Intelligent management system for fuel contract

Abstract

The invention provides an intelligent management system for a fuel contract, and belongs to the technical field of contract management, and the system comprises a first obtaining module which obtains all target fuel contract data, and carries out the preprocessing of the target fuel contract data; the analysis module is used for performing analysis according to a machine learning technology on the basis of the preprocessed target fuel contract data, and obtaining a plurality of key number words in the target fuel contract according to an analysis result; the second acquisition module is used for acquiring different feature information of the target fuel contract data according to the plurality of key number words; and the display module is used for performing batch management on the target fuel contract data according to the different feature information, and performing multi-angle display through a visualization technology. The problems that scientific management and control cannot be carried out on open contract settlement related supporting material delivery, the management and control risk and business disputes are increased, contract management is disordered, the searching time is long when needed related contracts are extracted, and the efficiency is low are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of contract management, and in particular to an intelligent management system for fuel contracts. Background Art

[0002] With the rapid development of my country's economy, energy demand has increased year by year. Fuel contracts are an important tool for energy transactions between enterprises, and their management efficiency is directly related to the economic interests of enterprises.

[0003] The existing contract management system is unable to scientifically manage and control the delivery of supporting materials related to the settlement of open contracts, which increases management risks and business disputes. At the same time, when various business links need document support, it is impossible to establish a reference relationship with the document in the delivery sharing center, and the management of contracts is relatively chaotic. When extracting the required related contracts, the search time is long, resulting in low efficiency.

[0004] Therefore, the present invention proposes an intelligent management system for fuel contracts. Summary of the invention

[0005] The present invention provides an intelligent management system for fuel contracts, which is used to solve the defects in the prior art that it is impossible to scientifically manage the delivery of supporting materials related to the settlement of open contracts, which increases the management risks and business disputes, and the management of contracts is relatively chaotic. When extracting the required related contracts, the search time is long, resulting in low efficiency.

[0006] In one aspect, the present invention provides an intelligent management system for fuel contracts, comprising: The first acquisition module: acquires all target fuel contract data and pre-processes the target fuel contract data; Analysis module: Analyze the pre-processed target fuel contract data using machine learning technology, and obtain multiple key words in the target fuel contract based on the analysis results; The second acquisition module: acquires different characteristic information of the target fuel contract data according to multiple key words; Display module: manage the target fuel contract data in batches according to the different characteristic information, and display it from multiple angles through visualization technology.

[0007] According to an intelligent management system for fuel contracts provided by the present invention, a first acquisition module includes: Determining unit: determining a database storing target fuel contract data, and determining IP address and port information according to the database; A first acquisition unit: acquiring corresponding access rights according to the IP address and port information; Retrieval unit: retrieves all target fuel contract data according to the SQL query statement based on the access permission.

[0008] An intelligent management system for fuel contracts provided by the present invention further includes: Import module: import all the target fuel contract data into the spreadsheet, remove duplicate and erroneous data according to the multiple functions of the spreadsheet, and ensure that all contracts have complete necessary information; Conversion module: convert the data after removing duplication and errors into a proper format, and convert the target fuel contract into a dictionary object according to the converted format; The third acquisition module: grouping and summarizing the converted target fuel contracts according to different standards; The fourth acquisition module: quickly search for the required target contract based on the summary results.

[0009] According to the present invention, an intelligent management system for fuel contracts, an analysis module, includes: The second acquisition unit is used to acquire the processing result corresponding to each contract based on the pre-processed target fuel contract data based on the natural language processing algorithm; Training unit: selecting a suitable machine learning algorithm to train the model according to the processing results; Among them, when training the model, hyperparameters are set for the model and cross-validation is used to evaluate the performance and generalization ability of the model; Extraction unit: performs word segmentation and stem extraction on the target fuel contract based on the set hyperparameters and evaluated model; The third acquisition unit is configured to acquire a plurality of key words in the target fuel contract based on the extraction result.

[0010] According to an intelligent management system for fuel contracts provided by the present invention, the second acquisition module includes: Input unit: input the multiple key words into the word frequency statistical model to obtain the frequency and weight of each key word in the contract; Arrangement unit: Arrange the key words in descending order of frequency according to the occurrence frequency and weight to form an ordered list, and obtain the first N keywords whose occurrence frequency is greater than a preset threshold; Generating unit: generating a document similarity matrix according to the first N keywords, analyzing the similarity matrix, and obtaining the correlation and difference between the keywords; The fourth acquisition unit is configured to acquire different characteristic information of the target fuel contract data according to the correlation and difference between the keywords.

[0011] An intelligent management system for fuel contracts provided by the present invention further includes: Management module: All target fuel contracts and supporting material documents are managed electronically through digital means; Storage module: Centrally store all files according to management results and link to corresponding files through unique file IDs; The first extraction module: extracts the data information of the corresponding file by means of file reference, and converts it into basic information of the business document to achieve the accuracy of the contract.

[0012] An intelligent management system for fuel contracts provided by the present invention further includes: Establishment module: Establish open contract management process and system, and formulate clear open contract templates and standardized open contract content according to the open contract management process and system; Evaluation and identification module: performing contract risk evaluation and identification on the open contract template and the open contract content; Signing module: online signing, approval and management based on the contract cat according to the recognition results; Review and update module: Regularly review and update open contracts based on management results to ensure real-time management of open contracts.

[0013] According to an intelligent management system for fuel contracts provided by the present invention, before evaluating the identification module, the system is also used to conduct a qualification review of the open contract, specifically: The second extraction module: extracts clause information from the open contract content, and determines the contract event relationship and contract event elements based on the clause information; The first determination module: determines the transaction attributes based on the contract event relationship and contract event elements; The first word segmentation processing module: performs the first transaction word segmentation processing on the open contract content based on the transaction attributes according to the pre-built word segmentation word library to obtain the first word segmentation result; Second word segmentation processing module: start a multi-thread task, use the multi-thread task to segment the open contract content, perform second transaction word segmentation processing on the segmented open contract content, and obtain the second word segmentation result; The first calculation module calculates the matching degree between the first word segmentation result and the second word segmentation result, and determines the transaction detail index of the open contract content according to the calculation result; The second determination module: determining the completeness qualification index of the open contract content according to the transaction detail index of the open contract content; The third determination module: obtains multiple constraint attribute tags in the open contract content and determines the associated content weight value of each constraint attribute tag; The fourth determination module: determines the sensitivity level of each constraint attribute label, and determines the proportion of sensitive content in the open contract content according to the sensitivity level; The fifth determination module: determining the legality and eligibility index of the open contract content according to the proportion of sensitive content; The sixth determination module: determining the overall eligibility index of the open contract content according to the legal eligibility index and the complete eligibility index of the open contract content; Judgment module: judge whether the overall eligibility index is greater than or equal to the preset index. If not, issue an open contract unqualified reminder; If so, determine the audit steps based on the content file attributes and determine the audit status factor of each step; The second calculation module: integrates and calculates the contents of open contracts according to the audit status factors to determine the negative feedback impact parameters; Seventh determination module: determining negative contract description state parameters in the open contract content according to negative feedback impact parameters; Screening module: Conduct characteristic item index screening on negative contract description status parameters to determine the eligibility of open contracts.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By preprocessing the target fuel contract to improve the quality, integrity and availability of the data, and obtaining multiple key words in the contract, different characteristic information of the contract data can be extracted and managed in batches, which reduces the management and control risks and improves the management efficiency of the contract. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a structural diagram of an intelligent management system for fuel contracts provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a first acquisition module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1: An intelligent management system for fuel contracts provided by an embodiment of the present invention is as follows: Figure 1 As shown, the system mainly includes the following modules: The first acquisition module: acquires all target fuel contract data and pre-processes the target fuel contract data; Analysis module: Analyze the pre-processed target fuel contract data using machine learning technology, and obtain multiple key words in the target fuel contract based on the analysis results; The second acquisition module: acquires different characteristic information of the target fuel contract data according to multiple key words; Display module: manage the target fuel contract data in batches according to the different characteristic information, and display it from multiple angles through visualization technology.

[0019] In this embodiment, the target fuel contract data may include: contract name, start and end dates, contract amount, payment method, supplier name, product / service description, unit price, quantity, and tax rate.

[0020] In this embodiment, preprocessing refers to a series of processing and conversion of raw data before data processing and analysis, such as data cleaning and data integration.

[0021] In this embodiment, machine learning refers to the ability of a computer system to autonomously "learn" how to perform specific tasks without being explicitly programmed.

[0022] In this embodiment, the multiple key numerals refer to key numbers and words in the contract, such as the total amount, installment amount, and installment period.

[0023] In this embodiment, different characteristic information of the fuel contract data includes: Contract type: Fuel contracts can be divided into different types, such as long-term contracts, short-term contracts, spot contracts, etc., according to the content and purpose of the contract.

[0024] Transaction frequency: How often fuel transactions are recorded, such as weekly, monthly or quarterly.

[0025] Transaction volume: Record the quantity of each fuel transaction, average consumption speed, minimum order quantity, etc.

[0026] Supplier: The name and contact details of the supplier providing the service for each fuel contract.

[0027] Price information: Collect detailed information on fuel prices, such as ex-factory price, freight, discounts, etc.

[0028] In this embodiment, batch management is to divide the contracts into multiple batches according to feature information for management, and the contracts in each batch have the same features.

[0029] In this embodiment, visualization technology refers to technology that can transform abstract information, concepts, processes, etc. into specific visual expressions such as images, models, or videos.

[0030] In this embodiment, multi-angle display refers to displaying the contract by using multiple viewing angles and methods, such as bar charts, videos, and animations.

[0031] The beneficial effects of the above technical solution are: by preprocessing the target fuel contract to improve the quality, integrity and availability of the data, and obtaining multiple key words in the contract, so as to extract different characteristic information of the contract data and manage them in batches, it reduces the management and control risks and improves the management efficiency of the contract.

[0032] Embodiment 2: Based on Example 1, the first acquisition module of the embodiment of the present invention is as follows: Figure 2 As shown, including: Determining unit: determining a database storing target fuel contract data, and determining IP address and port information according to the database; A first acquisition unit: acquiring corresponding access rights according to the IP address and port information; Retrieval unit: retrieves all target fuel contract data according to the SQL query statement based on the access permission.

[0033] In this embodiment, an IP address is a numeric identifier that uniquely identifies the location of a device on the Internet.

[0034] In this embodiment, a port is a network interface used to distinguish different application processes in a computer network. Each open application has a unique port number associated with it. The port number can be any number ranging from 0 to 65535.

[0035] In this embodiment, access rights refer to the conditions that need to be met when operating a resource or system, which involve who can access the resource, when the resource can be accessed, and how the resource can be accessed.

[0036] In this embodiment, SQL query statements are a programming method for querying a database, and data can be obtained, added, modified or deleted from the database through these statements.

[0037] The beneficial effects of the above technical solution are: by determining the IP address and port information through the fuel contract database, thereby obtaining the corresponding access rights, protecting the security of the data and preventing unauthorized operations, and retrieving all target fuel contract data based on SQL query statements. The query results can be optimized without changing the basic query logic to improve query efficiency.

[0038] Embodiment 3: Based on Example 2, the embodiment of the present invention further includes: Import module: import all the target fuel contract data into the spreadsheet, remove duplicate and erroneous data according to the multiple functions of the spreadsheet, and ensure that all contracts have complete necessary information; Conversion module: convert the data after removing duplication and errors into a proper format, and convert the target fuel contract into a dictionary object according to the converted format; The third acquisition module: grouping and summarizing the converted target fuel contracts according to different standards; The fourth acquisition module: quickly search for the required target contract based on the summary results.

[0039] In this embodiment, the multiple functions may be filter, sort and merge units.

[0040] In this embodiment, the dictionary object is a data structure that stores data in the form of key-value pairs. Each key of the dictionary object is unique and can use any type of value as the corresponding value. The key is the column name and the value is the actual value of the column.

[0041] In this embodiment, the overall trend of the data mainly refers to the data distribution and variation patterns found in the data analysis process, which may be: numerical distribution, time series analysis, and spatial distribution.

[0042] The beneficial effect of the above technical solution is: by removing duplicate and erroneous data from the fuel contract data and converting it into an appropriate format, the target fuel contract is converted into a dictionary object according to the converted format, and the data can be quickly accessed and modified according to specific keys, thereby improving the efficiency of data preprocessing.

[0043] Embodiment 4: Based on Example 3, the analysis module of the embodiment of the present invention includes: The second acquisition unit is used to acquire the processing result corresponding to each contract based on the pre-processed target fuel contract data based on the natural language processing algorithm; Training unit: selecting a suitable machine learning algorithm to train the model according to the processing results; Among them, when training the model, hyperparameters are set for the model and cross-validation is used to evaluate the performance and generalization ability of the model; Extraction unit: performs word segmentation and stem extraction on the target fuel contract based on the set hyperparameters and evaluated model; The third acquisition unit is configured to acquire a plurality of key words in the target fuel contract based on the extraction result.

[0044] In this embodiment, natural language processing refers to the ability of a computer to understand, interpret and generate human natural language.

[0045] In this embodiment, the machine learning algorithm can be a naive Bayes classifier, a support vector machine, a random forest, or a neural network.

[0046] In this embodiment, the hyperparameters may be the maximum word frequency and the minimum occurrence frequency.

[0047] In this embodiment, cross validation is a method for evaluating model performance by dividing the dataset into multiple parts and training the model iteratively to evaluate the generalization ability of the model.

[0048] In this embodiment, word segmentation refers to the process of dividing a continuous Chinese text into individual words or clauses to facilitate subsequent natural language processing tasks, such as part-of-speech tagging, named entity recognition, and dependency parsing.

[0049] In this embodiment, stem extraction refers to extracting the most representative and important words or phrases from an article or a text.

[0050] The beneficial effects of the above technical solution are: by performing natural language processing on the pre-processed fuel contract data, selecting a suitable machine learning algorithm to train the model, and performing word segmentation and stem extraction on the contract according to the trained model, a clearer and easier-to-process text representation can be obtained, thereby improving the performance of natural language processing, facilitating the subsequent acquisition of key words in the contract, and improving management efficiency.

[0051] Embodiment 5: Based on Example 4, the second acquisition module of this embodiment of the present invention includes: Input unit: input the multiple key words into the word frequency statistical model to obtain the frequency and weight of each key word in the contract; Arrangement unit: Arrange the key words in descending order of frequency according to the occurrence frequency and weight to form an ordered list, and obtain the first N keywords whose occurrence frequency is greater than a preset threshold; Generating unit: generating a document similarity matrix according to the first N keywords, analyzing the similarity matrix, and obtaining the correlation and difference between the keywords; The fourth acquisition unit is configured to acquire different characteristic information of the target fuel contract data according to the correlation and difference between the keywords.

[0052] In this embodiment, the word frequency statistical model is a mathematical model used to calculate the frequency of occurrence of words in a text.

[0053] In this embodiment, frequency refers to the number of times each word appears.

[0054] In this embodiment, the weight refers to a numerical value, which measures the importance of a certain numeral.

[0055] In this embodiment, frequency descending order refers to a method of sorting a group of words from high to low according to word frequency. Word frequency refers to the number of times a group of words appear in a text. In the frequency descending order, the words are arranged in order from most to least according to the number of times they appear, and the words with more appearances are arranged in front.

[0056] In this embodiment, the ordered list is a list format for displaying data, in which each item is arranged in a certain order.

[0057] In this embodiment, the preset threshold may be 30.

[0058] In this embodiment, the document similarity matrix is ​​a mathematical tool for measuring the similarity between documents. The document similarity matrix consists of rows and columns, where each row represents a document, and each column represents a feature or a word. Each cell in the matrix represents the occurrence of the feature or word in the document. If a feature or word appears in a document, a "1" is marked in the corresponding cell, otherwise a "0" is marked. The final matrix can calculate the similarity between each document and other documents and sort them.

[0059] The beneficial effects of the above technical solution are: obtaining the frequency and weight of each key word, and arranging them in descending order of frequency to form an ordered list, obtaining the top N keywords with an appearance frequency greater than a preset threshold, generating a similarity matrix, obtaining the correlation and difference between key words, and improving the accuracy and reliability of retrieving key contract information.

[0060] Embodiment 6: Based on Example 5, the embodiment of the present invention further includes: Management module: All target fuel contracts and supporting material documents are managed electronically through digital means; Storage module: Centrally store all files according to management results and link to corresponding files through unique file IDs; The first extraction module: extracts the data information of the corresponding file by means of file reference, and converts it into basic information of the business document to achieve the accuracy of the contract.

[0061] In this embodiment, digitization refers to the process of converting various information, data, audio, video, etc. from analog form to digital form.

[0062] In this embodiment, supporting material files refer to files used to support a project or business. These files record information such as the progress, implementation process, and results of the project, for example: Business operation documents: such as customer files, order records, inventory reports, sales reports, etc., used to record and manage the daily business operations of the enterprise.

[0063] Technical R&D documents: such as product design drawings, program codes, experimental reports, test reports, etc., used to record and manage technical R&D work.

[0064] Administrative documents: such as meeting minutes, notices, requests for instructions, report summaries, etc., are used to record and manage the work of internal organizations or departments.

[0065] Legal and regulatory documents: such as contract agreements, policies and regulations, standards and specifications, etc.

[0066] In this embodiment, electronic management refers to the process of comprehensive information collection, storage, transmission, sharing, application, service and management of various physical and non-physical objects through computer technology and network communication technology.

[0067] In this embodiment, the unique file ID is a unique identifier used to identify a specific file, which can ensure that each file has a unique identity, such as: A12345-67890, "A" is a prefix used to distinguish different types of files, and the following numbers and symbols represent the specific information of the file.

[0068] In this embodiment, the file reference refers to a string or code snippet used when a file is mentioned in a document or contract.

[0069] In this embodiment, the basic information of the business document includes: document number, applicant / purchaser, product / service name, purchase date, price / cost.

[0070] The beneficial effects of the above technical solution are: electronic management of contracts and supporting materials through digital means can improve work efficiency, reduce costs, and protect data security. At the same time, all files are centrally stored and linked to the corresponding files through unique file IDs, which can easily track and manage all files and ensure data consistency and integrity. Furthermore, by extracting information from the contract through file references, the content in a specific file can be quickly located and accessed, improving search efficiency.

[0071] Embodiment 7: Based on Example 6, the embodiment of the present invention further includes: Establishment module: Establish open contract management process and system, and formulate clear open contract templates and standardized open contract content according to the open contract management process and system; Evaluation and identification module: performing contract risk evaluation and identification on the open contract template and the open contract content; Signing module: online signing, approval and management based on the contract cat according to the recognition results; Review and update module: Regularly review and update open contracts based on management results to ensure real-time management of open contracts.

[0072] In this embodiment, an open contract means that when the contract is signed, the content of the contract is not completely determined and needs to be adjusted or modified according to actual conditions.

[0073] In this embodiment, the open contract management process and system include: clarifying the responsibilities of relevant departments and personnel, establishing and improving contract management system documents, improving the contract review mechanism, and optimizing the contract execution tracking system.

[0074] In this embodiment, Contract Cat is an online contract management tool for enterprises, which aims to help enterprises process and sign contracts more efficiently and reduce the cost and risk of contract management.

[0075] The beneficial effects of the above technical solution are: by clarifying the open contract template and the open contract content through the open contract management system and process, and conducting risk assessment on the goals and content, potential problems can be discovered and corrected in time, which can improve the quality and security of the contract. Furthermore, online signing and approval can be carried out through Contract Cat, and updates and reviews can be implemented, making the signing and management of contracts more convenient, compliant and real-time, while avoiding unnecessary business disputes.

[0076] Embodiment 8: Based on Example 7, before the evaluation and identification module of the embodiment of the present invention, the system is also used to perform a qualification review on the open contract, specifically: The second extraction module: extracts clause information from the open contract content, and determines the contract event relationship and contract event elements based on the clause information; The first determination module: determines the transaction attributes based on the contract event relationship and contract event elements; The first word segmentation processing module: performs the first transaction word segmentation processing on the open contract content based on the transaction attributes according to the pre-built word segmentation word library to obtain the first word segmentation result; Second word segmentation processing module: start a multi-thread task, use the multi-thread task to segment the open contract content, perform second transaction word segmentation processing on the segmented open contract content, and obtain the second word segmentation result; The first calculation module calculates the matching degree between the first word segmentation result and the second word segmentation result, and determines the transaction detail index of the open contract content according to the calculation result; The second determination module: determining the completeness qualification index of the open contract content according to the transaction detail index of the open contract content; The third determination module: obtains multiple constraint attribute tags in the open contract content and determines the associated content weight value of each constraint attribute tag; The fourth determination module: determines the sensitivity level of each constraint attribute label, and determines the proportion of sensitive content in the open contract content according to the sensitivity level; The fifth determination module: determining the legality and eligibility index of the open contract content according to the proportion of sensitive content; The sixth determination module: determining the overall eligibility index of the open contract content according to the legal eligibility index and the complete eligibility index of the open contract content; Judgment module: judge whether the overall eligibility index is greater than or equal to the preset index. If not, issue an open contract unqualified reminder; If so, determine the audit steps based on the content file attributes and determine the audit status factor for each step; The second calculation module: integrates and calculates the contents of open contracts according to the audit status factors to determine the negative feedback impact parameters; Seventh determination module: determining negative contract description state parameters in the open contract content according to negative feedback impact parameters; Screening module: Conduct characteristic item index screening on negative contract description status parameters to determine the eligibility of open contracts.

[0077] In this embodiment, the contract terms information is an important component of the contract, including rights and obligations clauses, performance period clauses, breach of contract liability clauses, confidentiality clauses, dispute resolution clauses, etc.

[0078] In this embodiment, the contract event relationship refers to the rights and obligations relationship between the parties to the contract arising from the performance, modification, cancellation, and termination of the contract, which involves the rights and obligations of the parties to the contract during the execution of the contract and the actual situation of the contract performance. For example, in a fuel sales contract, the buyer is obliged to pay the purchase price and the seller is obliged to deliver the goods.

[0079] In this embodiment, the contract event elements include: Contract parties: refers to the parties involved in the contract, such as the buyer, seller, lessee, etc.; Subject matter of the contract: refers to the specific goods or services involved in the contract, such as fuel; Contract Price: refers to the transaction price stipulated in the contract, i.e. the price that the buyer needs to pay; Payment method: refers to the payment method and time agreed in the contract, such as one-time payment, installment payment, mortgage payment, etc.; Delivery deadline: refers to the delivery time and place stipulated in the contract, such as date, place, time, etc.

[0080] In this embodiment, the transaction attribute refers to the basic characteristics or properties of the transaction, such as: tangible commodity transaction, intangible commodity transaction, financial transaction, trade transaction.

[0081] In this embodiment, the word segmentation word library is used to segment a text into multiple independent words or phrases.

[0082] In this embodiment, transaction word segmentation processing refers to the process of identifying and processing transaction events in transaction data, and screening out transaction-related words, such as amount and payment method.

[0083] In this embodiment, multi-threaded task segmentation of the open contract content refers to dividing the contract into several parts, such as terms and conditions, payment methods and timetable, and then handing them over to different team members for processing.

[0084] In this embodiment, the transaction detail index refers to the detailed information of each transaction.

[0085] In this embodiment, the completeness qualification index of the open contract content is an evaluation method used to measure whether the content of a contract is complete and meets the specified standards. The completeness qualification index is usually calculated by a scoring system, which scores the contract terms according to their importance and necessity, and scores each clause according to specific rules or standards. This scoring system may involve a series of different levels of scoring, such as A, B, C, etc., where A means full compliance with the requirements and C means non-compliance with the requirements.

[0086] In this embodiment, the constraint attribute tags are programming language keywords or tags used to define and restrict the contract content. For example, if these tags are data types (such as numbers, texts, etc.), it is necessary to ensure that their data types and formats are correct. If these tags are non-data types (such as dates or times), it is necessary to ensure that their values ​​are valid.

[0087] In this embodiment, the associated content weight value refers to the importance of the content corresponding to the tag, such as the importance of transaction time in a contract.

[0088] In this embodiment, the sensitivity level refers to the degree of protection of certain specific information in the contract.

[0089] In this embodiment, the sensitive content ratio refers to the ratio of the sensitive content in the contract to the entire contract, for example, sensitive content: full text content = 1:3.

[0090] In this embodiment, the legality index is an indicator for measuring the legality of the contract content, and is used to evaluate whether the content and form of the contract comply with relevant laws, regulations and public policies. The value range of this index is usually between 0 and 100, where 0 indicates complete non-compliance with legal provisions and 100 indicates complete compliance with legal provisions.

[0091] In this embodiment, the preset index is 85.

[0092] In this embodiment, the audit status factor is a key performance indicator for measuring the contract audit process, including: audit progress, audit quality, and audit system performance.

[0093] In this embodiment, negative feedback impact parameters may include grammatical errors, spelling errors, logical errors or data inconsistencies. In this embodiment, the negative contract description status parameters of the contract content may be: illegal, invalid, conflicting, unclear, beyond the scope of authorization, and controversial.

[0094] In this embodiment, characteristic item index screening is a method of evaluating contract quality, which involves measuring and analyzing various characteristics of the contract to determine whether they meet the expected standards and specifications.

[0095] The beneficial effect of the above technical solution is: by checking the characteristic item indicators of the negative contract description status parameters to determine the eligibility of the open contract, the eligibility and legality of the open contract can be guaranteed. At the same time, problems in the contract can be discovered and adjusted in time to avoid business disputes.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent management system for fuel contracts, characterized in that: include: The first acquisition module: acquires all target fuel contract data and pre-processes the target fuel contract data; Analysis module: Analyze the pre-processed target fuel contract data using machine learning technology, and obtain multiple key words in the target fuel contract based on the analysis results; The second acquisition module: acquires different characteristic information of the target fuel contract data according to multiple key words; Display module: manage the target fuel contract data in batches according to the different characteristic information, and display it from multiple angles through visualization technology.

2. The intelligent management system for fuel contracts according to claim 1 is characterized in that: The first acquisition module includes: Determining unit: determining a database storing target fuel contract data, and determining IP address and port information according to the database; A first acquisition unit: acquiring corresponding access rights according to the IP address and port information; Retrieval unit: retrieves all target fuel contract data according to the SQL query statement based on the access permission.

3. The intelligent management system for fuel contracts according to claim 1 is characterized in that: Also includes: Import module: import all the target fuel contract data into the spreadsheet, remove duplicate and erroneous data according to the multiple functions of the spreadsheet, and ensure that all contracts have complete necessary information; Conversion module: convert the data after removing duplication and errors into a proper format, and convert the target fuel contract into a dictionary object according to the converted format; The third acquisition module: grouping and summarizing the converted target fuel contracts according to different standards; The fourth acquisition module: quickly search for the required target contract based on the summary results.

4. The intelligent management system for fuel contracts according to claim 1 is characterized in that: Analysis modules, including: The second acquisition unit is used to acquire the processing result corresponding to each contract based on the pre-processed target fuel contract data based on the natural language processing algorithm; Training unit: selecting a suitable machine learning algorithm to train the model according to the processing results; Among them, when training the model, hyperparameters are set for the model and cross-validation is used to evaluate the performance and generalization ability of the model; Extraction unit: performs word segmentation and stem extraction on the target fuel contract based on the set hyperparameters and evaluated model; The third acquisition unit is configured to acquire a plurality of key words in the target fuel contract based on the extraction result.

5. The intelligent management system for fuel contracts according to claim 1 is characterized in that: The second acquisition module includes: Input unit: input the multiple key words into the word frequency statistical model to obtain the frequency and weight of each key word in the contract; Arrangement unit: Arrange the key words in descending order of frequency according to the occurrence frequency and weight to form an ordered list, and obtain the first N keywords whose occurrence frequency is greater than a preset threshold; Generating unit: generating a document similarity matrix according to the first N keywords, analyzing the similarity matrix, and obtaining the correlation and difference between the keywords; The fourth acquisition unit is configured to acquire different characteristic information of the target fuel contract data according to the correlation and difference between the keywords.

6. The intelligent management system for fuel contracts according to claim 1, characterized in that: Also includes: Management module: All target fuel contracts and supporting material documents are managed electronically through digital means; Storage module: Centrally store all files according to management results and link to corresponding files through unique file IDs; The first extraction module: extracts the data information of the corresponding file by means of file reference, and converts it into basic information of the business document to achieve the accuracy of the contract.

7. The intelligent management system for fuel contracts according to claim 1, characterized in that: Also includes: Establishment module: Establish open contract management process and system, and formulate clear open contract templates and standardized open contract content according to the open contract management process and system; Evaluation and identification module: performing contract risk evaluation and identification on the open contract template and the open contract content; Signing module: online signing, approval and management based on the contract cat according to the recognition results; Review and update module: Regularly review and update open contracts based on management results to ensure real-time management of open contracts.

8. The intelligent management system for fuel contracts according to claim 7 is characterized in that: Prior to evaluating the identification module, the system is also used to conduct a qualification review of the open contracts, specifically: The second extraction module: extracts clause information from the open contract content, and determines the contract event relationship and contract event elements based on the clause information; The first determination module: determines the transaction attributes based on the contract event relationship and contract event elements; The first word segmentation processing module: performs the first transaction word segmentation processing on the open contract content based on the transaction attributes according to the pre-built word segmentation word library to obtain the first word segmentation result; Second word segmentation processing module: start a multi-thread task, use the multi-thread task to segment the open contract content, perform second transaction word segmentation processing on the segmented open contract content, and obtain the second word segmentation result; The first calculation module calculates the matching degree between the first word segmentation result and the second word segmentation result, and determines the transaction detail index of the open contract content according to the calculation result; The second determination module: determining the completeness qualification index of the open contract content according to the transaction detail index of the open contract content; The third determination module: obtains multiple constraint attribute tags in the open contract content and determines the associated content weight value of each constraint attribute tag; The fourth determination module: determines the sensitivity level of each constraint attribute label, and determines the proportion of sensitive content in the open contract content according to the sensitivity level; The fifth determination module: determining the legality and eligibility index of the open contract content according to the proportion of sensitive content; The sixth determination module: determining the overall eligibility index of the open contract content according to the legal eligibility index and the complete eligibility index of the open contract content; Judgment module: judge whether the overall eligibility index is greater than or equal to the preset index. If not, issue an open contract unqualified reminder; If so, determine the audit steps based on the content file attributes and determine the audit status factor of each step; The second calculation module: integrates and calculates the contents of open contracts according to the audit status factors to determine the negative feedback impact parameters; Seventh determination module: determining negative contract description state parameters in the open contract content according to negative feedback impact parameters; Screening module: Conduct characteristic item index screening on negative contract description status parameters to determine the eligibility of open contracts.

Images