard data. The method comprises the following steps: determining label information corresponding to the enterprise to be processed based on a keyword in the standard data, and determining whether the enterprise to be processed is a marine-related enterprise according to the label information, comprising: matching the business scope and industry code in the standard data respectively based on a preset matching relationship to generate a combination code; comparing the business scope and the registration information, and determining a first marine-related level and a second marine-related level according to the comparison result; 4. The smart tag-based maritime business management method according to claim 3, characterized by, generating label information corresponding to the enterprise to be processed based on the combination code, the first marine-related level, and the second marine-related level; comparing the label information with a preset label, and determining whether the enterprise to be processed is a marine-related enterprise according to the comparison result. The method comprises the following steps: matching the business scope and industry code in the standard data respectively based on a preset matching relationship to generate a combination code, comprising:

5. The smart tag-based maritime business management method according to claim 4, characterized by, determining a first identifier corresponding to the business scope in the standard data based on a preset business scope correspondence relationship; determining a second identifier corresponding to the industry code in the standard data based on a preset industry code correspondence relationship; combining the first identifier and the second identifier to generate a combination code.

6. The smart tag-based maritime business management method according to claim 1, characterized by, After determining the second identifier corresponding to the industry code in the standard data based on the preset industry code correspondence relationship, the method further comprises the following steps: determining a third identifier corresponding to the industry name in the standard data based on a preset industry name correspondence relationship; combining the first identifier, the second identifier, and the third identifier to generate a combination code. The method comprises the following steps: generating enterprise parameters based on the marine-related parameters and the determination time stamp of the marine-related enterprise; ranking the marine-related enterprise according to the enterprise parameters, generating a unit directory, and constructing an enterprise identification library based on the unit directory.

7. A smart tag-based maritime business management system, characterized by, The method comprises the following steps: an acquisition unit is configured to acquire a data source of an enterprise to be processed; wherein the data source comprises an operating range, an industry code, registration information, and public information; wherein the public information comprises unstructured data reflecting enterprise dynamics and social evaluation; a data unit is configured to normalize the data source based on a preset template file to generate standard data; a label unit is configured to determine label information corresponding to the enterprise to be processed based on keywords in the standard data, and determine whether the enterprise to be processed is a marine-related enterprise according to the label information; an information unit is configured to match the label information corresponding to the enterprise to be processed and the public information based on a preset database to determine a marine-related parameter if the enterprise to be processed is not marine-related; and determine that the enterprise to be processed is a marine-related enterprise if the marine-related parameter is greater than or equal to a preset marine-related threshold; a construction unit is configured to generate a unit directory of marine economic activities based on the marine-related enterprise, and construct an enterprise identification library through the unit directory.

Images