A method, system and storage medium for intelligent management of traditional Chinese medicine literature based on language processing technology

Abstract

The present invention discloses a method, system and storage medium for intelligent management of TCM documents based on language processing technology, which relates to the field of intelligent data management, including: collecting and extracting the basic data set of target TCM documents to a central processing unit; determining the pointing storage execution mode of the target TCM documents based on basic characteristic values; tracking and sensing the stored target TCM documents to obtain tracking and sensing data; the central processing unit receives the tracking and sensing data for processing and intelligent management. By compressing and storing the target TCM documents to different degrees based on the basic characteristic values ​​of the TCM documents, the use of storage space is reduced, thereby saving storage costs. For documents with higher data quality, the security and reliability of the data are improved through higher levels of compression and backup storage.

Description

Technical Field

[0001] The present invention relates to the field of intelligent data management, and in particular to an intelligent management method, system and storage medium for traditional Chinese medicine literature based on language processing technology. Background Art

[0002] With the continuous progress of traditional Chinese medicine, the relevant literature has also shown an explosive growth. Therefore, when storing and processing these literature data, adequate management is required to ensure the integrity and availability of traditional Chinese medicine literature.

[0003] Existing technologies, such as the invention patent with announcement number: CN110069516B, are a method for realizing intelligent management technology of service content based on standard documents, which specifically includes establishing basic standard data, establishing standard sub-platforms, pushing sub-platform standard data, collecting sub-platform standard documents, summarizing sub-platform data, and improving the main system standard basic data. By collecting, summarizing, classifying, sorting, storing, and calculating the sub-system standard document data, the main system is provided with standard document reference data, and the standard document data of the master and slave systems are uniformly managed and automatically updated, thereby reducing the system operation complexity, uniformly managing the master and slave systems, and improving the system management efficiency.

[0004] The prior art, such as the invention patent with announcement number: CN111488505B, is a document management method using an automated three-dimensional library, which specifically includes: scanning the electronic label of the first target document to obtain label information; based on the document management database and according to the label information, determining the library address of the first target document, and storing the first target document in the automated three-dimensional library corresponding to the library address; obtaining the second target document input by the target user, and determining the management information of the second target document based on the document management database; based on the management information, sorting out the second target document from the automated three-dimensional library, and based on the document management database, document circulation management of the second target document. Using the automated three-dimensional library to store and sort the target documents facilitates intelligent circulation management of the documents, thereby improving efficiency.

[0005] Based on the above scheme, it can be seen that for the storage of TCM literature, the existing technology often only collects and classifies it in a general way, while different documents have different characteristics and quality. Therefore, general collection and processing often cannot take into account the specific characteristics of each target TCM literature. Therefore, there are currently problems with the characteristic distinction and quality screening of TCM literature. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a method, system and storage medium for intelligent management of TCM literature based on language processing technology. To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for intelligent management of TCM literature based on language processing technology, comprising:

[0007] The TCM documents uploaded from the edge channel that need to be stored in the document library are collected and recorded as target TCM documents, and the basic data set of the target TCM documents is extracted and transmitted to the central processor.

[0008] The central processing unit receives the basic data set of the target TCM document for processing, obtains the basic characteristic value of the target TCM document, determines the designated storage execution mode of the target TCM document based on the basic characteristic value, and stores the target TCM document in the document library in the designated storage execution mode.

[0009] The stored target TCM document is tracked and sensed, and the tracking and sensing data corresponding to the stored target TCM document is obtained and transmitted to the central processing unit.

[0010] The central processing unit receives and processes the tracking perception data corresponding to the stored target TCM literature to obtain the tracking perception result.

[0011] As a preferred technical solution, the basic data set of the extracted target TCM literature is transmitted to the central processor, specifically including:

[0012] The target TCM literature is imported into the processor for identification, and the basic data set of the target TCM literature is extracted and transmitted to the central processing unit.

[0013] The basic data set of the target TCM literature includes the character length, average sentence length, total number of tables and figures, byte value and number of cited references of the target TCM literature.

[0014] As a preferred technical solution, the central processor receives the basic data set of the target TCM literature for processing to obtain the basic characteristic value of the target TCM literature. The specific process is:

[0015] Verification parameters are extracted from the database, wherein the verification parameters include a character length verification value, an average sentence length verification value, a total number of charts verification value, a byte verification value, and a cited reference number verification value.

[0016] Based on the basic data set of the target TCM literature and the verification parameters, the basic characteristic values ​​of the target TCM literature are obtained through comprehensive processing. The specific conditions are:

[0017] in, is the basic characteristic value of the target TCM literature, is the character length of the target TCM literature, is the average sentence length of the target TCM literature, is the total number of tables and figures in the target TCM literature, is the byte value of the target TCM literature, is the number of cited references of the target TCM literature, Validates the value for character length, is the average sentence length verification value, Validate the value for the chart total, is the byte verification value, is the verification value of the number of cited references, is the character length weight factor, is the average sentence length weight factor, is the weight factor for the total number of graphs, is the byte value weight factor, is the weight factor of the number of cited references.

[0018] As a preferred technical solution, the designated storage execution method of determining the target TCM literature based on the basic characteristic value specifically includes:

[0019] Based on the basic feature value of the target TCM document and the basic feature threshold extracted from the database, when the basic feature value of the target TCM document is less than or equal to the basic feature threshold, the designated storage execution mode of the target TCM document is determined to be local storage.

[0020] When the basic feature value of the target TCM document is greater than the basic feature threshold, the designated storage execution mode of the target TCM document is determined as local storage and backup storage, thereby determining the designated storage execution mode of the target TCM document.

[0021] As a preferred technical solution, determining the designated storage execution mode of the target TCM literature also includes:

[0022] When the designated storage execution mode of the target TCM document is local storage and backup storage, the difference between the basic feature value of the target TCM document and the basic feature threshold is extracted and recorded as the backup compression benchmark value of the target TCM document.

[0023] According to the backup compression benchmark value of the target traditional Chinese medicine document and based on the execution compression ratios corresponding to the various backup compression benchmark value intervals stored in the database, the execution compression ratio corresponding to the interval in which the backup compression benchmark value of the target traditional Chinese medicine document is located is mapped and extracted, recorded as the designated execution compression ratio, and the target traditional Chinese medicine document is compressed with the designated execution compression ratio and stored in the backup location.

[0024] As a preferred technical solution, the tracking and sensing of the stored target TCM literature is performed to obtain the tracking and sensing data corresponding to the stored target TCM literature and transmit it to the central processor, specifically including:

[0025] The stored target TCM document is tracked and sensed to obtain tracking and sensing data corresponding to the stored target TCM document, wherein the tracking and sensing data includes the number of error characters, the current byte value, the number of metadata item losses, and the access and reading frequency.

[0026] The tracking perception data corresponding to the stored target TCM literature is transmitted to the central processing unit.

[0027] As a preferred technical solution, the central processor receives the stored tracking perception data corresponding to the target TCM literature and processes it to obtain the tracking perception results for intelligent management, specifically including:

[0028] Based on the tracking perception data of the target traditional Chinese medicine literature, a tracking perception data verification set is extracted from the database, and the tracking perception data verification set specifically includes: an error character number verification value, a metadata item missing number verification value, an access and reading frequency verification value, and a current byte value verification value.

[0029] The tracking perception data of the target TCM document and the tracking perception data verification set of the target TCM document are processed and analyzed to obtain the tracking perception damaged verification value corresponding to the stored target TCM document, and the damaged threshold is extracted from the database for comparison. If the tracking perception damaged verification value corresponding to the stored target TCM document is less than or equal to the damaged threshold, the stored target TCM document is determined to be in a lossless storage state, and the file repair process is not performed.

[0030] If the tracking perception damage check value corresponding to the stored target TCM document is greater than the damage threshold, the stored target TCM document is determined to be in a lossy storage state, and the current target TCM document is recorded as a document requiring repair.

[0031] The difference between the trace perception damaged check value and the damaged threshold of the demand repair document is extracted and recorded as the damaged benchmark feature value.

[0032] The damaged baseline characteristic value of the demand repair document is compared with the damaged processing cutoff value extracted from the database. When the damaged baseline characteristic value is less than or equal to the damaged processing cutoff value, it is determined that the demand repair document needs to be automatically repaired, and the demand repair document is automatically repaired.

[0033] When the damaged baseline characteristic value of the document requiring repair is greater than the damaged processing cutoff value, it is determined that the document requiring repair needs to be manually repaired, and a repair prompt signal is transmitted to the management terminal for prompting.

[0034] As a preferred technical solution, it also includes sensing the search request signal uploaded by the user on the edge channel, collecting the user's search keywords, and synchronously performing intelligent recommendation processing of traditional Chinese medicine literature for the user. The specific process is:

[0035] Based on the index tag keywords of each existing TCM document in the document library and according to the user's search keywords, a number of existing TCM documents that match the user's search keywords are screened and recorded as pre-recommended documents.

[0036] The number of citations, average daily page views, average visit time per person and publication time of each pre-recommended document are counted, and processed to obtain the recommendation priority of each pre-recommended document.

[0037] The recommendation priorities of the pre-recommended documents are arranged in descending order to obtain the recommended display order of the pre-recommended documents, and intelligent recommendation and display processing of traditional Chinese medicine documents is performed for users.

[0038] In addition, a Chinese medicine literature intelligent system based on language processing technology is also provided, including:

[0039] The document collection module is used to collect TCM documents uploaded from the edge channel that need to be stored in the document library, record them as target TCM documents, and extract the basic data set of the target TCM documents and transmit them to the central processor.

[0040] In the document processing module, the central processing unit receives the basic data set of the target TCM document for processing, obtains the basic characteristic value of the target TCM document, and determines the designated storage execution mode of the target TCM document based on the basic characteristic value.

[0041] The document sensing module is used to track and sense the stored target TCM document, and obtain the tracking and sensing data corresponding to the stored target TCM document and transmit it to the central processor.

[0042] The document management module is used for the central processor to receive and process the tracking perception data corresponding to the target traditional Chinese medicine document after storage, and obtain the tracking perception results for intelligent management.

[0043] A storage medium is also provided, comprising: the storage medium stores one or more programs, and the one or more programs are executed by one or more processors to implement the method described above.

[0044] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0045] (1) The present invention provides an intelligent management method for TCM literature based on language processing technology. By distinguishing the basic characteristic values ​​of TCM literature, target TCM literature is stored in different forms instead of directly classified storage, which can reduce the use of storage space and thus save storage costs. For documents with higher data quality, higher levels of compression and backup storage are used to improve data security and reliability.

[0046] (2) The present invention screens and prioritizes the content quality of target TCM literature. When a user makes a query, TCM literature with relatively high content quality is presented to the user first, thereby optimizing resource allocation, enhancing user experience, and strengthening retrieval effects.

[0047] (3) The present invention performs quality inspection on the stored target TCM documents, and determines whether the TCM documents to be repaired need to be repaired automatically or manually according to the degree of damage. The target TCM documents with less damage are automatically repaired, which frees up the energy of manual repair and allows it to focus on repairing the target TCM documents with more damage, thereby improving the overall efficiency.

[0048] Of course, any product implementing the present invention does not necessarily need to achieve all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The present invention is a flow chart of a method for intelligent management of traditional Chinese medicine literature based on language processing technology.

[0050] Figure 2 This is an example diagram of basic characteristic value scatter points of the target traditional Chinese medicine literature involved in the embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In the description of the present invention, it should be understood that terms such as "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or position relationship are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0053] See also Figure 1 As shown, the embodiment of the present invention provides a method for intelligent management of traditional Chinese medicine literature based on language processing technology, which specifically includes:

[0054] The TCM documents uploaded from the edge channel that need to be stored in the document library are collected and recorded as target TCM documents, and the basic data set of the target TCM documents is extracted and transmitted to the central processor.

[0055] The edge channel refers to the channel for data transmission and processing.

[0056] The document library refers to a database used to store target traditional Chinese medicine documents in the embodiment of the present invention.

[0057] The central processing unit in the embodiment of the present invention is used to analyze and process the basic characteristic values ​​of the target traditional Chinese medicine literature and track the perception data.

[0058] The step of extracting the basic data set of the target TCM literature and transmitting it to the central processor specifically includes: importing the target TCM literature into the processor for identification, extracting the basic data set of the target TCM literature, and transmitting it to the central processor.

[0059] The processor is used to identify the basic data set of the target traditional Chinese medicine literature using ASCII text encoding;

[0060] The basic data set of the target TCM literature includes the character length, average sentence length, total number of tables and figures, byte value and number of cited references of the target TCM literature.

[0061] The character length can reflect the level of detail of the document; a longer character length usually means that the document contains more detailed information.

[0062] The average sentence length can reflect the complexity of the expression of the document. A longer average sentence length usually means that the document uses a complex sentence structure.

[0063] Charts are an important way to express data and concepts in TCM literature. The total number of charts can reflect the intuitive information content of the literature. The use of charts can enhance the efficiency and understanding of information transmission. A high number of charts usually means that the literature data is richer and the information density is higher.

[0064] Byte value is usually related to character length, but focuses more on the overall size of the file. Byte value can be used to evaluate the technical quality of the document.

[0065] The number of cited references can reflect the academic value of the document.

[0066] The central processing unit receives and processes the basic data set of the target TCM document, obtains the basic characteristic value of the target TCM document, determines the designated storage execution mode of the target TCM document based on the basic characteristic value, and stores the target TCM document in the document library in the designated storage execution mode;

[0067] The central processor receives the basic data set of the target TCM literature for processing to obtain the basic characteristic value of the target TCM literature. The specific process is as follows:

[0068] Extracting verification parameters from a database, the verification parameters including a character length verification value, an average sentence length verification value, a total number of charts verification value, a byte verification value, and a number of cited references verification value;

[0069] The verification parameter is used as a verification reference value of the basic data set of the target TCM literature. When the basic data set of the target TCM literature is larger relative to the corresponding verification parameter, the basic characteristic value of the target TCM literature is higher.

[0070] Based on the basic data set of the target TCM literature and the verification parameters, the basic characteristic values ​​of the target TCM literature are obtained through comprehensive processing. The specific conditions are:

[0071] in, is the basic characteristic value of the target TCM literature, is the character length of the target TCM literature, is the average sentence length of the target TCM literature, is the total number of tables and figures in the target TCM literature, is the byte value of the target TCM literature, is the number of cited references of the target TCM literature, Validates the value for character length, is the average sentence length verification value, Validate the value for the chart total, is the byte verification value, is the verification value of the number of cited references, is the character length weight factor, is the average sentence length weight factor, is the weight factor for the total number of graphs, is the byte value weight factor, is the weight factor of the number of cited references.

[0072] It should be noted that the character length weight factor, average sentence length weight factor, total number of charts weight factor, byte value weight factor and number of cited references weight factor all have a value range between 0 and 1 and meet the following conditions: The character length weight factor is an impact factor corresponding to the basic characteristic value of the target TCM literature preset in the database, which indicates the numerical value of the influence of the character length on the basic characteristic value of the target TCM literature. When used, the character length weight factor can be directly obtained from the database, and its corresponding relationship is a pre-set mapping relationship. For example, the basic characteristic value of the target TCM literature and the character length weight factor corresponding to the character length form a mapping set, and the real-time character length is input into the mapping set to obtain the character length weight factor, in which the mapping relationship is one-to-one correspondence; the average sentence length weight factor is an impact factor corresponding to the basic characteristic value of the target TCM literature preset in the database, which indicates the average sentence length on the target TCM literature. The numerical value of the influence degree of the basic characteristic value of the medical literature can be directly obtained from the database when used, and the corresponding relationship is a pre-set mapping relationship. For example: the basic characteristic value of the target Chinese medicine literature and the average sentence length corresponding to the average sentence length form a mapping set, and the real-time average sentence length is input into the mapping set to obtain the average sentence length weight factor, in which the mapping relationship is one-to-one correspondence; the weight factor of the total number of charts is the influence factor corresponding to the basic characteristic value of the target Chinese medicine literature preset in the database, which indicates the numerical value of the influence degree of the total number of charts on the basic characteristic value of the target Chinese medicine literature. When used, the weight factor of the total number of charts can be directly obtained from the database, and the corresponding relationship is a pre-set mapping relationship. The mapping relationship set in advance, for example: the basic characteristic value of the target TCM literature and the total number of charts corresponding to the weight factor of the total number of charts form a mapping set, and the total number of real-time charts is input into the mapping set to obtain the weight factor of the total number of charts, wherein the mapping relationship is one-to-one correspondence; the byte value weight factor is the influence factor corresponding to the basic characteristic value of the target TCM literature preset in the database, which represents the numerical value of the influence degree of the byte value on the basic characteristic value of the target TCM literature. When used, the byte value weight factor can be directly obtained from the database, and its corresponding relationship is a pre-set mapping relationship, for example: the basic characteristic value of the target TCM literature and the byte value weight factor corresponding to the byte value form a mapping set, and the real-time byte value is input into the mapping set to obtain the weight factor of the total number of charts, wherein the mapping relationship is one-to-one correspondence; the byte value weight factor is the influence factor corresponding to the basic characteristic value of the target TCM literature preset in the database, which represents the numerical value of the influence degree of the byte value on the basic characteristic value of the target TCM literature. When used, the byte value weight factor can be directly obtained from the database, and its corresponding relationship is a pre-set mapping relationship. The byte value weight factor is obtained by inputting the mapping set, and the mapping relationship is one-to-one; the weight factor of the number of cited references is the impact factor corresponding to the basic characteristic value of the target Chinese medicine document preset in the database, which represents the numerical value of the influence of the number of cited references on the basic characteristic value of the target Chinese medicine document. When used, the weight factor of the number of cited references can be directly obtained from the database, and its corresponding relationship is a pre-set mapping relationship. For example: the basic characteristic value of the target Chinese medicine document and the weight factor of the number of cited references corresponding to the number of cited references form a mapping set, and the real-time number of cited references is input into the mapping set to obtain the weight factor of the number of cited references, and the mapping relationship is one-to-one.

[0073] It should also be noted that this embodiment analyzes the basic characteristic values ​​of the target traditional Chinese medicine literature, and there is a certain correlation between the parameters involved. For example, the character length and the average sentence length are directly related. The character length is the total number of characters in the entire document, and the average sentence length is the average length of all sentences in the document. If the total number of characters in the document is very high, but the number of sentences is relatively small, then the average sentence length will usually be longer. On the contrary, if the total number of characters in the document is low, but the number of sentences is large, the average sentence length will be shorter. The character length and the byte value are usually positively correlated. The longer the character length, the larger the byte value.

[0074] like Figure 2 What is shown is a scatter plot example of the basic characteristic values ​​of the target TCM literature involved in the embodiment of the present invention. The example plot shows ten groups of different basic characteristic values ​​of the target TCM literature. In this embodiment, the horizontal axis is the instance number of the target TCM literature, and the vertical axis is the basic characteristic value of the target TCM literature. By simultaneously processing the basic data set of the target TCM literature including the character length, average sentence length, total number of charts, byte value and number of cited references of the target TCM literature, it is ensured that the basic characteristic values ​​of the target TCM literature comprehensively characterize the characteristic parameter level of the target TCM literature. In actual use, the target TCM literature with low basic characteristic values ​​may have document data errors or low data quality. Therefore, it is necessary to distinguish and process the basic characteristic values ​​of the target TCM literature, and to store the target TCM literature with high basic characteristic values ​​in a more precise and secure manner.

[0075] The method of determining the designated storage execution mode of the target TCM literature based on the basic characteristic value specifically includes:

[0076] Based on the basic feature value of the target TCM document and the basic feature threshold extracted from the database, when the basic feature value of the target TCM document is less than or equal to the basic feature threshold, the designated storage execution mode of the target TCM document is determined to be local storage.

[0077] When the basic feature value of the target TCM document is greater than the basic feature threshold, the designated storage execution mode of the target TCM document is determined as local storage and backup storage, thereby determining the designated storage execution mode of the target TCM document.

[0078] It should be noted that, for target TCM documents whose designated storage executors are local storage and backup storage, local storage and backup storage can improve data security and prevent accidental deletion. For example, if data is accidentally deleted locally, it can be restored from the backup.

[0079] Determining the designated storage execution mode of the target TCM literature also includes:

[0080] When the designated storage execution mode of the target TCM document is local storage and backup storage, the difference between the basic feature value of the target TCM document and the basic feature threshold is extracted and recorded as the backup compression benchmark value of the target TCM document.

[0081] According to the backup compression benchmark value of the target traditional Chinese medicine document, and based on the execution compression ratios corresponding to each backup compression benchmark value interval stored in the database, the execution compression ratio corresponding to the backup compression benchmark value of the target traditional Chinese medicine document is mapped and extracted, recorded as the specified execution compression ratio, and the target traditional Chinese medicine document is compressed with the specified execution compression ratio and stored in the backup location.

[0082] By distinguishing basic characteristic values ​​from thresholds, the present invention can ensure that documents with higher value receive additional backup protection, thereby reducing the risk of data loss. By calculating a backup compression baseline value, the compression ratio can be adjusted according to the importance and storage requirements of the document, balancing the requirements for storage space and data recovery speed. When data recovery is required, the document can be quickly located and recovered according to different compression ratios, thereby improving the efficiency of data management.

[0083] The stored target TCM document is tracked and sensed, and the tracking and sensing data corresponding to the stored target TCM document is obtained and transmitted to the central processing unit.

[0084] The tracking and sensing of the stored target TCM literature to obtain the tracking and sensing data corresponding to the stored target TCM literature and transmit it to the central processor specifically includes:

[0085] An automated verification script is used to track and sense the stored target TCM literature to obtain tracking and sensing data, which includes the number of erroneous characters, the current byte value, the number of metadata item losses, and the access and retrieval frequency.

[0086] Transmits tracking perception data to the central processor.

[0087] The number of error characters refers to the number of unexpected characters detected in a text file. The more error characters there are, the lower the quality of the text file. This usually indicates that the file has been damaged during transmission, storage or processing, resulting in damaged data integrity. The unexpected or garbled characters can be measured using the ASCII text encoding mentioned above.

[0088] The current byte value refers to the specific numerical value of the byte in the target TCM literature after storage.

[0089] The number of lost metadata items refers to the amount of metadata lost during file storage or transmission, which is obtained using the property viewing function built into the operating system. Metadata is very important for understanding the context and source of files. The more metadata items are lost, the lower the overall quality and usability of the file. For example, metadata items include title, author, creation date, modification date, and file type.

[0090] The access frequency refers to the number of times a file is read. A high access frequency may cause damage to the file during the reading process.

[0091] The central processing unit receives and processes the tracking perception data corresponding to the stored target TCM literature, and obtains the tracking perception results for intelligent management.

[0092] The central processor receives the stored tracking perception data corresponding to the target TCM literature and processes it to obtain the tracking perception results for intelligent management, specifically including:

[0093] Based on the tracking perception data of the target TCM literature, the tracking perception damage check value corresponding to the stored target TCM literature is analyzed. The specific processing method is as follows:

[0094] A tracking perception data check set is extracted from the database, wherein the tracking perception data check set specifically includes: an error character number check value, a current byte value check value, a metadata item loss number check value, and an access frequency check value.

[0095] The tracking perception data verification set is used as a verification benchmark value for the tracking perception data of the target TCM document. The larger the tracking perception data of the target TCM document is relative to the corresponding tracking perception data verification set, the higher the tracking perception damage verification value of the target TCM document.

[0096] The tracking perception data of the target TCM literature and the tracking perception data verification set are processed and analyzed to obtain the tracking perception damage verification value corresponding to the stored target TCM literature, and the damage threshold is extracted from the database for comparison processing. Among them, the tracking perception damage verification value corresponding to the stored target TCM literature is specifically processed as follows:

[0097]

[0098] in, is the tracking perception damage check value corresponding to the stored target TCM document, is the current byte value of the target TCM document after storage, is the number of error characters in the target TCM literature after storage, is the number of metadata items lost in the target TCM literature after storage, The access frequency of the stored target TCM literature. is the byte value of the target TCM document before storage, is the current byte value check value, is the error character count check value, The missing check value for the metadata item. To access the frequency check value, is the current byte value weight factor, is the weight factor of the number of wrong characters, is the weight factor for the number of metadata item losses, It is the weight factor of access frequency.

[0099] It should be noted that the current byte value weight factor, the error character number weight factor, the metadata item loss real number weight factor and the access frequency weight factor all have a value range between 0 and 1 and meet The current byte value weight factor is an influence factor corresponding to the tracking perception damaged check value corresponding to the stored target TCM document preset in the database, which indicates the numerical value of the influence degree of the current byte value on the tracking perception damaged check value corresponding to the stored target TCM document. When used, the current byte value weight factor can be directly obtained from the database, and its corresponding relationship is a preset mapping relationship. For example: the tracking perception damaged check value corresponding to the stored target TCM document and the current byte value weight factor corresponding to the current byte value form a mapping set, and the real-time current byte value is input into the mapping set to obtain the current byte value weight factor, in which the mapping relationship is one-to-one correspondence; error character The number weight factor is an impact factor corresponding to the tracking perception damage check value corresponding to the stored target TCM document preset in the database, which represents the numerical value of the influence of the number of error characters on the tracking perception damage check value corresponding to the stored target TCM document. When used, the error character number weight factor can be directly obtained from the database, and its corresponding relationship is a preset mapping relationship. For example: the tracking perception damage check value corresponding to the stored target TCM document and the error character number weight factor corresponding to the error character number form a mapping set, and the real-time error character number is input into the mapping set to obtain the error character number weight factor, wherein the mapping relationship is one-to-one correspondence; the metadata item loss real number weight factor The sub is the impact factor corresponding to the tracking perception damage check value corresponding to the stored target TCM document preset in the database, which represents the numerical value of the influence of the metadata item loss number on the tracking perception damage check value corresponding to the stored target TCM document. When used, the metadata item loss number weight factor can be directly obtained from the database, and the corresponding relationship is a preset mapping relationship. For example: the tracking perception damage check value corresponding to the stored target TCM document and the metadata item loss number weight factor corresponding to the metadata item loss number form a mapping set, and the real-time metadata item loss number is input into the mapping set to obtain the metadata item loss number weight factor, wherein the mapping relationship is one-to-one correspondence; access The access frequency weight factor is an impact factor corresponding to the tracking perception damage verification value corresponding to the stored target TCM document preset in the database, which represents the numerical value of the influence of the access frequency on the tracking perception damage verification value corresponding to the stored target TCM document. The access frequency weight factor can be directly obtained from the database when used, and the corresponding relationship is a pre-set mapping relationship. For example: the tracking perception damage verification value corresponding to the stored target TCM document and the access frequency weight factor corresponding to the access frequency form a mapping set, and the real-time access frequency is input into the mapping set to obtain the access frequency weight factor, and the mapping relationship is one-to-one.

[0100] If the tracking perception damage check value corresponding to the stored target TCM document is less than or equal to the damage threshold, the stored target TCM document is determined to be in a lossless storage state, and the file repair process is not performed.

[0101] If the tracking perception damage check value corresponding to the stored target TCM document is greater than the damage threshold, the stored target TCM document is determined to be in a lossy storage state, and the current target TCM document is recorded as a document requiring repair.

[0102] The difference between the trace perception damaged check value and the damaged threshold of the demand repair document is extracted and recorded as the damaged benchmark feature value.

[0103] The damaged baseline characteristic value of the demand repair document is compared with the damaged processing cutoff value extracted from the database. When the damaged baseline characteristic value is less than or equal to the damaged processing cutoff value, it is determined that the demand repair document needs to be automatically repaired, and the demand repair document is automatically repaired.

[0104] The automatic repair process includes using the text editor Sublime Text and assisting with the professional text repair tool TextFixer to repair the required repair document according to a preset procedure;

[0105] When the damaged baseline characteristic value of the document requiring repair is greater than the damaged processing cutoff value, it is determined that the document requiring repair needs to be manually repaired, and a repair prompt signal is transmitted to the management terminal for prompting.

[0106] It should be noted that the present invention performs quality inspection on the stored target TCM documents, and determines the TCM documents to be repaired in two forms: automatic repair and manual repair according to the degree of damage. The target TCM documents with less damage are automatically repaired, which frees up the energy of manual repair and allows it to focus on repairing the target TCM documents with more damage, thereby improving the overall efficiency.

[0107] The transmission of the repair prompt signal to the management terminal for prompting, in the embodiment of the present invention, means that the central processor covers the "manual repair required" label on the document to be repaired, and transmits the "repair required" signal to the management terminal, waiting for manual repair processing by the staff.

[0108] In this embodiment, the present invention also provides a method for intelligent management of TCM literature based on language processing technology, which also includes sensing the search request signal uploaded by the user on the edge channel, collecting the user's search keywords, and synchronously performing intelligent recommendation processing of TCM literature for the user. The specific process is:

[0109] Based on the index tag keywords of each existing TCM document in the document library and according to the user's search keywords, a number of existing TCM documents that match the user's search keywords are screened and recorded as pre-recommended documents.

[0110] In the embodiment of the present invention, the index tag keywords of the existing traditional Chinese medicine documents include the traditional Chinese medicine name index tag keywords, disease type index tag keywords and treatment method index tag keywords pre-stored in the database.

[0111] For example, the keywords of the Chinese medicine name index tag include "angelica", "tangerine peel", etc., the keywords of the disease type index tag include "qi deficiency", "liver depression", etc., and the keywords of the treatment method index tag include "acupuncture", "cupping", etc.

[0112] The number of citations, average daily page views, average visit time per person and publication time of each pre-recommended document are counted, and processed to obtain the recommendation priority of each pre-recommended document.

[0113] The number of citations reflects the academic influence and contribution of the document. Documents with a large number of citations are usually of higher quality and have innovative or in-depth content.

[0114] The average daily page views reflect the popularity of the document and user attention. Documents with a high average daily page views are more in line with user needs or have higher appeal.

[0115] The average visit time per person reflects the user's level of involvement and interest in the document. Documents with longer average visit time per person usually provide richer information or more in-depth analysis.

[0116] The length of publication reflects the novelty and timeliness of the literature. Newer literature receives more attention and citations due to the novelty of its content.

[0117] It should be noted that the average daily browsing times and average visit duration of each pre-recommended document are obtained by counting the document library access data in the intelligent system of traditional Chinese medicine documents based on language processing technology involved in the embodiment of the present invention.

[0118] The number of citations and publication time of each pre-recommended document are obtained as basic information during the literature collection stage.

[0119] The number of citations, average daily browsing times, average visit time per person and publication time of each pre-recommended document are analyzed and processed to obtain the recommendation priority of each pre-recommended document, including:

[0120]

[0121] in, For the The recommendation priority of the pre-recommended literature, For the The number of citations of the pre-recommended literature, For the The average daily number of views of the recommended documents, For the Average visit time per person for each recommended document. For the The publication time of the pre-recommended literature, is the number of the pre-recommended document, , is the total number of pre-recommended documents, is the citation weight factor, is the weight factor of the average number of daily views, is the weight factor of average visit duration per person, It is the publication time weight factor. It should be noted that, in the embodiment of the present invention, in order to prevent the extreme situation that the daily average browsing number appears negative because the number of times the user cancels or hides the browsing history is greater than the actual browsing number, an operation to eliminate negative numbers is performed. For example, a user browses a pre-recommended document 5 times on a certain day, chooses to hide the browsing history before reading, and applies to cancel the browsing history after browsing. Then, the daily browsing number left by the user for the pre-recommended document is -5 times. Similar data processing methods are also set in web pages such as Medium and The New York Times to eliminate errors caused by users canceling or hiding browsing history.

[0122] It should be noted that the weight factor of the number of citations, the weight factor of the average number of daily views, the weight factor of the average visit time per person and the weight factor of the publication time are all within the range of 0 to 1 and meet the requirements of , the citation count weight factor is the impact factor corresponding to the recommendation priority of each pre-recommended document preset in the database, indicating the numerical value of the influence of the citation count on the recommendation priority of each pre-recommended document. When used, the citation count weight factor can be directly obtained from the database, and the corresponding relationship is a preset mapping relationship. For example, the recommendation priority of each pre-recommended document and the citation count weight factor corresponding to the citation count form a mapping set, and the real-time citation count is input into the mapping set to obtain the citation count weight factor, in which the mapping relationship is one-to-one correspondence; the average daily browsing count weight factor is the impact factor corresponding to the recommendation priority of each pre-recommended document preset in the database, indicating the numerical value of the influence of the average daily browsing count on the recommendation priority of each pre-recommended document. When used, the average daily browsing count weight factor can be directly obtained from the database, and the corresponding relationship is a preset mapping relationship. For example, the recommendation priority of each pre-recommended document and the average daily browsing count weight factor corresponding to the average daily browsing count form a mapping set, and the real-time average daily browsing count is input into the mapping set to obtain the average daily browsing count weight factor, in which the mapping relationship is one-to-one correspondence; people The average access time weight factor is an impact factor of the average access time weight factor corresponding to the recommendation priority of each pre-recommended document preset in the database, which indicates the numerical value of the influence of the average access time on the recommendation priority of each pre-recommended document. The average access time weight factor can be directly obtained from the database when used, and the corresponding relationship is a preset mapping relationship. For example, the recommendation priority of each pre-recommended document and the average access time weight factor corresponding to the average access time form a mapping set, and the real-time average access time is input into the mapping set to obtain the average access time weight factor, and the mapping relationship is one-to-one correspondence; the publication time weight factor is an impact factor corresponding to the recommendation priority of each pre-recommended document preset in the database, which indicates the numerical value of the influence of the publication time on the recommendation priority of each pre-recommended document. The publication time weight factor can be directly obtained from the database when used, and the corresponding relationship is a preset mapping relationship. For example, the recommendation priority of each pre-recommended document and the publication time weight factor corresponding to the publication time form a mapping set, and the real-time publication time is input into the mapping set to obtain the publication time weight factor, and the mapping relationship is one-to-one correspondence.

[0123] It should also be noted that there is a certain correlation between the number of citations, average daily browsing times, average visit time per person and publication time of each pre-recommended document. Generally, there is a positive correlation between the number of citations, average daily browsing times and average visit time per person. If a document has a large number of citations, it will usually have a higher average daily browsing times and average visit time per person. The publication time will also affect the number of citations, average daily browsing times and average visit time per person. Documents with shorter publication times will receive more attention due to the timeliness and novelty of their content.

[0124] The recommendation priorities of the pre-recommended documents are arranged in descending order to obtain the recommended display order of the pre-recommended documents, and intelligent recommendation and display processing of traditional Chinese medicine documents is performed for users.

[0125] The present invention screens and prioritizes the content quality of target TCM documents, and when a user makes a query, TCM documents with relatively high content quality are presented to the user first, thereby optimizing resource allocation, enhancing user experience, and strengthening retrieval effects.

[0126] In this embodiment, the present invention further provides a TCM literature intelligent system based on language processing technology, comprising:

[0127] The document collection module is used to collect TCM documents uploaded from the edge channel that need to be stored in the document library, record them as target TCM documents, and extract the basic data set of the target TCM documents and transmit them to the central processor;

[0128] The document processing module, the central processing unit receives the basic data set of the target TCM document for processing, obtains the basic characteristic value of the target TCM document, and determines the designated storage execution mode of the target TCM document based on the basic characteristic value;

[0129] The document sensing module is used to track and sense the stored target TCM document, and obtain the tracking and sensing data corresponding to the stored target TCM document and transmit it to the central processor;

[0130] The document management module is used for the central processor to receive and process the tracking perception data corresponding to the target traditional Chinese medicine document after storage, and obtain the tracking perception results for intelligent management.

[0131] In another embodiment, the intelligent system for Chinese medicine literature based on language processing technology further includes:

[0132] The user interaction module is used to help users browse and download the retrieved Chinese medicine literature.

[0133] Personalized recommendation module, the system collects the user's historical search keywords, and sorts each historical search keyword from high to low according to the number of searches, to obtain the recommended display order of each historical search keyword. When the user searches, it is displayed and recommended as a recommended keyword ranking list.

[0134] In this embodiment, the present invention further provides a storage medium, including: the storage medium stores one or more programs, and the one or more programs are executed by one or more processors to implement the above-mentioned method.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0136] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A method for intelligent management of traditional Chinese medicine literature based on language processing technology, characterized in that: include: Collect the TCM documents uploaded from the edge channel that need to be stored in the document library, record them as target TCM documents, and extract the basic data set of the target TCM documents and transmit them to the central processor; The central processing unit receives and processes the basic data set of the target TCM document, obtains the basic characteristic value of the target TCM document, determines the designated storage execution mode of the target TCM document based on the basic characteristic value, and stores the target TCM document in the document library in the designated storage execution mode; The central processor receives the basic data set of the target TCM literature for processing to obtain the basic characteristic value of the target TCM literature. The specific process is as follows: Extracting verification parameters from a database, the verification parameters including a character length verification value, an average sentence length verification value, a total number of charts verification value, a byte verification value, and a number of cited references verification value; Tracking and sensing the stored target TCM literature, and obtaining tracking and sensing data corresponding to the stored target TCM literature and transmitting it to the central processor; The central processing unit receives and processes the tracking perception data corresponding to the stored target TCM literature to obtain the tracking perception results; The basic data set based on the target TCM literature and the verification parameters are comprehensively processed to obtain the basic characteristic values ​​of the target TCM literature. The specific conditions are: Among them, A is the basic feature value of the target TCM literature, E is the character length of the target TCM literature, is the average sentence length of the target TCM literature, P is the total number of tables and figures in the target TCM literature, b is the byte value of the target TCM literature, T is the number of cited references in the target TCM literature, Validates the value for character length, is the average sentence length verification value, Validate the value for the chart total, is the byte verification value, is the verification value of the number of cited references, is the character length weight factor, is the average sentence length weight factor, is the weight factor for the total number of graphs, is the byte value weight factor, is the weight factor of the number of cited references.

2. According to claim 1, a method for intelligent management of traditional Chinese medicine literature based on language processing technology is characterized by: The step of extracting the basic data set of the target TCM literature and transmitting it to the central processing unit specifically includes: Importing the target TCM literature into the processor for identification, extracting the basic data set of the target TCM literature, and transmitting it to the central processor; The basic data set of the target TCM literature includes the character length, average sentence length, total number of tables and figures, byte value and number of cited references of the target TCM literature.

3. According to claim 1, a method for intelligent management of traditional Chinese medicine literature based on language processing technology is characterized by: The method of determining the designated storage execution mode of the target TCM literature based on the basic characteristic value specifically includes: Based on the basic feature value of the target TCM document and the basic feature threshold extracted from the database, when the basic feature value of the target TCM document is less than or equal to the basic feature threshold, the designated storage execution mode of the target TCM document is determined to be local storage; When the basic feature value of the target TCM document is greater than the basic feature threshold, the designated storage execution mode of the target TCM document is determined as local storage and backup storage, thereby determining the designated storage execution mode of the target TCM document.

4. According to claim 3, a method for intelligent management of TCM literature based on language processing technology is characterized by: Determining the designated storage execution mode of the target TCM literature also includes: When the designated storage execution mode of the target TCM document is local storage and backup storage, the difference between the basic feature value of the target TCM document and the basic feature threshold is extracted and recorded as the backup compression benchmark value of the target TCM document; According to the backup compression benchmark value of the target traditional Chinese medicine document and based on the execution compression ratios corresponding to the various backup compression benchmark value intervals stored in the database, the execution compression ratio corresponding to the interval in which the backup compression benchmark value of the target traditional Chinese medicine document is located is mapped and extracted, recorded as the designated execution compression ratio, and the target traditional Chinese medicine document is compressed with the designated execution compression ratio and stored in the backup location.

5. According to claim 1, a method for intelligent management of traditional Chinese medicine literature based on language processing technology is characterized by: The tracking and sensing of the stored target TCM literature to obtain the tracking and sensing data corresponding to the stored target TCM literature and transmit it to the central processor specifically includes: Tracking and sensing the stored target TCM document to obtain tracking and sensing data corresponding to the stored target TCM document, wherein the tracking and sensing data includes the number of error characters, the current byte value, the number of metadata item losses, and the access and reading frequency; The tracking perception data corresponding to the stored target TCM literature is transmitted to the central processing unit.

6. According to claim 5, a method for intelligent management of TCM literature based on language processing technology is characterized by: The central processor receives the stored tracking perception data corresponding to the target TCM literature and processes it to obtain the tracking perception results for intelligent management, specifically including: Based on the tracking perception data of the target TCM literature, a tracking perception data check set is extracted from the database, wherein the tracking perception data check set specifically includes: a check value for the number of error characters, a check value for the number of missing metadata items, a check value for the access frequency, and a check value for the current byte value; The tracking perception data of the target TCM document and the tracking perception data verification set of the target TCM document are processed and analyzed to obtain the tracking perception damage verification value corresponding to the stored target TCM document, and the damage threshold is extracted from the database for comparison. If the tracking perception damage verification value corresponding to the stored target TCM document is less than or equal to the damage threshold, the stored target TCM document is determined to be in a lossless storage state, and the file repair process is not performed; If the tracking perception damage check value corresponding to the stored target TCM document is greater than the damage threshold, the stored target TCM document is determined to be in a damaged storage state, and the current target TCM document is recorded as a document that needs to be repaired; Extract the difference between the trace perception damage check value and the damage threshold of the demand repair document and record it as the damaged benchmark feature value; Compare the damaged baseline characteristic value of the demand repair document with the damaged processing cutoff value extracted from the database. When the damaged baseline characteristic value is less than or equal to the damaged processing cutoff value, it is determined that the demand repair document needs to be automatically repaired, and the demand repair document is automatically repaired; When the damaged baseline characteristic value of the document requiring repair is greater than the damaged processing cutoff value, it is determined that the document requiring repair needs to be manually repaired, and a repair prompt signal is transmitted to the management terminal for prompting.

7. According to claim 1, a method for intelligent management of TCM literature based on language processing technology, characterized in that: It also includes sensing the search request signal uploaded by the user on the edge channel, collecting the user's search keywords, and simultaneously performing intelligent recommendation processing of traditional Chinese medicine literature for the user. The specific process is as follows: Based on the index tag keywords of each existing TCM document in the document library and the user's search keywords, a number of existing TCM documents that match the user's search keywords are screened and recorded as pre-recommended documents; The number of citations, average daily page views, average visit time per person and publication time of each pre-recommended document are counted, and the recommendation priority of each pre-recommended document is obtained by processing; The recommendation priorities of the pre-recommended documents are arranged in descending order to obtain the recommended display order of the pre-recommended documents, and intelligent recommendation and display processing of traditional Chinese medicine documents is performed for users.

8. A system using the intelligent management method of TCM literature based on language processing technology as claimed in any one of claims 1 to 7, characterized in that: include: The document collection module is used to collect TCM documents uploaded from the edge channel that need to be stored in the document library, record them as target TCM documents, and extract the basic data set of the target TCM documents and transmit them to the central processor; The document processing module, the central processing unit receives the basic data set of the target TCM document for processing, obtains the basic characteristic value of the target TCM document, and determines the designated storage execution mode of the target TCM document based on the basic characteristic value; The document sensing module is used to track and sense the stored target TCM document, and obtain the tracking and sensing data corresponding to the stored target TCM document and transmit it to the central processor; The document management module is used for the central processor to receive and process the tracking perception data corresponding to the target traditional Chinese medicine document after storage, and obtain the tracking perception results for intelligent management.

9. A storage medium, characterized in that: include: The storage medium stores one or more programs, and the one or more programs are executed by one or more processors to implement the method according to any one of claims 1 to 7.

Images