A green procurement list management system

Abstract

This invention relates to a green procurement list management system, comprising: a data collection, processing, and database subsystem for collecting data sources and constructing a big data index library; an applicant enterprise module of the green procurement list management subsystem for receiving enterprise login information; a certification body module for verification based on certification certificates and PI N codes, calling the big data index library; an applicant enterprise module receiving enterprise information and application information after receiving a certification approval message, the enterprise information including basic enterprise information and sales contact information, and the application information including product information and a commitment letter; a management body generating list publicity information based on enterprise information and application information, and displaying the product list and enterprises; sending the list publicity information to the applicant enterprise module; and a management body module receiving review information for adjustments to product information, and generating official list information after approval.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a green procurement list management system. Background Technology

[0002] There is an urgent need to apply mainstream information management and big data technologies to create information resource databases for enterprise environmental protection requirements, environmental labeling product information, and enterprise environmental archives. This will involve collecting, analyzing, processing, and managing various types of unstructured data, targeting interface methods with existing information systems, in order to initially form an effective big data collection database for enterprise environmental information.

[0003] In the existing technology, the data in the existing green procurement list management system requires a lot of manual processing by business personnel to finally form a public list (only twice a year); if the frequency of list publication is adjusted to once a month, it is basically impossible to complete the list publication manually.

[0004] The system's operation relies heavily on existing developers for data processing, impacting its long-term health and maintenance. The inability to automate data integration, coupled with the increasing business and data volume of the new generation of products, will inevitably increase the IT maintenance burden on both systems.

[0005] Therefore, there is an urgent need for a new green procurement list management system. Summary of the Invention

[0006] The purpose of this invention is to provide a green procurement list management system to address the shortcomings of existing technologies and solve the problems existing in the prior art.

[0007] To achieve the above objectives, the present invention provides a green procurement list management system, comprising:

[0008] The data acquisition, processing, and database subsystem is used to acquire data sources, including a first type of data source and a second type of data source; it processes the first type of data source and the second type of data source to build a big data index library.

[0009] The green procurement list management subsystem includes modules for management organizations, certification bodies, and applicant companies.

[0010] The application enterprise module is used to receive enterprise login information, which includes an authentication certificate and a PIN code, and to send the authentication certificate and PIN code to the certification authority module.

[0011] The certification authority module verifies the certification certificate and the PIN code by calling the big data index database. After successful verification, it sends a certification success message to the applicant enterprise module.

[0012] Upon receiving the authentication approval message, the applicant enterprise module receives enterprise information and application information, including basic enterprise information and sales contact information, and product information and a commitment letter; and then sends the product information and application information to the management agency module.

[0013] The management agency generates a list of public information based on the enterprise information and application information, and displays the product list and enterprises; the list of public information is then sent to the applicant enterprise module.

[0014] The applying enterprise module receives the adjusted product information in response to the list of public information, and sends the adjusted product information to the management agency module;

[0015] The management module receives the review information for the adjusted product information and generates an official list after the review is approved.

[0016] In one possible implementation, the management agency module is further configured to intelligently review the submitted information using machine learning and natural language processing technologies to identify risk points and non-compliance items. In another possible implementation, the certification agency module verifies the certification certificate and the PI N code by calling the big data index database. Upon successful verification, it sends a certification approval message to the applicant enterprise module, specifically for the following purposes:

[0017] The certification body module verifies the enterprise by calling the big data index library based on the certification certificate and the PI N code. After the enterprise is verified, the product is verified. After the product is verified, an environmental labeling certificate is generated and sent to the data collection, processing and database subsystem.

[0018] The data collection, processing, and database subsystem stores the environmental certification.

[0019] In one possible implementation, the basic enterprise information includes the manufacturer's name, manufacturer's address, enterprise type, legal representative, organization code certificate, contact person's name, contact person's landline phone number, contact person's email address, and contact person's mobile phone number; the detailed shareholder information includes the shareholder's name, investment amount, and investment ratio; and the sales contact information includes the names and contact information of the sales contact person and the supervisor.

[0020] In one possible implementation, the product information includes application guidelines, product editing, draft list, product list query, review status query, and historical product functions.

[0021] In one possible implementation, the applicant enterprise module, before receiving the application information, further includes:

[0022] When a product is selected to be added to the procurement list and a CA electronic signature is received, declaration information is generated.

[0023] In one possible implementation, the management module is further configured to extract and save the commitment letter from the declaration information.

[0024] In one possible implementation, the data acquisition, processing, and database subsystem is specifically used for:

[0025] The second type of data source is unstructured data; including text files, image data, audio data, and video data.

[0026] The text files, image data, audio data, and video data are cleaned and their formats converted.

[0027] Extract keywords from text data;

[0028] Feature extraction from image data using computer vision technology;

[0029] Audio features are extracted from audio data using sound recognition technology; the audio features include pitch and frequency.

[0030] Based on computer vision and sound recognition technologies, video data is processed to obtain time-series image data and audio features;

[0031] Label keywords, image data features, and audio features, and add classification tags;

[0032] Based on data characteristics and query requirements, the index structure is determined; the index structure includes inverted indexes, hash tables, and tree structures.

[0033] An index is constructed based on the extracted features and the index structure.

[0034] In one possible implementation, the data acquisition, processing, and database subsystem is further used to compress or partition the index to optimize it.

[0035] By applying the green procurement list management system provided in this embodiment of the invention, an index can be built based on big data, and tripartite connection between enterprises, certification and management agencies can be achieved, thereby improving procurement processing efficiency. Attached Figure Description

[0036] Figure 1 A schematic diagram of the structure of the green procurement list management system provided in this embodiment of the invention;

[0037] Figure 2 A flowchart for the data acquisition, processing, and database subsystem. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0039] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0040] Figure 1 This is a schematic diagram of the green procurement list management system provided in an embodiment of the present invention. The green procurement list management system includes a data collection, processing, and database subsystem and a green procurement list management subsystem. The following is in conjunction with... Figure 1 The technical solution of the present invention will be described with reference to specific embodiments.

[0041] The data acquisition, processing, and database subsystem 1 is used to acquire data sources, including a first type of data source and a second type of data source; it processes the first type of data source and the second type of data source to build a big data index library.

[0042] Specifically, the first type of data source is structured data, and the second type of data source is unstructured data.

[0043] For the first type of data source, you can directly build single-column indexes, composite indexes, unique indexes, full-text indexes, clustered indexes, and non-clustered indexes. When building indexes for structured data, you can analyze the requirements, determine which fields are most frequently used in queries, and consider the selectivity of these fields, i.e., the ratio of the number of distinct values ​​to the total number of records. Then, choose an appropriate index type, that is, select the appropriate index type based on the data type of the field and the query requirements. Finally, create the index, that is, use SQL statements or other database management tools to create the index.

[0044] For unstructured data, including text files, image data, audio data, and video data, the process begins with cleaning and format conversion. Cleaning removes irrelevant or redundant information, such as HTML tags and special characters, while formatting converts data from different formats into a unified format for easier subsequent processing. Next, keyword extraction is performed on the text data. Natural language processing techniques (such as word segmentation, stemming, and word vectorization) can be used to extract keywords, themes, and other features. Then, computer vision techniques are used to extract features from the image data, for example, using convolutional neural networks. Next, audio features are extracted from the audio data using sound recognition technology, including pitch and frequency. Then, video data is processed using computer vision and sound recognition technologies to obtain time-series image data and audio features. Finally, keywords, image data features, and audio features are labeled and categorized. For example, data can be manually or automatically labeled, adding categorization labels or other attribute information to each data point. Next, based on data characteristics and query requirements, the index structure is determined; this index structure includes inverted indexes, hash tables, and tree structures. Finally, based on the extracted features and the index structure, an index is constructed. Thus, building an index based on extracted features enables the rapid location of relevant data records.

[0045] Furthermore, indexes can be compressed or partitioned to optimize them.

[0046] This application focuses on green procurement. Therefore, the index library built by the data collection, organization, and database subsystem can organize big data document sources for each enterprise, thereby establishing the big data index library, which facilitates subsequent enterprise certification, verification, and other operations.

[0047] The Green Procurement List Management Subsystem 2 consists of an application enterprise module 21, a certification body module 22, and a management organization module 23. The management organization module can be the module logged in by the administrator's terminal, the certification body module can be the module used by the certification body's terminal to access the certification body, and the application enterprise module is the module logged in by the enterprise's terminal.

[0048] The application enterprise module is used to receive enterprise login information, which includes an authentication certificate and a PIN code, and to send the authentication certificate and PIN code to the certification authority module.

[0049] The certification authority module verifies the certification certificate and the PIN code by calling the big data index database. After successful verification, it sends a certification success message to the applicant enterprise module.

[0050] The big data index contains enterprise information, including the number of certified employees and PI N codes. You can directly call the index to determine whether the certification certificate and PI N code exist.

[0051] Upon receiving the authentication approval message, the applicant enterprise module receives enterprise information and application information. The enterprise information includes basic enterprise information, detailed shareholder information, and sales contact information. The application information includes product information and a commitment letter. The module then sends the product information and application information to the management agency module.

[0052] The basic enterprise information includes the manufacturer's name, address, enterprise type, legal representative, organization code certificate, contact person's name, landline phone number, email address, and mobile phone number. The detailed shareholder information includes the shareholder's name, investment amount, and investment ratio. The sales contact information includes the name and contact information of the sales contact person and their supervisor. Product information refers to the basic information of the products to be declared. The commitment letter is submitted after receiving confirmation of the "commitment" option when submitting the declaration information. Commitment letters include enterprise commitment letters and historical commitment letters. The enterprise commitment letter represents the enterprise's commitment to the products included in the list, and is legally binding with a CA electronic signature. Once the commitment letter is signed, the product editing and deletion functions will be disabled. To sign the commitment letter, click "Sign and Seal," and then click "Submit" after the "Signing Successful" message appears. Historical commitment letters are archived and managed by the enterprise, and can be viewed.

[0053] During the public notice period and before the company's commitment letter is signed, detailed product information can be filled in and maintained; this includes product querying and exporting. Querying includes searching for the company's products by category, brand, product model, certificate number, certificate expiration date, whether they are included in the list, and product status. Exporting includes generating an Excel file. Editing is only allowed during the reporting period and before a commitment letter is signed. If "Add to Purchase List" is selected as "Yes," all required fields must be filled in before saving. If "Add to Purchase List" is selected as "No," required fields can be left blank and the file can be saved. Product details and product images are not required fields; all others are required.

[0054] The management agency generates a list of public information based on the enterprise information and the application information, and displays the product list and enterprises; the list of public information is then sent to the applicant enterprise module.

[0055] The list includes a product list, which comprises a list of company products, a draft list for public comment, a draft list for approval, and a backup of the current data archive. The draft list for approval allows users to view product data from companies that have passed the review process.

[0056] The applying enterprise module receives the adjusted product information in response to the list of public information, and sends the adjusted product information to the management agency module;

[0057] Among them, "adjusted product information" refers to the information after adjustments to the product information.

[0058] The management module receives the review information for the adjusted product information and generates an official list after the review is approved.

[0059] The management module is also used to intelligently review the submitted information using machine learning and natural language processing technologies to identify risk points and non-compliance items.

[0060] Specifically, first, a large amount of historical application information is collected, including approved and unapproved cases. Corresponding review results are collected, including approval, rejection, and requests for supplementary materials. Risk points and non-compliance items are marked for each application. Then, data preprocessing is performed, including text cleaning to remove irrelevant characters, punctuation, stop words, etc., retaining the core content. Standardization is performed, such as unifying date formats and monetary units. Feature extraction is performed, extracting useful features from the text, such as keywords, entities, and syntactic structures. Next, feature engineering is performed, including text feature extraction, including calculating word importance to distinguish keywords from common words. Pre-trained word embedding models (such as Word2Vec and GloVe) are used to convert words into vector representations. Named entity recognition is performed to identify and extract entity information such as names of people, places, and organizations. Feature extraction includes field value extraction, extracting key field values ​​from the application form, such as applicant name, contact information, and application type. Time feature extraction is performed, extracting time-related features such as application date and deadline. Numerical feature extraction is performed, extracting numerical features such as quantity. Next, model selection and training are performed. Machine learning models at this stage include, but are not limited to, logistic regression, random forest, support vector machine, and gradient boosting tree. Model training then proceeds, including: Data partitioning: Dividing the dataset into training, validation, and test sets. Training process: Training the model using the training set, tuning hyperparameters using the validation set, and evaluating model performance using the test set. Loss function: Selecting an appropriate loss function, such as cross-entropy loss or mean squared error loss. Optimization algorithm: Using optimization algorithms such as gradient descent and Adam for model training. Finally, risk points and non-compliance items are identified. This includes: Rule matching: Defining a series of rules, such as keyword matching and pattern matching, for initial screening of potential risk points. Model prediction: Using the trained model to predict the application information, outputting a risk score and non-compliance items. Comprehensive judgment: Combining the rule matching and model prediction results, a comprehensive judgment is made on the risk points and non-compliance items in the application information.

[0061] Furthermore, the certification authority module verifies the certification certificate and PIN code by calling the big data index database. After successful verification, it sends a certification approval message to the applicant enterprise module. Specifically, this is used for:

[0062] The certification body module verifies the enterprise by calling the big data index database based on the certification certificate and the PIN code. Once the enterprise is verified, the product is verified. Once the product is verified, a ring mark certificate is generated and sent to the data collection, processing and database subsystem.

[0063] The data collection, processing, and database subsystem stores the environmental certification for future use.

[0064] Specifically, the product certification module serves as the primary channel for enterprises to apply for environmental labeling certificates. It allows for the immediate access to detailed information about the enterprise, and the uploaded documents also serve as an important part of the enterprise's archives. The system needs to implement formatted data import of required enterprise information and the collection of enterprise data from information systems containing relevant enterprise information. It also needs to complete interface calls to enterprise files and contact person files in the certification business system and reflect this in this project. A file management module for electronic attachments should also be implemented.

[0065] By applying the green procurement list management system provided in this embodiment of the invention, an index can be built based on big data, and tripartite connection between enterprises, certification and management agencies can be achieved, thereby improving procurement processing efficiency.

[0066] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0067] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0068] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A green procurement list management system, characterized in that, The system includes: The data acquisition, processing, and database subsystem is used to acquire data sources, including a first type of structured data source and a second type of unstructured data source; it processes the first type of structured data source and the second type of unstructured data source to build a big data index library; The green procurement list management subsystem includes modules for management organizations, certification bodies, and applicant companies. The application enterprise module is used to receive enterprise login information, which includes an authentication certificate and a PIN code, and then send the authentication certificate and PIN code to the authentication authority module. The certification authority module verifies the certification certificate and the PIN code by calling the big data index database. After successful verification, it sends a certification success message to the applicant enterprise module. After receiving the certification approval message, the application enterprise module receives enterprise information and product application information. The enterprise information includes basic enterprise information and sales contact information, and the application information includes product information and a commitment letter. The application enterprise module then sends the enterprise information and product application information to the management agency module. The management agency module is configured to: collect historical application information and corresponding review results to construct a training dataset; based on the training dataset, train a machine learning model to identify risk points and non-compliance items in the application information; use the trained machine learning model to perform predictive analysis on the currently received product application information, and intelligently determine risk points and non-compliance items by combining predefined rule matching; generate and display a list of public information based on the enterprise information and application information; and send the list of public information to the applicant enterprise module. The applicant enterprise module is used to receive the adjusted product information in response to the list disclosure information and send it to the management agency module; The management module is also used to review the adjusted product information and generate a formal green procurement list after the review is approved.

2. The system according to claim 1, characterized in that, The management module is also used to intelligently review the submitted information using machine learning and natural language processing technologies to identify risk points and non-compliance items.

3. The system according to claim 1, characterized in that, The certification authority module verifies the certification certificate and PIN code by calling the big data index database. After successful verification, it sends a certification approval message to the applicant enterprise module, specifically including: The certification body module verifies the enterprise by calling the big data index database based on the certification certificate and the PIN code. Once the enterprise is verified, the product is verified. Once the product is verified, a ring mark certificate is generated and sent to the data collection, processing and database subsystem. The data collection, processing, and database subsystem stores the environmental certification.

4. The system according to claim 1, characterized in that, The basic enterprise information includes the manufacturer's name, manufacturer's address, enterprise type, legal representative, organization code certificate, contact person's name, contact person's landline phone number, contact person's email address, and contact person's mobile phone number; the sales contact information includes the names and contact information of the sales contact person and their supervisor.

5. The system according to claim 1, characterized in that, The product information includes application guidelines, product editing, draft list, product list query, review status query, and historical product functions.

6. The system according to claim 1, characterized in that, Before receiving the application information, the application enterprise module also includes: When a product is selected to be added to the procurement list, declaration information is generated.

7. The system according to claim 6, characterized in that, The management module is also used to extract and save the commitment letter from the application information.

8. The system according to claim 1, characterized in that, The data acquisition, processing, and database subsystem is specifically used for: The second type of unstructured data source includes text files, image data, audio data, and video data; The text files, image data, audio data, and video data are cleaned and their formats converted. Extract keywords from text data; Feature extraction from image data using computer vision technology; Audio features are extracted from audio data using sound recognition technology; the audio features include pitch and frequency. Based on computer vision and sound recognition technologies, video data is processed to obtain time-series image data and audio features; Label keywords, image data features, and audio features, and add classification tags; The index structure is determined based on data characteristics and query requirements; the index structure includes inverted indexes, hash tables, and tree structures. An index is constructed based on the extracted features and the index structure.

9. The system according to claim 8, characterized in that, The data acquisition, processing, and database subsystem is also used to compress or partition the index in order to optimize it.

Images