Enterprise document management methods, devices, equipment and storage media

Abstract

This invention relates to artificial intelligence technology and discloses a method for enterprise document management in the financial sector. The method includes: classifying documents in a managed enterprise document set according to the enterprise's organizational structure information to obtain document organization information categories; identifying the file type, business category, and source system of the documents in the managed enterprise document set; constructing a tag directory hierarchy for the managed enterprise document set based on the enterprise's organizational structure information, file type, business category, and source system; filtering the managed enterprise document set according to basic information and document organization information categories to obtain a set of authorized enterprise documents; and selecting a recommended document set from the authorized enterprise document set based on historical operation behavior data and basic information, and displaying the tag directory hierarchy of the recommended document set. This invention also proposes an enterprise document management device, electronic device, and storage medium. This invention can improve the efficiency and accuracy of document retrieval for financial enterprises.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an enterprise document management method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] As companies grow and expand, they accumulate more and more documents, which typically include rules and regulations, organizational structure, business descriptions, operating instructions, customer information, etc. For example, in the insurance business department of a financial company, the documents usually include rules and regulations, organizational structure, policy information, product terms, proposals, insurance rights and benefits, etc. The types of documents are numerous and the management is complex.

[0003] Currently, enterprise documents are often scattered across different computers, servers, or systems, making it unclear what operations employees have performed on the files and hindering document change tracking. Sensitive documents cannot be securely monitored, posing security risks. The lack of centralized storage and unclear directory structures makes document collaboration and sharing difficult. Enterprise document management is limited to backup and saving, failing to integrate with daily business operations, thus preventing the formation of an effective enterprise knowledge network and hindering the narrowing of search scope when querying documents.

[0004] In summary, current enterprise document management methods result in low efficiency and accuracy when searching enterprise documents. Summary of the Invention

[0005] This invention provides a method, apparatus, and computer-readable storage medium for enterprise document management, the main purpose of which is to solve the problems of low efficiency and accuracy when querying enterprise documents.

[0006] To achieve the above objectives, the present invention provides an enterprise document management method, comprising:

[0007] Obtain enterprise organizational structure information, and classify the documents in the enterprise document collection to be managed according to the enterprise organizational structure information to obtain document organization information categories;

[0008] Identify the file type, business category, and source system of the documents in the enterprise document collection to be managed;

[0009] Based on the enterprise organizational structure information, the file type, the business category, and the source system, construct a tag directory hierarchy for the enterprise document set to be managed;

[0010] Obtain basic information about enterprise users, and filter the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users;

[0011] Collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, filter out a recommended document set from the authorized enterprise document set, and display the tag directory level of the recommended document set.

[0012] Optionally, the step of filtering a recommended document set from the authorized enterprise document set based on the historical operation behavior data and the basic information includes:

[0013] Using the BERT model in the preset document recommendation model, the key behavioral features of the historical operation behavior data and the key job features of the basic information are extracted respectively.

[0014] By using the fusion layer in the preset document recommendation model, the key behavioral features and the key job features are fused to obtain a user feature vector;

[0015] Using the matching model in the preset document recommendation model, calculate the matching score between the user feature vector and the authorized enterprise document set;

[0016] Authorized enterprise documents with matching scores higher than a preset threshold are selected as recommended documents, and all recommended documents are aggregated to obtain a recommended document set.

[0017] Optionally, the step of calculating the matching score between the user feature vector and the authorized enterprise document set using the matching model in the preset document recommendation model includes:

[0018] Extract the feature vectors of each document in the authorized enterprise document set to obtain the authorized enterprise document feature vector set;

[0019] Randomly select a permission enterprise document feature vector from the set of permission enterprise document feature vectors as the first permission enterprise document feature vector, calculate the matching degree between the first permission enterprise document feature vector and the user feature vector, and obtain the matching degree matrix.

[0020] The matching degree matrix is ​​normalized and weighted by row and column respectively to obtain the attention weights;

[0021] The feature vectors of the first-permission enterprise document and the feature vectors of the other enterprise documents are weighted using attention weights to obtain the weighted feature vectors of the first-permission enterprise document and the weighted feature vectors of the other enterprise documents.

[0022] The weighted first-permission enterprise document feature vector is concatenated with the weighted feature vectors of other enterprise documents to obtain the concatenated permission enterprise document feature vector. The matching score between the concatenated permission enterprise document feature vector and the user feature vector is calculated using the softmax function.

[0023] Optionally, the step of filtering the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users includes:

[0024] Extract the job information and permission information from the basic information;

[0025] Based on the permission information, select documents from the set of enterprise documents to be managed that match the permissions of the enterprise users, and use them as the first document set;

[0026] Calculate the similarity between the job information and the document organization information category of the documents in the first document set;

[0027] Documents corresponding to document organization information categories with similarity greater than a preset similarity threshold are selected from the first document set and used as the permission enterprise document set corresponding to the enterprise user.

[0028] Optionally, the step of classifying documents in the document set of the enterprise to be managed according to the enterprise organizational structure information to obtain document organization information categories includes:

[0029] Extract keywords from the documents in the enterprise document collection to be managed;

[0030] The keywords are matched with the enterprise's organizational structure information to obtain the organizational information associated with the keywords, and the organizational information is used as the document organization information category of the document corresponding to the keywords.

[0031] Optionally, the step of constructing a tag directory hierarchy for the enterprise document set to be managed based on the enterprise organizational structure information, the file type, the business category, and the source system includes:

[0032] First, second, third, and fourth tag directory levels are constructed based on the enterprise organizational structure information, the file type, the business category, and the source system, respectively.

[0033] Optionally, identifying the business category of documents in the enterprise document set to be managed includes:

[0034] The documents in the document set of the enterprise to be managed are segmented into words to obtain a document word segmentation sequence;

[0035] Extract the feature vectors of the word segmentation sequence to obtain the document word segmentation vector set;

[0036] R document segmentation feature vectors are randomly selected from the document segmentation vector set as r initial cluster centroids;

[0037] Calculate the distance between each document segmentation feature vector in the document segmentation vector set and the initial cluster centroid;

[0038] Based on the magnitude of the distance, select the document word segmentation feature vectors corresponding to the distances as the k cluster centroids for clustering;

[0039] Calculate the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k cluster centroids, and classify the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance;

[0040] Calculate the average value of the document segmentation feature vectors in each class, update the k cluster centroids based on the average value, and return to the steps described above: calculate the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k updated cluster centroids, and classify the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance until convergence is achieved, thus completing the classification of the enterprise document set to be managed and obtaining the business category of the documents in the enterprise document set to be managed.

[0041] To address the above problems, the present invention also provides an enterprise document management device, the device comprising:

[0042] The classification module is used to obtain enterprise organizational structure information, classify the documents in the document collection of the enterprise to be managed according to the enterprise organizational structure information, and obtain the document organization information category.

[0043] The identification module is used to identify the file type, business category, and source system of the documents in the enterprise document set to be managed;

[0044] The directory building module is used to build a tag directory hierarchy for the enterprise document set to be managed based on the enterprise organizational structure information, the file type, the business category and the source system;

[0045] The document filtering module is used to obtain basic information of enterprise users, filter the set of enterprise documents to be managed according to the basic information and the document organization information category, and obtain the set of enterprise documents with permissions corresponding to the enterprise users.

[0046] The recommendation module is used to collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, to filter out a recommended document set from the authorized enterprise document set and display the tag directory level of the recommended document set.

[0047] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0048] At least one processor; and,

[0049] A memory communicatively connected to the at least one processor; wherein,

[0050] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the enterprise document management method described above.

[0051] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the enterprise document management method described above.

[0052] This invention classifies documents in a managed enterprise document set based on the enterprise's organizational structure information to obtain document organization information categories. It identifies the file type, business category, and source system of the documents in the managed enterprise document set. Based on the enterprise's organizational structure information, file type, business category, and source system, it designs document directory pages with different dimensions for the managed enterprise document set, allowing users to browse documents from multiple perspectives and find the most suitable viewing method according to their needs. Users can intuitively understand the directory structure of the documents. Furthermore, it filters the managed enterprise document set based on the basic information and the document organization information categories to obtain the enterprise document set corresponding to the enterprise user's permissions, reducing the number of interfering documents and making enterprise document queries more efficient. Finally, based on the historical operation behavior data and the basic information, it filters out recommended document sets from the authorized enterprise document sets, recommending documents that users are most likely to need, narrowing the query scope, and displays the tag directory hierarchy of the recommended document sets, making it easier and more intuitive for users to obtain documents, thereby improving the efficiency and accuracy of enterprise document queries in the financial field. Therefore, the enterprise document management method, device, electronic device, and computer-readable storage medium proposed in this invention can solve the problem of low efficiency and accuracy when financial companies conduct enterprise document searches. Attached Figure Description

[0053] Figure 1 A flowchart illustrating an enterprise document management method according to an embodiment of the present invention;

[0054] Figure 2 for Figure 1A detailed implementation flowchart of one step in the enterprise document management method shown below;

[0055] Figure 3 for Figure 1 A detailed implementation flowchart of another step in the enterprise document management method shown;

[0056] Figure 4 A functional block diagram of an enterprise document management device provided in an embodiment of the present invention;

[0057] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the enterprise document management method according to an embodiment of the present invention.

[0058] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0059] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0060] This application provides an enterprise document management method. The executing entity of the enterprise document management method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the enterprise document management method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0061] Reference Figure 1 The diagram shown is a flowchart illustrating an enterprise document management method according to an embodiment of the present invention. In this embodiment, the enterprise document management method includes:

[0062] S1. Obtain enterprise organizational structure information, and classify the documents in the enterprise document collection to be managed according to the enterprise organizational structure information to obtain document organization information categories.

[0063] In this embodiment of the invention, the enterprise organizational structure information refers to the overall organizational information of the company. For example, the organizational structure of a financial company is usually divided into a board of directors, a supervisory board, an audit department, a bank, an insurance company, etc.

[0064] In detail, S1 describes classifying documents in the managed enterprise document set according to the enterprise organizational structure information to obtain document organization information categories, including:

[0065] Extract keywords from the documents in the enterprise document collection to be managed;

[0066] The keywords are matched with the enterprise's organizational structure information to obtain the organizational information associated with the keywords, and the organizational information is used as the document organization information category of the document corresponding to the keywords.

[0067] In this embodiment of the invention, keywords can be extracted from documents in the enterprise document set to be managed using machine learning methods, semantic similarity statistics methods, and other methods.

[0068] In this embodiment of the invention, a common similarity algorithm can be used to calculate the similarity between the keyword and the enterprise organizational structure information, and the organizational information with the highest similarity in the enterprise organizational structure information can be used as the organizational information associated with the keyword.

[0069] S2. Identify the file type, business category, and source system of the documents in the enterprise document collection to be managed.

[0070] In this embodiment of the invention, the file type typically includes text types such as TXT and PDF, which can be identified by the document's suffix.

[0071] In this embodiment of the invention, the business category is related to the substantive content of the document and can be obtained by classifying the content of the document. For example, the documents of a financial company can be divided into several categories such as funds, stocks, and insurance based on the business category.

[0072] Specifically, S2, which describes identifying the business categories of documents in the enterprise document set to be managed, includes:

[0073] The documents in the document set of the enterprise to be managed are segmented into words to obtain a document word segmentation sequence;

[0074] Extract the feature vectors of the word segmentation sequence to obtain the document word segmentation vector set;

[0075] R document segmentation feature vectors are randomly selected from the document segmentation vector set as r initial cluster centroids;

[0076] Calculate the distance between each document segmentation feature vector in the document segmentation vector set and the initial cluster centroid;

[0077] Based on the magnitude of the distance, select the document word segmentation feature vectors corresponding to the distances as the k cluster centroids for clustering;

[0078] Calculate the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k cluster centroids, and classify the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance;

[0079] Calculate the average value of the document segmentation feature vectors in each class, update the k cluster centroids based on the average value, and return to the steps described above: calculate the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k updated cluster centroids, and classify the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance until convergence is achieved, thus completing the classification of the enterprise document set to be managed and obtaining the business category of the documents in the enterprise document set to be managed.

[0080] In this embodiment of the invention, the source system refers to the source location of the document, which can be categorized according to notes or other methods.

[0081] S3. Based on the enterprise organizational structure information, the file type, the business category, and the source system, construct a tag directory hierarchy for the enterprise document set to be managed.

[0082] Specifically, S3 includes:

[0083] First, second, third, and fourth tag directory levels are constructed based on the enterprise organizational structure information, the file type, the business category, and the source system, respectively.

[0084] In this embodiment of the invention, based on the enterprise organizational structure information, the file type, the business category, and the source system, document directory pages of different dimensions are designed for the document set of the enterprise to be managed, so that users can browse documents from multiple perspectives and find the most suitable document viewing method according to their needs. Users can intuitively understand the directory structure of the documents (the department, file type, business, and source system).

[0085] S4. Obtain the basic information of the enterprise user, and filter the enterprise document set to be managed according to the basic information and the document organization information category to obtain the enterprise document set with permissions corresponding to the enterprise user.

[0086] In this embodiment of the invention, the basic information of the enterprise user includes: age, gender, job position, job level, and set permissions. For example, if an employee of a financial company has the same job position and job level, but his or her job duties have changed, the permissions he or she applies for in the system may also change.

[0087] For details, please refer to Figure 2As shown, step S4, filtering the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise user, includes:

[0088] S41. Extract the job information and permission information from the basic information;

[0089] S42. Select documents that match the enterprise user permissions from the enterprise document set to be managed according to the permission information, and use them as the first document set;

[0090] S43. Calculate the similarity between the job information and the document organization information category of the documents in the first document set;

[0091] S44. Select documents from the first document set whose document organization information category has a similarity greater than a preset similarity threshold as the permission enterprise document set corresponding to the enterprise user.

[0092] In this embodiment of the invention, for example, if the permission scope of the customer manager's permission setting for the auto insurance business of a financial company is A, then the first document set is all documents within the scope of A. Further, based on the job information: customer manager of auto insurance business, the document organization information category of the document is matched to obtain the document whose document organization information category matches that of the customer manager of auto insurance business as the permission enterprise document set corresponding to the enterprise user.

[0093] In this embodiment of the invention, the set of enterprise documents to be managed is filtered according to the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users, thereby reducing the number of interfering documents and making enterprise document queries more efficient.

[0094] S5. Collect the historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, filter out the recommended document set from the authorized enterprise document set, and display the tag directory level of the recommended document set.

[0095] In this embodiment of the invention, big data collection tools can be used to collect historical operation behavior data of enterprise users. The historical operation behavior data is a record of document browsing, which is a record of document information browsed in the past period within a preset time period, such as the document information browsed by the customer manager of the insurance business of a financial company in the past year.

[0096] In this embodiment of the invention, after collecting the historical operation behavior data of the enterprise users, the historical operation behavior data can be stored in a preset database, such as Hive.

[0097] For details, please refer to Figure 3As shown, in S5, the process of filtering a recommended document set from the authorized enterprise document set based on the historical operation behavior data and the basic information includes:

[0098] S51. Using the BERT model in the preset document recommendation model, extract the key behavioral features of the historical operation behavior data and the key job features of the basic information respectively.

[0099] S52. Using the fusion layer in the preset document recommendation model, the key behavioral features and the key job features are fused to obtain a user feature vector;

[0100] S53. Using the matching model in the preset document recommendation model, calculate the matching score between the user feature vector and the authorized enterprise document set;

[0101] S54. The enterprise documents with matching scores higher than a preset threshold are selected as recommended documents, and all recommended documents are aggregated to obtain a recommended document set.

[0102] In this embodiment of the invention, the preset document recommendation model can be composed of a BERT model, a fusion layer, and a matching model. The BERT model is a large-scale pre-trained language model based on bidirectional Transformer, which has powerful language representation and feature extraction capabilities and can extract features of each word in the text. The fusion layer can concatenate vectors. The matching model includes a matching layer and a fully connected layer. The matching layer can perform an outer product on the text to be matched to obtain a similarity matrix. The fully connected layer can obtain a matching score by normalizing the two-dimensional vector using softmax.

[0103] Further, the step of calculating the matching score between the user feature vector and the authorized enterprise document set using the matching model in the preset document recommendation model includes:

[0104] Extract the feature vectors of each document in the authorized enterprise document set to obtain the authorized enterprise document feature vector set;

[0105] Randomly select a permission enterprise document feature vector from the set of permission enterprise document feature vectors as the first permission enterprise document feature vector, calculate the matching degree between the first permission enterprise document feature vector and the user feature vector, and obtain the matching degree matrix.

[0106] The matching degree matrix is ​​normalized and weighted by row and column respectively to obtain the attention weights;

[0107] The feature vectors of the first-permission enterprise document and the feature vectors of the other enterprise documents are weighted using attention weights to obtain the weighted feature vectors of the first-permission enterprise document and the weighted feature vectors of the other enterprise documents.

[0108] The weighted first-permission enterprise document feature vector is concatenated with the weighted feature vectors of other enterprise documents to obtain the concatenated permission enterprise document feature vector. The matching score between the concatenated permission enterprise document feature vector and the user feature vector is calculated using the softmax function.

[0109] This invention improves the accuracy of matching between enterprise users and authorized enterprise documents by using the attention weight, thereby enhancing the precision of document recommendations and improving the efficiency and accuracy of enterprise document queries.

[0110] In this embodiment of the invention, by fully combining the historical operation behavior data of enterprise users and the basic information of users, the system recommends the documents that users are most likely to need, thus narrowing the search scope. The system also displays the tag directory hierarchy of the recommended document set, making it easier and more intuitive for users to obtain documents, thereby improving the efficiency and accuracy of enterprise document search.

[0111] In this embodiment of the invention, when the enterprise user queries a document, the query scope can be narrowed based on the user's basic information, and documents that the user may need can be recommended based on the historical operation behavior data and job information. Employees do not need to search through the document directory layer by layer, and can quickly understand information such as document type, business category and source system.

[0112] This invention, through its embodiments, categorizes documents in a managed enterprise document set based on the enterprise's organizational structure information to obtain document organization information categories. It identifies the file type, business category, and source system of the documents in the managed enterprise document set. Based on the enterprise's organizational structure information, file type, business category, and source system, it designs document directory pages with different dimensions for the managed enterprise document set, allowing users to browse documents from multiple perspectives and find the most suitable viewing method for their needs. Users can intuitively understand the directory structure of the documents. Furthermore, it filters the managed enterprise document set based on the basic information and the document organization information categories to obtain the enterprise document set corresponding to the enterprise user's permissions, reducing the number of interfering documents and improving efficiency when querying enterprise documents. Finally, based on the historical operation behavior data and the basic information, it filters out recommended document sets from the authorized enterprise document sets, recommending documents that the user is most likely to need, narrowing the search scope, and displays the tag directory hierarchy of the recommended document sets, making it easier and more intuitive for users to obtain documents, thereby improving the efficiency and accuracy of enterprise document queries. Therefore, the enterprise document management method proposed in this invention can solve the problem of low efficiency and accuracy when financial companies search for enterprise documents.

[0113] like Figure 4 The diagram shown is a functional block diagram of an enterprise document management device provided in an embodiment of the present invention.

[0114] The enterprise document management device 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the enterprise document management device 100 may include a classification module 101, an identification module 102, a directory construction module 103, a document filtering module 104, and a recommendation module 105. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0115] In this embodiment, the functions of each module / unit are as follows:

[0116] The classification module 101 is used to obtain enterprise organizational structure information, classify documents in the enterprise document collection to be managed according to the enterprise organizational structure information, and obtain document organization information categories.

[0117] The identification module 102 is used to identify the file type, business category, and source system of the documents in the enterprise document set to be managed;

[0118] The directory construction module 103 is used to construct a tag directory hierarchy for the enterprise document set to be managed based on the enterprise organizational structure information, the file type, the business category, and the source system.

[0119] The document filtering module 104 is used to obtain basic information of enterprise users, filter the set of enterprise documents to be managed according to the basic information and the document organization information category, and obtain the set of enterprise documents with permissions corresponding to the enterprise users.

[0120] The recommendation module 105 is used to collect the historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, to filter out a recommended document set from the authorized enterprise document set and display the tag directory level of the recommended document set.

[0121] In detail, the modules in the enterprise document management device 100 described in this embodiment of the invention employ the same methods as described above during use. Figures 1 to 3 The same technical means are used in the enterprise document management method described in the article, and can produce the same technical effect, so they will not be repeated here.

[0122] like Figure 5 The diagram shown is a structural schematic of an electronic device for implementing an enterprise document management method according to an embodiment of the present invention.

[0123] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program, such as an enterprise document management program, stored in the memory 11 and capable of running on the processor 10.

[0124] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing enterprise document management programs) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0125] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of an enterprise document management program, but also to temporarily store data that has been output or will be output.

[0126] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0127] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0128] Figure 5 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 5The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0129] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0130] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0131] The enterprise document management program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0132] Obtain enterprise organizational structure information, and classify the documents in the enterprise document collection to be managed according to the enterprise organizational structure information to obtain document organization information categories;

[0133] Identify the file type, business category, and source system of the documents in the enterprise document collection to be managed;

[0134] Based on the enterprise organizational structure information, the file type, the business category, and the source system, construct a tag directory hierarchy for the enterprise document set to be managed;

[0135] Obtain basic information about enterprise users, and filter the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users;

[0136] Collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, filter out a recommended document set from the authorized enterprise document set, and display the tag directory level of the recommended document set.

[0137] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0138] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0139] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0140] Obtain enterprise organizational structure information, and classify the documents in the enterprise document collection to be managed according to the enterprise organizational structure information to obtain document organization information categories;

[0141] Identify the file type, business category, and source system of the documents in the enterprise document collection to be managed;

[0142] Based on the enterprise organizational structure information, the file type, the business category, and the source system, construct a tag directory hierarchy for the enterprise document set to be managed;

[0143] Obtain basic information about enterprise users, and filter the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users;

[0144] Collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, filter out a recommended document set from the authorized enterprise document set, and display the tag directory level of the recommended document set.

[0145] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0146] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0148] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0149] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0150] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0151] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0152] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for enterprise document management, characterized in that, The method includes: Obtain enterprise organizational structure information, and classify the documents in the enterprise document collection to be managed according to the enterprise organizational structure information to obtain document organization information categories; Identify the file type, business category, and source system of the documents in the enterprise document collection to be managed; Based on the enterprise organizational structure information, the file type, the business category, and the source system, construct a tag directory hierarchy for the enterprise document set to be managed; Obtain basic information about enterprise users, and filter the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the set of enterprise documents with permissions corresponding to the enterprise users; Collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, filter out a recommended document set from the authorized enterprise document set, and display the tag directory level of the recommended document set; The step of selecting a recommended document set from the authorized enterprise document set based on the historical operation behavior data and the basic information includes: Using the BERT model in the preset document recommendation model, the key behavioral features of the historical operation behavior data and the key job features of the basic information are extracted respectively. By using the fusion layer in the preset document recommendation model, the key behavioral features and the key job features are fused to obtain a user feature vector; Using the matching model in the preset document recommendation model, calculate the matching score between the user feature vector and the authorized enterprise document set; Authorized enterprise documents with matching scores higher than a preset threshold are selected as recommended documents, and all recommended documents are aggregated to obtain a recommended document set.

2. The enterprise document management method as described in claim 1, characterized in that, The step of calculating the matching score between the user feature vector and the authorized enterprise document set using the matching model in the preset document recommendation model includes: Extract the feature vectors of each document in the authorized enterprise document set to obtain the authorized enterprise document feature vector set; Randomly select a permission enterprise document feature vector from the set of permission enterprise document feature vectors as the first permission enterprise document feature vector, calculate the matching degree between the first permission enterprise document feature vector and the user feature vector, and obtain the matching degree matrix. The matching degree matrix is ​​normalized and weighted by row and column respectively to obtain the attention weights; The feature vector of the first-permission enterprise document and the feature vectors of all other-permission enterprise documents are weighted using attention weights to obtain the weighted feature vector of the first-permission enterprise document and the weighted feature vectors of all other-permission enterprise documents. The weighted first-permission enterprise document feature vector is concatenated with the weighted feature vectors of other enterprise documents to obtain the concatenated permission enterprise document feature vector. The matching score between the concatenated permission enterprise document feature vector and the user feature vector is calculated using the softmax function.

3. The enterprise document management method as described in claim 1, characterized in that, The step of filtering the set of enterprise documents to be managed based on the basic information and the document organization information category to obtain the permission-based enterprise document set corresponding to the enterprise user includes: Extract the job information and permission information from the basic information; Based on the permission information, select documents from the set of enterprise documents to be managed that match the permissions of the enterprise users, and use them as the first document set; Calculate the similarity between the job information and the document organization information category of the documents in the first document set; Documents corresponding to document organization information categories with similarity greater than a preset similarity threshold are selected from the first document set and used as the permission enterprise document set corresponding to the enterprise user.

4. The enterprise document management method as described in claim 1, characterized in that, The step of classifying documents in the managed enterprise document set according to the enterprise organizational structure information to obtain document organization information categories includes: Extract keywords from the documents in the enterprise document collection to be managed; The keywords are matched with the enterprise's organizational structure information to obtain the organizational information associated with the keywords, and the organizational information is used as the document organization information category of the document corresponding to the keywords.

5. The enterprise document management method as described in claim 1, characterized in that, The step of constructing a tag directory hierarchy for the enterprise document set to be managed based on the enterprise organizational structure information, the file type, the business category, and the source system includes: First, second, third, and fourth tag directory levels are constructed based on the enterprise organizational structure information, the file type, the business category, and the source system, respectively.

6. The enterprise document management method as described in claim 1, characterized in that, The identification of the business categories of documents in the enterprise document set to be managed includes: The documents in the document set of the enterprise to be managed are segmented into words to obtain a document word segmentation sequence; Extract the feature vectors of the word segmentation sequence to obtain the document word segmentation vector set; R document segmentation feature vectors are randomly selected from the document segmentation vector set as r initial cluster centroids; Calculate the distance between each document segmentation feature vector in the document segmentation vector set and the initial cluster centroid; Based on the magnitude of the distance, select the document word segmentation feature vectors corresponding to the distances as the k cluster centroids for clustering; Calculate the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k cluster centroids, and classify the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance; Calculate the average value of the document segmentation feature vectors in each class, update the k cluster centroids based on the average value, and return to the steps described above: calculating the Euclidean distance between each document segmentation feature vector in the document segmentation vector set and the k updated cluster centroids, and classifying the document segmentation feature vectors into the class of the cluster centroid with the shortest Euclidean distance until convergence is achieved, thus completing the classification of the enterprise document set to be managed and obtaining the business category of the documents in the enterprise document set to be managed.

7. An enterprise document management device, used to implement the enterprise document management method as described in any one of claims 1 to 6, characterized in that, The device includes: The classification module is used to obtain enterprise organizational structure information, classify the documents in the document collection of the enterprise to be managed according to the enterprise organizational structure information, and obtain the document organization information category. The identification module is used to identify the file type, business category, and source system of the documents in the enterprise document set to be managed; The directory building module is used to build a tag directory hierarchy for the enterprise document set to be managed based on the enterprise organizational structure information, the file type, the business category and the source system; The document filtering module is used to obtain basic information of enterprise users, filter the set of enterprise documents to be managed according to the basic information and the document organization information category, and obtain the set of enterprise documents with permissions corresponding to the enterprise users. The recommendation module is used to collect historical operation behavior data of the enterprise users, and based on the historical operation behavior data and the basic information, to filter out a recommended document set from the authorized enterprise document set and display the tag directory level of the recommended document set.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the enterprise document management method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the enterprise document management method as described in any one of claims 1 to 6.

Images