Electronic archive management method and system for enterprise project management

Abstract

The invention provides an electronic archive management method and system for enterprise project management. The method comprises the following steps: acquiring a first group of electronic archives and a second group of electronic archives in an enterprise project management system; obtaining content features of the archives according to the received first group of electronic archives and the received second group of electronic archives; calculating to obtain a similarity estimated value of the archives according to the content features; and according to the content features and the similarity estimation value, calculating to obtain an optimization strategy of archive management. According to the invention, the optimization of archive management can be realized, and the efficiency and accuracy of project management decision are improved.

Description

Technical Field

[0001] The present invention relates to the field of enterprise project management, and more specifically, to an electronic archive management method and system for enterprise project management. Background Art

[0002] In enterprise project management, electronic archive management is a key link to ensure effective organization and rapid retrieval of project information. Traditional electronic archive management methods often rely on simple classification and storage mechanisms, which have obvious limitations when dealing with large amounts of heterogeneous data. With the expansion of enterprise project scale and the increase in data volume, how to efficiently manage and utilize these electronic archives has become a challenge. Existing technologies usually use keyword-based search and basic metadata management, which are unable to cope with complex archive association and similarity analysis. In addition, traditional archive management methods lack the ability to deeply analyze archive content, making it difficult to identify and utilize complex relationships between archives, which limits the application potential of archive management in project management decision-making.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects: the existing electronic archive management methods are unable to effectively process and analyze the content characteristics of a large number of electronic archives, resulting in the lack of pertinence and accuracy in the optimization strategy of archive management; at the same time, the existing technology also has deficiencies in archive similarity estimation and classification consistency analysis, which makes it impossible to fully utilize the potential value of electronic archives in project management decision support. Summary of the invention

[0004] The invention provides an electronic archive management method and system for enterprise project management.

[0005] In a first aspect of the present invention, there is provided an electronic archive management method for enterprise project management, comprising:

[0006] Obtain the first set of electronic files and the second set of electronic files in the enterprise project management system;

[0007] Obtaining content characteristics of the archives according to the received first group of electronic archives and second group of electronic archives;

[0008] Calculating an estimated value of similarity of the archives based on the content features;

[0009] The optimization strategy for archive management is calculated based on the content characteristics and similarity estimation values.

[0010] As a further improvement of the present application, the step of calculating the similarity estimation value of the archives according to the content features includes:

[0011] Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files;

[0012] Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives;

[0013] Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula:

[0014]

[0015] Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector.

[0016] As a further improvement of the present application, the step of obtaining the content characteristics of the archives according to the received first group of electronic archives and the second group of electronic archives includes: obtaining the classification characteristics of the archives according to the received first group of electronic archives and the second group of electronic archives, including:

[0017] Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set corresponding to the first group of electronic archives and a classification label set corresponding to the second group of electronic archives;

[0018] Based on the classification label set corresponding to the first group of electronic archives and the classification label set corresponding to the second group of electronic archives, and using the calculation method of set intersection and union, the classification consistency scores of the two groups of electronic archives are obtained;

[0019] Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula:

[0020]

[0021] Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

[0022] As a further improvement of the present application, the step of obtaining the content features of the archives according to the received first and second groups of electronic archives further includes: dividing the content feature search interval of the first group of electronic archives according to the number of archives in the first group of electronic archives and the estimated value of the classification consistency between the first and second groups of electronic archives; dividing the content feature search interval of the second group of electronic archives according to the number of archives in the second group of electronic archives and the estimated value of the classification consistency between the first and second groups of electronic archives, and the specific steps include:

[0023] Determine the number of files N1 of the first group of electronic files and the number of files N2 of the second group of electronic files;

[0024] Divide N1 and N2 by the predetermined number of intervals K to obtain the number of files that should be included in each search interval;

[0025] The number of files in each search interval is adjusted according to the classification consistency estimation value of the first group of electronic files and the second group of electronic files. If the classification consistency estimation value is higher than a preset threshold, the number of files with similar classification labels in each search interval is reduced. If the classification consistency estimation value is less than or equal to the preset threshold, the number of files with similar classification labels in each search interval is increased.

[0026] As a further improvement of the present application, the step of obtaining the content features of the archives according to the received first group of electronic archives and second group of electronic archives further includes: obtaining a feature peak position by using content feature search in any divided content feature search interval, and determining the feature peak position in other divided content feature search intervals according to the distribution law of the peak position, and the specific steps include:

[0027] Extract content features of electronic archives within each search interval to form feature vectors;

[0028] Use clustering algorithm to analyze feature vectors and identify feature peak locations;

[0029] Based on the identified characteristic peak positions, the characteristic peak positions in other search intervals are predicted. By comparing the peak positions of adjacent intervals, the search strategy is adjusted to improve the accuracy of characteristic peak recognition.

[0030] As a further improvement of the present application, the step of calculating the optimization strategy for archive management according to the content features and the similarity estimation values ​​includes selecting the archive management strategy that maximizes the sum of archive similarities as the optimization strategy according to the content features and the similarity estimation values, and the specific steps include:

[0031] Calculate the similarity between each pair of electronic profiles;

[0032] Add up the similarity scores of all profiles to get the total similarity score;

[0033] According to the total similarity score, the archive management strategy that can maximize the total similarity score is selected as the optimization strategy.

[0034] As a further improvement of the present application, according to the content characteristics, similarity estimation values ​​and the optimization strategy of archive management, a project management strategy that maximizes the sum of the optimization strategies of project management decisions is selected as decision support, and the specific steps include:

[0035] Step 7.1: For each project management decision, calculate the optimal strategy value of the decision based on the content characteristics and similarity estimates of its related electronic archives;

[0036] Step 7.2: Accumulate the optimization strategy values ​​of all project management decisions to obtain the total optimization strategy value of the project management decisions;

[0037] Step 7.3: Compare the total optimization strategy values ​​of different project management decisions, and select the project management decision with the largest total optimization strategy value as the final decision support;

[0038] Step 7.4: The specific method for calculating the optimized strategy value includes:

[0039] Step 7.4.1: For each project management decision, identify the set of electronic records that it involves;

[0040] Step 7.4.2: For each pair of files in the electronic file collection, calculate their similarity scores;

[0041] Step 7.4.3: Multiply the similarity score of each pair of files by the preset weight factor to obtain a weighted similarity score;

[0042] Step 7.4.4: Add up all weighted similarity scores to obtain the optimal strategy value for the project management decision.

[0043] As a further improvement of the present application, the electronic archive is a text archive, an image archive or a multimedia archive.

[0044] In a second aspect of the present invention, there is provided an electronic archive management system for enterprise project management, comprising:

[0045] The file processing module is used to obtain the first set of electronic files and the second set of electronic files in the enterprise project management system;

[0046] A feature extraction module, used for obtaining content features of archives according to the received first group of electronic archives and second group of electronic archives;

[0047] A similarity estimation module, used for calculating the similarity estimation value of the archive according to the content features;

[0048] The archive management optimization module is used to calculate the optimization strategy of archive management according to the content characteristics and similarity estimation values.

[0049] Furthermore, the calculating of the similarity estimation value of the archive according to the content feature includes:

[0050] Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files;

[0051] Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives;

[0052] Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula:

[0053]

[0054] Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector;

[0055] The content characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include: the classification characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include:

[0056] Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set corresponding to the first group of electronic archives and a classification label set corresponding to the second group of electronic archives;

[0057] Based on the classification label set corresponding to the first group of electronic archives and the classification label set corresponding to the second group of electronic archives, and using the calculation method of set intersection and union, the classification consistency scores of the two groups of electronic archives are obtained;

[0058] Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula:

[0059]

[0060] Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

[0061] The above-mentioned embodiments of the present invention have at least the following beneficial effects: by implementing the enterprise project management electronic archive management method described in the present invention, the efficiency and accuracy of archive management can be significantly improved. The method enables the archive management strategy to be based on the in-depth analysis of the archive content through feature extraction and similarity calculation, thereby optimizing the archive classification and retrieval process. In addition, by calculating the similarity estimation value and classification consistency estimation value of the archive, the association between archives can be more accurately identified, providing more reliable support for project management decisions. The application of this method can significantly reduce the time of archive retrieval in project management and improve the accuracy of decision-making, thereby improving the quality and efficiency of the entire project management.

[0062] In addition, the electronic archive management system design of the present invention can be flexibly applied to different types of electronic archives, including text archives, image archives or multimedia archives, which enhances the versatility and applicability of the system. The system can reduce the need for manual operation and management costs through automated feature extraction and similarity estimation. At the same time, the content feature search interval division and feature peak position prediction functions provided by the system can further improve the intelligent level of archive management. The integrated application of these technologies can effectively support enterprises in information organization and decision-making in project management, bringing higher operational efficiency and stronger market competitiveness to enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0064] Figure 1 A flowchart of an electronic archive management method for enterprise project management provided by an embodiment of the present invention.

[0065] Figure 2 A schematic diagram of the structure of an electronic archive management system for enterprise project management provided by one embodiment of the present invention.

[0066] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0068] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0069] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0070] Reference below Figure 1 , Figure 1 The flowchart of the electronic archive management method for enterprise project management provided by one embodiment of the present invention is as follows. Figure 1 As shown, an electronic archive management method 100 for enterprise project management includes:

[0071] Step 101, obtaining a first set of electronic files and a second set of electronic files in an enterprise project management system;

[0072] Step 102, obtaining content characteristics of the files according to the received first group of electronic files and second group of electronic files;

[0073] Step 103, calculating and obtaining a similarity estimation value of the archive according to the content features;

[0074] Step 104, calculating and obtaining an optimization strategy for archive management based on the content features and similarity estimation values.

[0075] It should be noted that the method includes obtaining a first set of electronic files and a second set of electronic files in the enterprise project management system, where the electronic files refer to various types of files stored in electronic form, including but not limited to text documents, images, audio and video, etc. These files may contain various information related to the project, such as project plans, progress reports, meeting minutes, etc.

[0076] Specifically, when implementing this method, the two sets of electronic archives can be imported from the enterprise project management system. For example, an automated script can be set up to regularly capture updated archive data from the system. These archives can be classified according to criteria such as project stage, type or creation date, and stored in a database or cloud storage service for subsequent processing and analysis.

[0077] Preferably, in order to improve efficiency and accuracy, the two sets of electronic archives may be preprocessed, for example, removing irrelevant metadata, standardizing document formats, compressing image files, etc.

[0078] Furthermore, different priorities can be assigned to archives based on their importance or frequency of use, so that they can be given more attention in subsequent analysis. This ensures that the analysis process is more efficient and useful results can be obtained faster.

[0079] In some embodiments, the step of calculating the similarity estimation value of the archive according to the content feature includes:

[0080] Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files;

[0081] Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives;

[0082] Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula:

[0083]

[0084] Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector.

[0085] It should be noted that the method involves obtaining content features of the archives based on the received first group of electronic archives and the second group of electronic archives. The content features here refer to useful information in the archives that can be extracted and analyzed, such as keywords in text archives, tones and textures in image archives, etc.

[0086] Specifically, when implementing this method, the two groups of electronic archives are first subjected to feature extraction processing. For example, for text archives, natural language processing technology can be used to extract keywords and phrases; for image archives, image recognition technology can be used to extract color histograms and shape features. After feature extraction, the content feature sets of the two groups of archives will be obtained.

[0087] Preferably, the feature extraction process can be further refined. For example, for text archives, the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm can be used to evaluate the importance of keywords; for image archives, a deep learning model can be used to identify and extract more complex visual features.

[0088] Furthermore, we can select appropriate feature extraction algorithms according to the type and content of the archives to improve the accuracy and efficiency of feature extraction. Through these optimizations, we can more effectively identify the key content features of the archives, providing a more reliable foundation for subsequent similarity calculations and archive management.

[0089] In some embodiments, obtaining the classification characteristics of the archives according to the received first group of electronic archives and second group of electronic archives includes:

[0090] Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set C1 corresponding to the first group of electronic archives and a classification label set C2 corresponding to the second group of electronic archives;

[0091] The classification consistency scores of the two sets of electronic archives are obtained by using the calculation method of set intersection and union based on C1 and C2;

[0092] Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula:

[0093]

[0094] Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

[0095] It should be noted that the method includes obtaining classification features of archives based on the received first group of electronic archives and the second group of electronic archives. The classification features here refer to the categories or labels assigned to archives according to their contents, which are helpful for systematic organization and management of archives. The classification features can be based on attributes such as project type, document source, and importance level.

[0096] Specifically, when implementing the method, the two sets of electronic archives are first processed with classification labels. This means that each electronic archive is assigned one or more classification labels, which can be preset or dynamically generated based on the archive content. For example, a project report may be labeled as project report, finance, and 2023. The classification label set can be a list or a database table that contains the classification information of all archives.

[0097] Preferably, the classification labels can be processed using automated classification algorithms, such as decision trees, random forests or neural networks, which can automatically assign classification labels based on the content of the archives.

[0098] Furthermore, in order to improve the accuracy of classification, a supervised learning process can be introduced, in which the classification results are manually reviewed and adjusted, and then fed back into the algorithm for optimization. This method can not only improve the efficiency of classification, but also ensure the accuracy and consistency of classification results. In this way, electronic archives can be managed and retrieved more efficiently, thereby improving the performance of the entire archive management system.

[0099] In some embodiments, the step of obtaining the content features of the archives according to the received first and second groups of electronic archives further includes: dividing the content feature search interval of the first group of electronic archives according to the number of archives in the first group of electronic archives and the estimated value of the classification consistency between the first and second groups of electronic archives; dividing the content feature search interval of the second group of electronic archives according to the number of archives in the second group of electronic archives and the estimated value of the classification consistency between the first and second groups of electronic archives, and the specific steps include:

[0100] Determine the number of files N1 of the first group of electronic files and the number of files N2 of the second group of electronic files;

[0101] Divide N1 and N2 by the predetermined number of intervals K to obtain the number of files that should be included in each search interval;

[0102] The number of files in each search interval is adjusted according to the classification consistency estimation value of the first group of electronic files and the second group of electronic files. If the classification consistency estimation value is higher than a preset threshold, the number of files with similar classification labels in each search interval is reduced. If the classification consistency estimation value is less than or equal to the preset threshold, the number of files with similar classification labels in each search interval is increased.

[0103] It should be noted that the content feature search interval of the first group of electronic archives is divided according to the number of archives in the first group of electronic archives and the estimated value of the classification consistency of the first and second groups of electronic archives, and the content feature search interval of the second group of electronic archives is divided according to the number of archives in the second group of electronic archives and the estimated value of the classification consistency of the first and second groups of electronic archives. The search interval here refers to the area divided in the archive content feature space, which is used to limit the scope of search and analysis to improve processing efficiency and accuracy.

[0104] Specifically, when implementing this method, it is first necessary to determine the number of files in the first and second groups of electronic files and their classification consistency estimates. This number and classification consistency estimate can be directly obtained through records and analysis in the file management system. Then, the number of files in each group is divided by the predetermined number of intervals, which can be set according to the processing capacity of the system and the degree of sophistication of the analysis. For example, if the first group has 1,000 files and the predetermined number of intervals is 10, then each search interval should contain 100 files. In this way, the first group of files can be divided into 10 search intervals.

[0105] Preferably, in order to improve the flexibility and adaptability of the search interval division, a dynamic adjustment mechanism can be introduced. Specifically, if the classification consistency estimate is higher than the preset threshold, the number of archives with similar classification labels in each search interval is reduced to ensure the diversity of the archives; if the classification consistency estimate is less than or equal to the preset threshold, the number of archives with similar classification labels in each search interval is increased to strengthen the consistency of content features. This adjustment mechanism can adjust the number of archives in each interval according to the diversity and complexity of the archive content. For intervals with more concentrated content, the number of archives can be appropriately reduced to facilitate more detailed analysis; and for intervals with more dispersed content, the number of archives can be increased to increase processing speed.

[0106] Furthermore, the size of the search interval can be adjusted according to the importance and frequency of use of the archives to ensure that key archives can receive adequate attention and analysis. Through these optimizations, the content characteristics of electronic archives can be more effectively managed and utilized, thereby improving the efficiency and effectiveness of archive management.

[0107] In some embodiments, the step of obtaining the content features of the archives according to the received first group of electronic archives and second group of electronic archives further includes: obtaining a feature peak position by using content feature search in any divided content feature search interval, and determining the feature peak positions in other divided content feature search intervals according to the distribution law of the peak position, and the specific steps include:

[0108] Extract content features of electronic archives within each search interval to form feature vectors;

[0109] Use clustering algorithm to analyze feature vectors and identify feature peak locations;

[0110] Based on the identified characteristic peak positions, the characteristic peak positions in other search intervals are predicted. By comparing the peak positions of adjacent intervals, the search strategy is adjusted to improve the accuracy of characteristic peak recognition.

[0111] It should be noted that the method includes obtaining a characteristic peak position by using content feature search in any divided content feature search interval, and determining the characteristic peak position in other divided content feature search intervals according to the distribution law of the peak position. The characteristic peak position mentioned here refers to a representative or significant point in the content feature space, which can be used as a typical representative of the archive content features in the interval.

[0112] Specifically, when implementing the method, content features of the electronic archives in each search interval are extracted to form feature vectors, and then these feature vectors are analyzed using a clustering algorithm to identify the feature peak positions.

[0113] More specifically, the clustering algorithm can be K-means, hierarchical clustering or DBSCAN, etc. The specific algorithm can be determined according to the characteristics and distribution of the archive content. Through cluster analysis, the most representative feature vector in each interval, that is, the feature peak position, can be found.

[0114] Preferably, in order to improve the accuracy of the characteristic peak position identification, a multi-step clustering verification method can be used. First, a preliminary clustering analysis is performed in a search interval to determine the preliminary characteristic peak position. Then, this peak position is used as a reference point to perform clustering analysis on adjacent search intervals to verify and adjust the characteristic peak position.

[0115] Furthermore, machine learning technology can be introduced to identify and predict the peak position of features through training models, thereby improving the accuracy and efficiency of prediction. Through these optimization measures, the content features of electronic archives can be more effectively identified and utilized, thereby improving the quality and efficiency of archive management.

[0116] In some embodiments, according to the content features and the similarity estimation values, the archive management strategy that maximizes the sum of archive similarities is selected as the optimization strategy, and the specific steps include:

[0117] Calculate the similarity between each pair of electronic profiles;

[0118] Add up the similarity scores of all profiles to get the total similarity score;

[0119] According to the total similarity score, the archive management strategy that can maximize the total similarity score is selected as the optimization strategy.

[0120] It should be noted that the method includes selecting the archive management strategy that maximizes the sum of archive similarities based on content characteristics and similarity estimates as the optimization strategy. The archive management strategy here refers to a series of management decisions and action plans aimed at optimizing the storage, retrieval and use of archives to improve the efficiency and effectiveness of archive management.

[0121] Specifically, when implementing this method, the similarity between each pair of electronic archives is first calculated. This can be achieved by comparing the similarity of their contents, including feature vectors. Similarity calculations can be performed using methods such as cosine similarity, Jaccard similarity, or Euclidean distance. Next, the similarity scores of all archives are added together to obtain a total similarity score. This total similarity score reflects the overall similarity of the archive collection and can be used as a basis for selecting archive management strategies.

[0122] Preferably, in order to maximize the sum of archive similarities, an optimization algorithm can be used to select the best archive management strategy. For example, linear programming, dynamic programming or genetic algorithm can be used to solve this problem.

[0123] Furthermore, weight factors can be introduced to adjust the contribution of different archives or different features to the total similarity score to reflect the importance of the archive or the relevance of the features. Through these optimization measures, the similarity information of archives can be used more effectively, thereby improving the quality and efficiency of archive management.

[0124] In some embodiments, according to the content features, similarity estimation values ​​and the optimization strategy of archive management, a project management strategy that maximizes the sum of the optimization strategies of project management decisions is selected as decision support, and the specific steps include:

[0125] Step 7.1: For each project management decision, calculate the optimal strategy value of the decision based on the content characteristics and similarity estimates of its related electronic archives;

[0126] Step 7.2: Accumulate the optimization strategy values ​​of all project management decisions to obtain the total optimization strategy value of the project management decisions;

[0127] Step 7.3: Compare the total optimization strategy values ​​of different project management decisions, and select the project management decision with the largest total optimization strategy value as the final decision support;

[0128] Step 7.4: The specific method for calculating the optimized strategy value includes:

[0129] Step 7.4.1: For each project management decision, identify the set of electronic records that it involves;

[0130] Step 7.4.2: For each pair of files in the electronic file collection, calculate their similarity scores;

[0131] Step 7.4.3: Multiply the similarity score of each pair of files by the preset weight factor to obtain a weighted similarity score;

[0132] Step 7.4.4: Add up all weighted similarity scores to obtain the optimal strategy value for the project management decision.

[0133] It should be noted that the method includes selecting a project management strategy that maximizes the sum of the optimization strategies for project management decisions based on content characteristics, similarity estimates, and optimization strategies for archive management as decision support. The project management strategy here refers to a series of strategies and action plans formulated to achieve project goals. These strategies need to comprehensively consider various factors of the project, including time, cost, quality, and resources.

[0134] Specifically, when implementing this method, the optimization strategy value of each project management decision is first calculated based on the content characteristics and similarity estimates of its related electronic archives. This can be done by analyzing key information in the archives, such as project plans, progress reports, and risk assessments, to determine the potential impact and effect of each decision. Then, the optimization strategy values ​​of all project management decisions are accumulated to obtain the total optimization strategy value of the project management decisions. This total optimization strategy value reflects the comprehensive effect of all decisions and can be used as a basis for selecting the final decision support.

[0135] Preferably, in order to improve the calculation accuracy of the optimization strategy value of project management decisions, a machine learning model can be introduced to analyze the archive content and predict the decision effect. For example, algorithms such as support vector machines, random forests, or neural networks can be used to process large amounts of archive data and predict the potential results of each decision.

[0136] Furthermore, historical data can be used to train and validate the model to improve the accuracy of the prediction. Through these optimization measures, archival information can be used more effectively to support project management decisions, thereby improving the success rate and efficiency of the project.

[0137] In some embodiments, the electronic file is a text file, an image file, or a multimedia file.

[0138] It should be noted that the electronic archives involved in this method are text archives, image archives or multimedia archives. The electronic archives mentioned here refer to information collections stored in electronic form, which can include files of various formats and types, such as text files (TXT, PDF, Word documents), image files (JPG, PNG, GIF), audio files (MP3, WAV), video files (MP4, AVI), etc. These electronic archives are indispensable information resources in enterprise project management.

[0139] Specifically, when implementing this method, different types of electronic archives need to be processed and analyzed accordingly. For example, text archives can extract keywords and themes through text mining technology, image archives can extract color, texture and shape features through image processing technology, and multimedia archives may need to combine audio and video analysis technology to extract relevant features. These feature extraction processes require the selection of appropriate technologies and tools based on the type and content of the archive.

[0140] Preferably, in order to improve the efficiency and accuracy of feature extraction, advanced data processing and machine learning technologies can be used. For example, for text archives, natural language processing (NLP) technologies such as sentiment analysis and entity recognition can be used; for image archives, deep learning models such as convolutional neural networks (CNN) can be used to extract high-level visual features; for multimedia archives, audio and video analysis technologies such as speech recognition and action recognition can be combined.

[0141] Furthermore, appropriate pre-processing and post-processing steps can be selected according to the specific needs and resource conditions of the project to optimize the effect of feature extraction and analysis. Through these optimization measures, various types of electronic archives can be managed and utilized more effectively, thereby improving the overall efficiency and quality of enterprise project management.

[0142] The above-mentioned embodiments of the present invention have the following beneficial effects: the electronic archive management method of the present invention can optimize the archive management strategy and improve the efficiency and accuracy of project management decisions by comprehensively analyzing the content characteristics and similarities of electronic archives. Specifically, the method can make archive management more refined and personalized, and through feature extraction and similarity calculation, it can more accurately identify the associations and differences between archives, thereby providing more accurate decision support for project management. The application of this method can significantly improve the speed and accuracy of archive retrieval, reduce the complexity of manual operations, and enhance the intelligent level of archive management, bringing higher efficiency and better decision-making quality to enterprise project management.

[0143] like Figure 2 As shown, in some embodiments, an electronic archive management system 200 for enterprise project management includes:

[0144] The file processing module 201 is used to obtain the first set of electronic files and the second set of electronic files in the enterprise project management system;

[0145] A feature extraction module 202, configured to obtain content features of archives according to the received first group of electronic archives and second group of electronic archives;

[0146] A similarity estimation module 203, used to calculate the similarity estimation value of the archive according to the content features;

[0147] The archive management optimization module 204 is used to calculate the optimization strategy of archive management according to the content characteristics and similarity estimation values.

[0148] It is understandable that the modules and references recorded in the electronic archive management system 200 for enterprise project management Figure 1 Therefore, the operations, features and beneficial effects described above for the electronic archive management method for enterprise project management are also applicable to the electronic archive management system 200 for enterprise project management and the modules contained therein, and will not be repeated here.

[0149] In some embodiments, the calculating of the similarity estimation value of the archive according to the content feature includes:

[0150] Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files;

[0151] Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives;

[0152] Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula:

[0153]

[0154] Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector;

[0155] The content characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include: the classification characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include:

[0156] Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set corresponding to the first group of electronic archives and a classification label set corresponding to the second group of electronic archives;

[0157] Based on the classification label set corresponding to the first group of electronic archives and the classification label set corresponding to the second group of electronic archives, and using the calculation method of set intersection and union, the classification consistency scores of the two groups of electronic archives are obtained;

[0158] Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula:

[0159]

[0160] Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

[0161] It should be noted that the system includes an archive processing module, a feature extraction module, a similarity estimation module and an archive management optimization module. The archive processing module here refers to a part of the system that is responsible for obtaining electronic archives from the enterprise project management system. These archives are various types of records and documents generated during the project management process.

[0162] Specifically, when the system is implemented, the archive processing module will import electronic archives from the enterprise project management system regularly or as needed through automated scripts or API calls. These archives may include project plans, progress updates, financial reports, meeting minutes, design drawings, photos, videos, etc. The feature extraction module will analyze these archives and extract key information, such as keywords for text archives, resolution and color mode for image archives, etc.

[0163] Preferably, the archive processing module can be designed to have high compatibility and scalability to support electronic archives in multiple formats and project management systems from different sources. The feature extraction module can adopt advanced text mining, image processing and multimedia analysis technologies to improve the accuracy and efficiency of feature extraction. The similarity estimation module will use these features to calculate the similarities between archives, and the archive management optimization module will propose management strategies based on these similarities to optimize the storage, retrieval and use of archives.

[0164] Furthermore, the system can include a user interface that allows users to monitor and manage the process of file processing and analysis, as well as adjust system parameters to adapt to specific project management needs. Through these optimization measures, the flexibility and adaptability of the system can be improved, so that it can better serve enterprise project management.

[0165] Reference below Figure 3 , which shows a schematic diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0166] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0167] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0168] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0169] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention to form a technical solution.

Claims

1. An electronic archive management method for enterprise project management, characterized in that: The following steps are involved: Obtain the first set of electronic files and the second set of electronic files in the enterprise project management system; Obtaining content characteristics of the archives according to the received first group of electronic archives and second group of electronic archives; Calculating an estimated value of similarity of the archives based on the content features; The optimization strategy for archive management is calculated based on the content characteristics and similarity estimation values.

2. The electronic archive management method for enterprise project management according to claim 1, characterized in that: The step of calculating the similarity estimation value of the archive according to the content feature comprises: Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files; Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives; Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula: Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector.

3. The electronic archive management method for enterprise project management according to claim 2, characterized in that: The step of obtaining the content characteristics of the archives according to the received first group of electronic archives and the second group of electronic archives includes: obtaining the classification characteristics of the archives according to the received first group of electronic archives and the second group of electronic archives, including: Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set corresponding to the first group of electronic archives and a classification label set corresponding to the second group of electronic archives; Based on the classification label set corresponding to the first group of electronic archives and the classification label set corresponding to the second group of electronic archives, and using the calculation method of set intersection and union, the classification consistency scores of the two groups of electronic archives are obtained; Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula: Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

4. The electronic archive management method for enterprise project management according to claim 3, characterized in that: The step of obtaining the content features of the archives according to the received first and second groups of electronic archives further includes: dividing the content feature search interval of the first group of electronic archives according to the number of archives in the first group of electronic archives and the estimated value of the classification consistency of the first and second groups of electronic archives; dividing the content feature search interval of the second group of electronic archives according to the number of archives in the second group of electronic archives and the estimated value of the classification consistency of the first and second groups of electronic archives, and the specific steps include: Determine the number of files N1 of the first group of electronic files and the number of files N2 of the second group of electronic files; Divide N1 and N2 by the predetermined number of intervals K to obtain the number of files that should be included in each search interval; The number of files in each search interval is adjusted according to the classification consistency estimation value of the first group of electronic files and the second group of electronic files. If the classification consistency estimation value is higher than a preset threshold, the number of files with similar classification labels in each search interval is reduced. If the classification consistency estimation value is less than or equal to the preset threshold, the number of files with similar classification labels in each search interval is increased.

5. The electronic archive management method for enterprise project management according to claim 4, characterized in that: The step of obtaining the content features of the archives according to the received first group of electronic archives and second group of electronic archives further includes: obtaining a feature peak position by using content feature search in any divided content feature search interval, and determining the feature peak positions in other divided content feature search intervals according to the distribution law of the peak position, and the specific steps include: Extract content features of electronic archives within each search interval to form feature vectors; Use clustering algorithm to analyze feature vectors and identify feature peak locations; Based on the identified characteristic peak positions, the characteristic peak positions in other search intervals are predicted. By comparing the peak positions of adjacent intervals, the search strategy is adjusted to improve the accuracy of characteristic peak recognition.

6. The electronic archive management method for enterprise project management according to claim 5, characterized in that: The step of calculating the optimization strategy for archive management according to the content features and the similarity estimation value includes selecting the archive management strategy that maximizes the sum of archive similarities as the optimization strategy according to the content features and the similarity estimation value, and the specific steps include: Calculate the similarity between each pair of electronic profiles; Add up the similarity scores of all profiles to get the total similarity score; According to the total similarity score, the archive management strategy that can maximize the total similarity score is selected as the optimization strategy.

7. The electronic archive management method for enterprise project management according to claim 6, characterized in that: According to the content characteristics, similarity estimation values ​​and the optimization strategy of archive management, a project management strategy that maximizes the sum of the optimization strategies of project management decisions is selected as decision support, and the specific steps include: Step 7.1: For each project management decision, calculate the optimal strategy value of the decision based on the content characteristics and similarity estimates of its related electronic archives; Step 7.2: Accumulate the optimization strategy values ​​of all project management decisions to obtain the total optimization strategy value of the project management decisions; Step 7.3: Compare the total optimization strategy values ​​of different project management decisions, and select the project management decision with the largest total optimization strategy value as the final decision support; Step 7.4: The specific method for calculating the optimized strategy value includes: Step 7.4.1: For each project management decision, identify the set of electronic records that it involves; Step 7.4.2: For each pair of files in the electronic file collection, calculate their similarity scores; Step 7.4.3: Multiply the similarity score of each pair of files by the preset weight factor to obtain a weighted similarity score; Step 7.4.4: Add up all weighted similarity scores to obtain the optimal strategy value for the project management decision.

8. An electronic archive management method for enterprise project management according to any one of claims 1 to 7, characterized in that: The electronic file is a text file, an image file or a multimedia file.

9. An electronic archive management system for enterprise project management, characterized in that: include: The file processing module is used to obtain the first set of electronic files and the second set of electronic files in the enterprise project management system; A feature extraction module, used for obtaining content features of archives according to the received first group of electronic archives and second group of electronic archives; A similarity estimation module, used for calculating the similarity estimation value of the archive according to the content features; The archive management optimization module is used to calculate the optimization strategy of archive management according to the content characteristics and similarity estimation values.

10. The electronic archive management system for enterprise project management according to claim 9, characterized in that: The calculating of the similarity estimation value of the archive according to the content feature includes: Perform feature extraction processing on the first group of electronic files and the second group of electronic files respectively to obtain content features corresponding to the first group of electronic files and content features corresponding to the second group of electronic files; Based on the content features corresponding to the first group of electronic archives and the content features corresponding to the second group of electronic archives, a similarity calculation method is used to obtain multiple similarity scores of the two groups of electronic archives; Compare the multiple similarity scores of the first group of electronic archives with the multiple similarity scores of the second group of electronic archives to obtain the content features corresponding to the two archives with the highest similarity; and obtain the similarity estimation value of the archives according to the content features by the following formula: Among them, Similarity is the estimated value of the similarity of the archives, F1 and F2 are the content feature vectors of the two groups of electronic archives, and n is the dimension of the feature vector; The content characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include: the classification characteristics of the archives obtained according to the received first group of electronic archives and the second group of electronic archives include: Performing classification label processing on the first group of electronic archives and the second group of electronic archives respectively to obtain a classification label set corresponding to the first group of electronic archives and a classification label set corresponding to the second group of electronic archives; Based on the classification label set corresponding to the first group of electronic archives and the classification label set corresponding to the second group of electronic archives, and using the calculation method of set intersection and union, the classification consistency scores of the two groups of electronic archives are obtained; Calculate the ratio of the classification consistency score to the total number of classification labels, and obtain the classification consistency estimate of the archive using the following formula: Among them, Consistency is the estimated value of the classification consistency of the archives, C1 is the classification label set corresponding to the first group of electronic archives, and C2 is the classification label set corresponding to the second group of electronic archives; |C1∩C2| represents the number of elements in the intersection of C1 and C2, and |C1∪C2| represents the number of elements in the union of C1 and C2.

Images