College purchased commodity classification system and method

Abstract

The invention provides a university purchase commodity classification system and method, and the system comprises a data collection module which is used for collecting commodity data involved in university commodity purchase business; the feature extraction module is used for extracting feature data related to financial fund project management and fixed asset input requirements according to the collected commodity data; the commodity classification module is used for classifying the commodities according to the extracted feature data by adopting a machine learning or deep learning algorithm to obtain a classification result of the commodities; and the comparison generation module is used for comparing the feature data of different commodities and optimizing the classification result of the commodities according to the comparison result. According to the invention, specific requirements of financial fund project management and fixed asset entry are combined with commodity classification, and commodity classification is carried out automatically, so that the efficiency and accuracy of commodity classification are improved; dynamic adjustment and optimization of commodity classification are realized through a data comparison generation algorithm, and the accuracy of commodity classification is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of commodity classification, and in particular to a commodity classification system and method for university procurement. Background Art

[0002] In the existing technology, the commodity classification of university procurement business mainly relies on manual operation, lacking automated and intelligent processing methods, which leads to low classification efficiency and easy errors. Summary of the invention

[0003] The present invention provides a system and method for classifying commodities purchased by universities, which are used to solve the defects of low efficiency and easy error in manual classification of commodities in the prior art, and improve the accuracy and efficiency of commodity classification through automatic data processing and intelligent classification algorithm.

[0004] The present invention provides a commodity classification system for university purchases, comprising:

[0005] The data collection module is used to collect commodity data involved in the commodity procurement business of colleges and universities;

[0006] A feature extraction module, for extracting feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data;

[0007] A commodity classification module, used to classify the commodities according to the extracted feature data using a machine learning or deep learning algorithm to obtain a classification result of the commodities;

[0008] The comparison generation module is used to compare the feature data of different commodities and optimize the classification results of the commodities according to the comparison results.

[0009] According to a commodity classification system for university purchases provided by the present invention, the commodity data includes one or more of commodity name, specification model, price, quantity, purpose and expiration date.

[0010] According to a commodity classification system for university purchases provided by the present invention, the characteristic data includes one or more of financial expenditure subjects, project types, budget types and asset attributes.

[0011] According to a commodity classification system for purchasing in colleges and universities provided by the present invention, the financial classification is divided according to the source of funds, the purpose of funds and the nature of funds of the project fund card. The financial classification is divided into budgetary funds and extra-budgetary funds according to the source of funds, divided into teaching funds, scientific research funds, administrative funds and logistics funds according to the purpose of funds, and divided into business funds and special funds according to the nature of funds.

[0012] According to a commodity classification system for university purchases provided by the present invention, the data collection module is also used to collect detailed data of the project fund card, and the detailed data includes the types of commodities purchased by the project fund card and the remaining amount of the project fund card;

[0013] The feature extraction module is used to:

[0014] Analyze the commodity data of the commodity to determine the analysis result of the commodity data, wherein the analysis result includes one or more of commodity attributes, price trend, purchase frequency, fund usage, and whether the commodity is a fixed asset;

[0015] According to the analysis result, determining the association relationship between the commodity data and the project expense card and fixed assets;

[0016] Based on the association relationship and the collected commodity data, feature data related to financial expense project management and fixed asset entry requirements are extracted.

[0017] According to a university purchase commodity classification system provided by the present invention, the characteristic data includes user behavior data and commodity attribute data of purchasing commodities, and the comparison generation module is specifically used for:

[0018] Using collaborative filtering algorithms, the classification results of the commodities are re-determined based on the user behavior data of the commodities purchased and the commodity attribute data;

[0019] In the case that the two classification results of the commodity are inconsistent, the latter classification result of the commodity is used as the final classification result of the commodity, or the two classification results are displayed for the user to select.

[0020] A commodity classification system for university purchases provided by the present invention further includes a user interaction interface for:

[0021] According to the query conditions input by the user, the classification results of the commodities corresponding to the query conditions are displayed;

[0022] The classification result of the commodity is updated using the classification result input by the user.

[0023] The present invention also provides a method for classifying commodities purchased by a university, comprising:

[0024] Collect commodity data involved in the commodity procurement business of colleges and universities through the data collection module;

[0025] Extracting feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data through a feature extraction module;

[0026] Using a machine learning or deep learning algorithm to classify the commodities according to the extracted feature data through a commodity classification module, so as to obtain a classification result of the commodities;

[0027] The feature data of different commodities are compared through the comparison generation module, and the classification results of the commodities are optimized according to the comparison results.

[0028] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for classifying commodities purchased by universities.

[0029] The university procurement commodity classification system and method provided by the present invention automatically classifies commodities by combining the specific requirements of financial expense project management and fixed asset entry with commodity classification, thereby improving the efficiency and accuracy of commodity classification; dynamically adjusts and optimizes commodity classification by generating an algorithm through data comparison, further improving the accuracy of commodity classification, and adapting to different project management needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] 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.

[0031] Figure 1 It is a structural diagram of the commodity classification system for university purchases provided by the present invention;

[0032] Figure 2 It is a schematic diagram of project fund card classification in the commodity procurement classification system for universities provided by the present invention;

[0033] Figure 3 It is a flow chart of the commodity classification method for university purchases provided by the present invention. DETAILED DESCRIPTION

[0034] 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.

[0035] Combine the following Figure 1 The present invention describes a commodity classification system for university purchases, comprising:

[0036] The data collection module 101 is used to collect commodity data involved in the commodity procurement business of the university;

[0037] The feature extraction module 102 is used to extract feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data;

[0038] The commodity classification module 103 is used to classify the commodities according to the extracted feature data using a machine learning or deep learning algorithm to obtain a classification result of the commodities;

[0039] The comparison generation module 104 is used to compare the feature data of different commodities and optimize the classification results of the commodities according to the comparison results.

[0040] The university procurement commodity classification system provided in this embodiment is mainly used for university procurement and procurement of university affiliated hospitals.

[0041] First, the data collection module 101 collects commodity data involved in the university's procurement business, including information such as price, purpose, and expiration date. These data will serve as the basis for algorithm processing.

[0042] Next, the feature extraction module 102 extracts feature data related to financial expense project management and fixed asset entry requirements based on the collected data. These feature data may include financial classification, budget coding, asset attributes, etc. of the commodity.

[0043] The commodity classification module 103 uses machine learning or deep learning technology, such as support vector machine (SVM), neural network or decision tree, to classify commodities according to the extracted features.

[0044] The random forest algorithm can be used to build a classification model, select appropriate feature variables, and interpret the model's results. This approach is particularly useful in accounting classification problems, such as classification problems in financial statements.

[0045] Commodities can be classified into multiple levels. For example, the first-level classification includes office supplies, books, cleaning supplies, industrial supplies, fitness and sports, and scientific research instruments. The second-level classification for office supplies includes writing tools, file management and storage, office paper and consumables, and auxiliary supplies. The third-level classification for writing artifacts includes pencils, ballpoint pens, gel pens, and fountain pens.

[0046] The comparison generation module 104 automatically generates classification results by comparing the feature data of different commodities, and optimizes and adjusts the classification results. This step can adopt a collaborative filtering algorithm to recommend similar commodities or categories by analyzing user behavior and commodity attributes.

[0047] In actual operation, multi-threading can be used to asynchronously process data from different users to improve the efficiency and response speed of the algorithm.

[0048] The classification algorithm can be integrated into the financial management system of colleges and universities to realize automatic commodity classification and management. This can be achieved by connecting with existing financial software and database systems to realize the automatic flow and update of data.

[0049] Through the above technologies and methods, the commodity classification problems required by different financial projects can be effectively handled, and the automation and intelligence level of university procurement business can be improved.

[0050] This embodiment automatically classifies goods by combining the specific requirements of financial expense project management and fixed asset entry with commodity classification, thereby improving the efficiency and accuracy of commodity classification; it realizes dynamic adjustment and optimization of commodity classification by generating an algorithm through data comparison, further improving the accuracy of commodity classification and adapting to different project management needs.

[0051] On the basis of the above embodiment, the commodity data in this embodiment includes one or more of commodity name, specification model, price, quantity, purpose and expiration date.

[0052] Based on the above embodiment, the characteristic data in this embodiment includes one or more of financial expenditure items, project types, budget types and asset attributes.

[0053] Based on the above embodiments, Figure 2 As shown, the financial classification in this embodiment is divided according to the funding source, funding purpose and funding nature of the project funding card. The financial classification is divided into budgetary funds and extra-budgetary funds according to the funding source, divided into teaching funds, scientific research funds, administrative funds and logistics funds according to the funding purpose, and divided into business funds and special funds according to the funding nature.

[0054] On the basis of the above embodiment, the data collection module in this embodiment is also used to collect detailed data of the project fund card, and the detailed data includes the types of goods purchased by the project fund card and the remaining amount of the project fund card;

[0055] The feature extraction module is used to:

[0056] Analyze the commodity data of the commodity to determine the analysis result of the commodity data, wherein the analysis result includes one or more of commodity attributes, price trend, purchase frequency, fund usage, and whether the commodity is a fixed asset;

[0057] According to the analysis result, determining the association relationship between the commodity data and the project expense card and fixed assets;

[0058] Based on the association relationship and the collected commodity data, feature data related to financial expense project management and fixed asset entry requirements are extracted.

[0059] The data collection module is responsible for collecting basic information about commodities purchased by colleges and universities, including commodity name, specification, purpose, price, etc., as well as detailed information on project funding cards, including the categories of commodities that can be purchased and the remaining amount.

[0060] The data analysis module conducts in-depth analysis of the collected data, including commodity attribute analysis, price trend analysis, purchase frequency analysis, fund use analysis, and fixed asset analysis. Fixed asset analysis uses information such as commodity classification and amount to confirm that the commodity is a fixed asset based on the fixed asset identification conditions provided by the university. If it is a fixed asset, fixed asset files need to be created.

[0061] Through data analysis, the correlation between commodity information and funds (detailed information on the target fund card) and assets (fixed asset information) is revealed, providing a scientific basis for the construction of classification models and fund and asset management.

[0062] Based on the correlation between the pre-acquired commodity information and funds (detailed information on the project fund card) and assets (fixed asset information), characteristic data related to the financial fund project management and fixed asset entry requirements corresponding to the collected commodity data are obtained.

[0063] Based on the extracted feature data, a scientific commodity classification model is constructed. The model uses advanced machine learning algorithms to comprehensively consider the attributes, prices, uses and other characteristics of commodities, and automatically classifies commodities into different categories. At the same time, the model also has adaptive learning capabilities, and can continuously optimize the classification effect according to new procurement data and funding and asset management needs.

[0064] It can also include a funding management module, which is combined with project funding card management to achieve full-process management such as funding matching, real-time freezing / unfreezing, approval, and settlement. The system can automatically match purchased goods with project funding cards to ensure the compliance and transparency of funding use. At the same time, the module also provides funding budgeting, execution monitoring, early warning and other functions to help colleges and universities effectively manage project funds.

[0065] It can also include a fixed asset authentication module, which can be connected to the fixed asset management system to realize the fixed asset authentication of purchased goods. The system can automatically identify whether the purchased goods belong to the category of fixed assets, and automatically include them in the fixed asset management system for fixed asset filing and other management.

[0066] It can also include a system integration module to integrate the above modules to form a complete scientific classification system for digital intelligent procurement of colleges and universities. The system integration module is responsible for data interaction and collaborative work between modules to ensure the stability and reliability of the system.

[0067] On the basis of the above embodiment, the characteristic data in this embodiment includes user behavior data and commodity attribute data of purchasing commodities, and the comparison generation module is specifically used for:

[0068] Using collaborative filtering algorithms, the classification results of the commodities are re-determined based on the user behavior data of the commodities purchased and the commodity attribute data;

[0069] In the case that the two classification results of the commodity are inconsistent, the latter classification result of the commodity is used as the final classification result of the commodity, or the two classification results are displayed for the user to select.

[0070] Based on the above embodiments, this embodiment also includes a user interaction interface for:

[0071] According to the query conditions input by the user, the classification results of the commodities corresponding to the query conditions are displayed;

[0072] The classification result of the commodity is updated using the classification result input by the user.

[0073] This embodiment provides a user interface, allowing the user to input query conditions, view classification results, and perform necessary manual intervention and adjustments, which helps to improve the accuracy of classification and adapt to different project management requirements.

[0074] Regularly evaluate and update classification algorithms to adapt to changes in financial project requirements. This may include updating feature extraction rules, adjusting classification model parameters, or introducing new algorithmic techniques. The following methods are used when evaluating algorithm accuracy and efficiency in financial classification tasks:

[0075] 1. Confusion Matrix:

[0076] The confusion matrix is ​​an important tool that shows the relationship between the actual classification results and the predicted classification results. Through the confusion matrix, you can calculate indicators such as precision, recall, and F1 score.

[0077] 2. Accuracy:

[0078] The accuracy rate is the ratio of correctly classified samples to the total number of samples, which can clearly judge the performance of the model. However, it should be noted that when the positive and negative samples are unbalanced, the accuracy rate may not reflect the overall situation of the model well.

[0079] 3. Precision:

[0080] Precision refers to the ratio of the number of correctly classified positive samples to the number of samples determined as positive samples by the classifier. It reflects the model's ability to distinguish negative samples. The higher the precision, the stronger the model's ability to distinguish negative samples.

[0081] 4. Recall:

[0082] Recall rate refers to the ratio of the number of correctly classified positive samples to the number of true positive samples. It reflects the model's ability to identify positive samples.

[0083] 5. F1 Score:

[0084] F1 Score is the harmonic mean of precision and recall, which is used to deal with the problem of imbalanced categories. It is an indicator that comprehensively considers precision and recall.

[0085] 6. ROC (Receiver Operating Characteristic curve) curve and AUC (Area Under the Curve) score:

[0086] The ROC curve is a curve that plots the true positive rate (TPR) and false positive rate (FPR) at different thresholds. AUC is the area under the ROC curve, which is used to quantify the classification ability of the model. The larger the AUC value, the better the classification performance of the model.

[0087] 7. Stability analysis:

[0088] Evaluate the robustness of the algorithm when facing different types of data or abnormal situations, that is, whether the algorithm can stably output correct results.

[0089] 8. Comparison with the optimal solution:

[0090] For some problems, the performance of optimal solutions or near-optimal solutions is known, and the efficiency of the algorithm can be evaluated by comparing with these solutions.

[0091] 9. Feedback from practical application:

[0092] The actual efficiency and effectiveness of the algorithm can be evaluated by collecting user feedback and usage data in actual application scenarios.

[0093] 10. Simulation and simulation:

[0094] In some algorithms where the performance cannot be measured directly, simulation or emulation methods can be used to estimate the efficiency of the algorithm.

[0095] In actual financial classification tasks, the AUC score can be applied in the fields of compliance and auditing, and the AUC score can be used to evaluate the model's ability to identify non-compliant behaviors. This is crucial to ensure that companies comply with regulations and reduce legal risks. The AUC score is diverse and important in financial classification tasks. It not only helps improve the accuracy of decision-making, but also helps companies reduce risks and improve efficiency.

[0096] Procurement management in universities faces many challenges, such as unclear commodity classification, cumbersome procurement process, opaque fund management, and complex fixed asset certification. These problems not only affect procurement efficiency, but also increase management costs. The present invention aims to provide a scientific classification of digital procurement commodities for universities that can intelligently classify and purchase commodities, seamlessly connect project fund card management, and simplify the fixed asset certification process, so as to improve the procurement, financial and asset management costs and efficiency of universities.

[0097] The present invention relates to a scientific classification system for digital procurement of goods in colleges and universities. The system deeply integrates multiple technical fields such as information technology, financial management, asset identification, and compliance risk control. It aims to achieve efficient and intelligent management of the procurement process while ensuring the compliance of project funding use and the accuracy of fixed asset identification.

[0098] 1. Information Technology

[0099] This system makes full use of modern information technology, including but not limited to cloud computing, big data, artificial intelligence and other cutting-edge technologies, to achieve the digitization, automation and intelligence of the procurement process. By building intelligent classification algorithms and data analysis models, the system can automatically identify, classify and match purchased goods, and at the same time associate them with project funding cards to ensure accurate control and efficient execution of procurement activities.

[0100] 2. Financial Management Field

[0101] In terms of financial management, this system has achieved seamless connection with the university's financial management system, and can monitor the use of project funds in real time, including key links such as budget formulation, fund allocation, use records, and settlement audits. By introducing the project fund card management mechanism, the system can ensure that each procurement activity is associated with a specific project fund card, thereby effectively avoiding fund abuse and illegal operations.

[0102] III. Asset Identification Area

[0103] For fixed asset identification, this system sets strict identification standards and processes based on relevant laws and regulations and the internal management system of colleges and universities. Through intelligent identification technology and data analysis, the system can automatically determine whether the purchased goods meet the identification conditions of fixed assets and generate corresponding asset identification reports. This not only improves the accuracy and efficiency of asset identification, but also helps colleges and universities better master and manage fixed assets.

[0104] IV. Compliance and Risk Control

[0105] In terms of compliance and risk control, the system has built-in multiple risk warning and prevention mechanisms, which can monitor potential risks in the procurement process in real time, including price anomalies, supplier credibility issues, and budget overruns. Once a risk is discovered, the system will immediately trigger the warning mechanism to remind relevant personnel to take timely measures to intervene and correct it. This helps colleges and universities maintain a high level of compliance and risk control capabilities during the procurement process.

[0106] V. Management Areas

[0107] After the university procurement platform is connected with the personnel system, seamless flow and sharing of data can be achieved, the operating process can be simplified, and management efficiency can be improved.

[0108] This embodiment has the following beneficial effects:

[0109] 1. Improve procurement efficiency and quality

[0110] Automated process optimization: The system significantly shortens the procurement cycle and improves work efficiency by automating the purchase application, approval, order placement and settlement process.

[0111] Intelligent classification and matching: Using advanced algorithm models, the system can automatically identify and classify purchased goods, and accurately match them with project funding cards to ensure the compliance and accuracy of procurement activities.

[0112] Data-driven decision-making: Through big data analysis, the system can provide decision-making support such as procurement trend forecasts and cost optimization suggestions, helping universities make more scientific and reasonable procurement decisions.

[0113] II. Strengthening project funding management

[0114] Funding card association monitoring: The system realizes the close association between project funding cards and procurement activities, monitors the use of funds in real time, and effectively avoids fund abuse and illegal operations.

[0115] Budget control and early warning: According to the set budget limit, the system automatically controls funds and issues early warnings when the budget is approaching or exceeded, ensuring the rational use of project funds.

[0116] 3. Optimize the identification of fixed assets

[0117] Intelligent asset identification: The system automatically identifies and classifies purchased goods based on fixed asset identification standards, improving the accuracy and efficiency of asset identification.

[0118] Information sharing: The system can realize the sharing of asset information, improve the transparency and controllability of asset management, and provide strong support for the optimal allocation and rational use of assets.

[0119] 4. Enhance compliance and risk control capabilities

[0120] Compliance check: The system has a built-in compliance check module to conduct real-time monitoring and early warning of procurement activities to ensure that procurement activities comply with relevant laws and regulations and the internal management system of universities.

[0121] Risk prevention and control mechanism: Through risk warning and prevention and control mechanisms, the system can promptly detect and deal with potential procurement risks, such as supplier credibility issues, price anomalies, etc., to ensure the smooth progress of procurement activities.

[0122] 5. Improve data analysis and decision support capabilities

[0123] Data mining and analysis: Using technologies such as big data and artificial intelligence, the system can conduct in-depth mining and analysis of procurement data, providing data support for university procurement decisions.

[0124] Visual display: Through visualization technology, the system can visualize procurement data, processes and results, improving the transparency and controllability of supervision.

[0125] 6. Promote the digital transformation of university procurement management

[0126] Digital empowerment: The implementation of this system has promoted the digital transformation of university procurement management and improved the intelligence level of procurement management.

[0127] Multi-department collaboration: The system can achieve collaborative work among multiple departments, improving the overall efficiency and collaboration of procurement management.

[0128] The following is a description of the commodity classification method for university purchases provided by the present invention. The commodity classification method for university purchases described below and the commodity classification system for university purchases described above can correspond to each other.

[0129] like Figure 3 As shown, the method includes:

[0130] Step 301, collecting commodity data involved in the commodity procurement business of the university through a data collection module;

[0131] Step 302, extracting feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data through a feature extraction module;

[0132] Step 303, using a machine learning or deep learning algorithm to classify the commodities according to the extracted feature data through a commodity classification module to obtain a classification result of the commodities;

[0133] Step 304: compare the feature data of different commodities through the comparison generation module, and optimize the classification result of the commodities according to the comparison result.

[0134] This embodiment automatically classifies goods by combining the specific requirements of financial expense project management and fixed asset entry with commodity classification, thereby improving the efficiency and accuracy of commodity classification; it realizes dynamic adjustment and optimization of commodity classification by generating an algorithm through data comparison, further improving the accuracy of commodity classification and adapting to different project management needs.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the university procurement commodity classification method provided by the above methods, and the method includes: collecting commodity data involved in the university commodity procurement business through a data acquisition module; extracting feature data related to financial project management and fixed asset entry requirements based on the collected commodity data through a feature extraction module; classifying the commodities according to the extracted feature data using a machine learning or deep learning algorithm through a commodity classification module to obtain the classification results of the commodities; comparing the feature data of different commodities through a comparison generation module, and optimizing the classification results of the commodities according to the comparison results.

[0136] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0137] 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. A commodity classification system for university purchases, characterized in that: include: The data collection module is used to collect commodity data involved in the commodity procurement business of colleges and universities; A feature extraction module, for extracting feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data; A commodity classification module, used to classify the commodities according to the extracted feature data using a machine learning or deep learning algorithm to obtain a classification result of the commodities; The comparison generation module is used to compare the feature data of different commodities and optimize the classification results of the commodities according to the comparison results.

2. The commodity classification system for university purchases according to claim 1 is characterized in that: The commodity data includes one or more of commodity name, specification model, price, quantity, purpose and validity period.

3. The commodity classification system for university purchases according to claim 1 is characterized in that: The characteristic data includes one or more of financial expenditure items, project types, budget types and asset attributes.

4. The commodity classification system for university purchases according to claim 3 is characterized in that: The financial classification is divided according to the funding source, funding purpose and funding nature of the project funding card. The financial classification is divided into budgetary funds and extra-budgetary funds according to the funding source, divided into teaching funds, scientific research funds, administrative funds and logistics funds according to the funding purpose, and divided into business funds and special funds according to the funding nature.

5. The commodity classification system for university purchases according to claim 1 is characterized in that: The data collection module is also used to collect detailed data of the project fund card, the detailed data including the types of goods purchased by the project fund card and the remaining amount of the project fund card; The feature extraction module is used to: Analyze the commodity data of the commodity to determine the analysis result of the commodity data, wherein the analysis result includes one or more of commodity attributes, price trend, purchase frequency, fund usage, and whether the commodity is a fixed asset; According to the analysis result, determining the association relationship between the commodity data and the project expense card and fixed assets; Based on the association relationship and the collected commodity data, feature data related to financial expense project management and fixed asset entry requirements are extracted.

6. The commodity classification system for university purchases according to claim 1 is characterized in that: The characteristic data includes user behavior data and commodity attribute data of purchasing commodities, and the comparison generation module is specifically used for: Using collaborative filtering algorithms, the classification results of the commodities are re-determined based on the user behavior data of the commodities purchased and the commodity attribute data; In the case that the two classification results of the commodity are inconsistent, the latter classification result of the commodity is used as the final classification result of the commodity, or the two classification results are displayed for the user to select.

7. The commodity classification system for university purchases according to any one of claims 1 to 6, characterized in that: Also includes a user interface for: According to the query conditions input by the user, the classification results of the commodities corresponding to the query conditions are displayed; The classification result of the commodity is updated using the classification result input by the user.

8. A method for classifying commodities purchased by a university, characterized in that: include: Collect commodity data involved in the commodity procurement business of colleges and universities through the data collection module; Extracting feature data related to financial expense project management and fixed asset entry requirements based on the collected commodity data through a feature extraction module; Using a machine learning or deep learning algorithm to classify the commodities according to the extracted feature data through a commodity classification module, so as to obtain a classification result of the commodities; The feature data of different commodities are compared through the comparison generation module, and the classification results of the commodities are optimized according to the comparison results.

Images