A method and system for processing unstructured documents in petroleum business

Abstract

The present application provides a method and system for processing unstructured documents of petroleum business, belonging to the technical field of business document analysis and processing; wherein, a method for processing unstructured documents of petroleum business includes, obtaining a group of petroleum business data documents provided by each database; determining basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; analyzing the human operation impact data of each of the petroleum business data documents according to a preset human label operation table and the number of labels contained in the document label data; calculating the document processing priority data of the petroleum business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data; adopting this scheme realizes the sorting of processing priorities of the petroleum business data documents, and ensures the processing security and processing efficiency of a large number of petroleum business data documents.

Description

Technical Field

[0001] The present application relates to the technical field of petroleum business document analysis, and in particular to a method and system for processing unstructured documents in petroleum business. Background Art

[0002] As one of the important carriers for recording oil business data, the regional databases in various regions will store a large number of oil business data documents; oil business data documents contain multiple tags to characterize their own data characteristics and document content characteristics; since the oil business data documents stored in databases in different regions are generated at different times and cover different corresponding oil business areas, their own document formats are also different; in order to improve the processing efficiency of unified processing of large quantities of oil business documents, it is very important to determine the processing strategy for large quantities of oil business documents. Summary of the invention

[0003] The present application provides a method and system for processing unstructured documents of petroleum business, which can improve the efficiency of unified processing of large quantities of petroleum business documents.

[0004] In a first aspect, the present application provides a method for processing unstructured documents in a petroleum business. The method comprises:

[0005] Obtaining a petroleum business data document group provided by each database; Obtaining a petroleum business data document group provided by each database; The petroleum business data document group includes a plurality of petroleum business data documents and document label data; The document label data includes the petroleum business data document group. Service The number and types of tags contained in the data document;

[0006] Determining basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels included in the document label data;

[0007] Analyzing the human operation impact data of each of the oil business data documents according to the preset human operation label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data;

[0008] The document processing priority data of the oil business data document group is calculated according to the basic label impact data, the label integrity impact data and the human operation impact data.

[0009] Further, the calculating of the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data includes:

[0010] Calculate single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the petroleum business data documents;

[0011] Determine the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group according to the single document processing priority data and a preset first threshold; the important petroleum business documents are petroleum business data documents whose single document processing priority data is higher than the preset first threshold; the unimportant petroleum business documents are petroleum business data documents whose single document processing priority data is not higher than the preset first threshold;

[0012] The document processing priority data of the petroleum business data document group is calculated based on the single document processing priority data of each petroleum business data document included in the petroleum business data document group, the number of important petroleum business documents included in the petroleum business data document group, and the number of unimportant petroleum business documents.

[0013] Furthermore, the method for calculating the document processing priority data includes:

[0014] Assume that there are p important oil business documents and q non-important oil business documents in any oil business data document group, and the single document processing priority data of the u-th important oil business document is , the single document processing priority data of the vth non-important petroleum business document is ;

[0015] ;

[0016] In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function;

[0017] in,

[0018] ;

[0019] In the formula, A threshold value for the number of non-critical petroleum business documents is preset.

[0020] Furthermore, the basic label impact data and label integrity impact data of each of the petroleum business data documents are determined according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels included in the document label data, including:

[0021] Determining basic label impact data according to a preset label impact database and label types included in the document label data;

[0022] The tag completeness impact data is calculated according to the number of tags included in the document tag data and the preset standard number of tags.

[0023] Furthermore, the human operation impact data of each of the oil business data documents is analyzed according to the preset human operation table and the number of tags included in the document tag data; the human operation impact data is associated with the number of tags included in the document tag data, including:

[0024] Determining the number of manually operated tags contained in the petroleum business data document according to a preset manual tag operation table and the tag types contained in the document tag data; the preset manual tag operation table contains tags of petroleum business data documents involving documents requiring manual operation;

[0025] The human operation impact data of each of the petroleum business data documents is analyzed according to the number of human operation tags.

[0026] Furthermore, the method for calculating the single document processing priority data includes:

[0027] ;

[0028] In the formula, Processing priority data for a single document; The basic label affects the data. Affects data for label integrity; To manually manipulate the number of labels, Affecting data for human manipulation; are respectively a preset first weight and a preset second weight; wherein .

[0029] In a second aspect, the present application provides a petroleum business unstructured document processing system, the system comprising:

[0030] An acquisition module is used to acquire a petroleum business data document group provided by each database; the petroleum business data document group includes a plurality of petroleum business data documents and document label data; the document label data includes the number and type of labels included in the petroleum business data document;

[0031] A determination module, used to determine the basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels included in the document label data;

[0032] An analysis module, used for analyzing the human operation impact data of each of the oil business data documents according to a preset human operation label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data;

[0033] A calculation module is used to calculate the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data.

[0034] Furthermore, the calculation module is further configured to calculate the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data, including:

[0035] Calculate single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the petroleum business data documents;

[0036] Determine the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group according to the single document processing priority data and a preset first threshold; the important petroleum business documents are petroleum business data documents whose single document processing priority data is higher than the preset first threshold; the unimportant petroleum business documents are petroleum business data documents whose single document processing priority data is not higher than the preset first threshold;

[0037] The document processing priority data of the petroleum business data document group is calculated based on the single document processing priority data of each petroleum business data document included in the petroleum business data document group, the number of important petroleum business documents included in the petroleum business data document group, and the number of unimportant petroleum business documents.

[0038] Furthermore, the calculation module is further configured such that the calculation method of the document processing priority data includes:

[0039] Assume that there are p important oil business documents and q non-important oil business documents in any oil business data document group, and the single document processing priority data of the u-th important oil business document is , the single document processing priority data of the vth non-important petroleum business document is ;

[0040] ;

[0041] In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function;

[0042] in,

[0043] ;

[0044] In the formula, A threshold value for the number of non-critical petroleum business documents is preset.

[0045] Furthermore, the determination module is further configured to determine the basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data, including:

[0046] Determining basic label impact data according to a preset label impact database and label types included in the document label data;

[0047] The tag completeness impact data is calculated according to the number of tags included in the document tag data and the preset standard number of tags.

[0048] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0050] Figure 1 A flowchart of a method for processing unstructured documents in a petroleum business in an embodiment of the present application is shown;

[0051] Figure 2 A block diagram of an unstructured document processing system for petroleum business in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0054] The present application provides a method and system for processing unstructured documents in petroleum business, which can determine the processing priority of each petroleum business data document, thereby improving the processing efficiency of a large number of petroleum business data documents.

[0055] In a first aspect, the present application provides a method for processing unstructured documents in a petroleum business. Figure 1 The specific steps included in the method are as follows.

[0056] Step S110: Obtain the oil business data document group provided by each database; obtain the oil business data document group provided by each database; the oil business data document group includes multiple oil business data documents and document label data; the document label data includes the number and type of labels contained in the oil business data document.

[0057] It can be understood that in the embodiment of the present application, there is a central database that receives the oil business data document groups provided by the databases of each region, and it is necessary to perform unified and standardized processing on the above-mentioned oil business data document groups to ensure that the documents finally presented are in the same format, which is convenient for viewing and data analysis; in the above-mentioned actual situation, there are a large number of oil business data document groups in the database of each region. The oil business data document groups here are when the oil business data documents are stored in each database, and each oil business data document has a certain relationship with each other. When collecting local oil business data, it itself is uploaded to the database of the corresponding local region in the form of individual documents and combined into groups; therefore, in the embodiment of the present application, it is also processed in the form of the same oil business data document group for priority analysis, which reduces the tediousness of document processing and improves document processing efficiency.

[0058] Step S120: determining basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels included in the document label data.

[0059] Specifically, determining the basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and the preset label impact database includes: determining the basic label impact data according to the preset label impact database and the types of labels contained in the document label data; and calculating the label integrity impact data according to the number of labels contained in the document label data and the preset standard label number.

[0060] It can be understood that the document tags here are built-in in each oil business data document; and the tag system here is built at the beginning of building the oil business data document rules; the specific construction method of the tag system will not be repeated here; it can be understood that the cloud stores a tag library, which contains all tags that may be involved in the oil business data document; the tag library contains the characteristics of the document data itself, such as the upload time of the oil business data document, the amount of data involved in the oil business data document, the oil business area corresponding to the oil business data document, etc.; it should be noted that the method of document processing involved in this application is to adopt automated processing, that is, to automatically analyze and process the documents through an artificial intelligence system; however, if the oil business data document is missing some important tags, manual intervention is required to analyze and process the document. At this time, the cost of document processing is greatly increased, and in this case, the processing priority of such documents will be reduced.

[0061] It can be understood that the number of standard tags here refers to the important data required for unified document conversion processing. If a document is missing some tags, it means that the document is missing some data, and the processing priority of this part of the document will decrease; and the preset tag impact database here contains the impact data corresponding to some tags contained in the document; the basic tag impact data here is calculated by multiplying each basic tag by the corresponding impact data, and then accumulating the above data to obtain the sum value, which is the basic tag impact data.

[0062] The label integrity impact data here is calculated by dividing the number of labels in the document by the preset standard label number value and then multiplying it by the preset label integrity impact coefficient to obtain the label integrity impact data.

[0063] Step S130: Analyze the human operation impact data of each of the oil business data documents according to the preset human operation table and the number of tags included in the document tag data; the human operation impact data is associated with the number of tags included in the document tag data.

[0064] Specifically, analyzing the human operation impact data of each of the oil business data documents according to the number of labels contained in the preset human label operation table and the document label data includes: determining the number of human operation labels contained in the oil business data document according to the preset human label operation table and the types of labels contained in the document label data; the preset human label operation table contains oil business data document labels involving documents requiring human operation; and analyzing the human operation impact data of each of the oil business data documents according to the number of human operation labels.

[0065] It is understandable that the preset manual label operation table includes the important labels mentioned above. The important labels here refer to labels that cannot be operated by artificial intelligence machines to extract important data from the document. That is, when this part of the label is missing, manual intervention is required to process the document.

[0066] Step S140: Calculate the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data.

[0067] In an embodiment of the present application, calculating the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data specifically includes: calculating single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the oil business data documents; determining the number of important oil business documents and the number of unimportant oil business documents contained in the oil business data document group according to the single document processing priority data and a preset first threshold; the important oil business document is a oil business data document whose single document processing priority data is higher than the preset first threshold; the unimportant oil business document is a oil business data document whose single document processing priority data is not higher than the preset first threshold; calculating the document processing priority data of the oil business data document group based on the single document processing priority data of each oil business data document contained in the oil business data document group, the number of important oil business documents and the number of unimportant oil business documents contained in the oil business data document group.

[0068] The calculation method of the single document processing priority data includes:

[0069] ;

[0070] In the formula, Processing priority data for a single document; The basic label affects the data. Affects data for label integrity; To manually manipulate the number of labels, Affecting data for human manipulation; are respectively a preset first weight and a preset second weight; wherein .

[0071] It can be understood that the human operation impact data here is a deformation of the activation function, which is zero at the zero point and suddenly changes when a=1, causing the slope of the function curve to surge; since a reflects the situation that requires human intervention, its impact is greater than that of the situation that does not require human intervention; however, if there are more situations that require human intervention, the change will not be too large.

[0072] The calculation method of the document processing priority data specifically includes:

[0073] Assume that there are p important oil business documents and q non-important oil business documents in any oil business data document group, and the single document processing priority data of the u-th important oil business document is , the single document processing priority data of the vth non-important petroleum business document is ;

[0074] ;

[0075] In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function;

[0076] in,

[0077] ;

[0078] In the formula, To preset a threshold for the number of non-critical petroleum business documents.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0080] In the second aspect, the present application provides a system for processing unstructured documents in the petroleum business. Figure 2As shown, the system includes an acquisition module 210, which is used to acquire a petroleum business data document group provided by each database; the petroleum business data document group includes multiple petroleum business data documents and document label data; the document label data includes the number of labels and the type of labels contained in the petroleum business data document; a determination module 220, which is used to determine the basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data; an analysis module 230, which is used to analyze the human operation impact data of each of the petroleum business data documents according to a preset human label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data; a calculation module 240, which is used to calculate the document processing priority data of the petroleum business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data.

[0081] The calculation module 240 is further configured to calculate the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data, including: calculating single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the oil business data documents; determining the number of important oil business documents and the number of unimportant oil business documents contained in the oil business data document group according to the single document processing priority data and a preset first threshold; the important oil business documents are oil business data documents whose single document processing priority data is higher than the preset first threshold; the unimportant oil business documents are oil business data documents whose single document processing priority data is not higher than the preset first threshold; calculating the document processing priority data of the oil business data document group based on the single document processing priority data of each oil business data document contained in the oil business data document group, the number of important oil business documents and the number of unimportant oil business documents contained in the oil business data document group.

[0082] Assume that there are p important oil business documents and q non-important oil business documents in any oil business data document group, and the single document processing priority data of the u-th important oil business document is , the single document processing priority data of the vth non-important petroleum business document is ;

[0083] ;

[0084] In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function;

[0085] in,

[0086] ;

[0087] In the formula, A threshold value for the number of non-critical petroleum business documents is preset.

[0088] The determination module 220 is further configured to determine the basic label impact data and label integrity impact data of each of the oil business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data, including determining the basic label impact data according to a preset label impact database and the types of labels contained in the document label data; and calculating the label integrity impact data according to the number of labels contained in the document label data and a preset standard number of labels.

[0089] The analysis module 230 is further configured to analyze the human operation impact data of each of the oil business data documents according to the preset human operation label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data, including determining the number of human operation labels contained in the oil business data document according to the preset human operation label operation table and the types of labels contained in the document label data; the preset human operation label operation table contains oil business data document labels involving documents requiring human operation; and analyzing the human operation impact data of each of the oil business data documents according to the number of human operation labels.

[0090] The method for calculating the single document processing priority data includes:

[0091] ;

[0092] In the formula, Processing priority data for a single document; The basic label affects the data. Affects data for label integrity; To manually manipulate the number of labels, Affecting data for human manipulation; are respectively a preset first weight and a preset second weight; wherein .

[0093] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0094] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for processing unstructured documents in petroleum business, characterized in that: include: Obtain the oil business data document group provided by various databases; Acquire a petroleum business data document group provided by each database; the petroleum business data document group includes a plurality of petroleum business data documents and document label data; the document label data includes the number and type of labels included in the petroleum business data document; Determining basic label impact data and label integrity impact data of each of the petroleum business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels included in the document label data; The basic tag impact data is calculated by multiplying each basic tag by the corresponding impact data, and then accumulating the above data to obtain the sum value, which is the basic tag impact data; the tag completeness impact data is calculated by dividing the number of tags in the document by the preset standard tag number value and then multiplying it by the preset tag completeness impact coefficient; Analyzing the human operation impact data of each of the oil business data documents according to the preset human operation label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data; Calculate the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data, wherein the document processing priority data is intended to indicate the processing order of the oil business data document group; The calculating of the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data comprises calculating a single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the oil business data documents; Determine the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group according to the single document processing priority data and a preset first threshold; the important petroleum business document is a petroleum business data document whose single document processing priority data is higher than the preset first threshold; the unimportant petroleum business document is a petroleum business data document whose single document processing priority data is not higher than the preset first threshold; calculate the document processing priority data of the petroleum business data document group based on the single document processing priority data of each petroleum business data document included in the petroleum business data document group, the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group; The step of analyzing the human operation impact data of each of the oil business data documents according to the preset human operation label operation table and the number of labels included in the document label data; associating the human operation impact data with the number of labels included in the document label data includes determining the number of human operation labels included in the oil business data document according to the preset human operation label operation table and the types of labels included in the document label data; the preset human operation label operation table includes labels of oil business data documents involving documents that require human operation; Analyze the human operation impact data of each of the oil business data files according to the number of human operation tags; The method for calculating the single document processing priority data includes: ; In the formula, Processing priority data for a single document; The basic label affects the data. The label integrity affects the data; e is a natural constant, To manually manipulate the number of labels, Affecting data for human manipulation; , are respectively a preset first weight and a preset second weight; wherein; ; The calculation method of the document processing priority data includes: assuming that there are p important oil business documents and q non-important oil business documents in any oil business data document group, the single document processing priority data of the u-th important oil business document is: , the single document processing priority data of the vth non-important petroleum business document is ; ; In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function; in, ; In the formula, To set a threshold for the number of non-critical petroleum business documents; The basic label impact data and label integrity impact data of each of the petroleum business data documents are determined based on the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data, including: determining the basic label impact data based on a preset label impact database and the types of labels contained in the document label data; and calculating the label integrity impact data based on the number of labels contained in the document label data and a preset standard number of labels.

2. A petroleum business unstructured document processing system, characterized in that: include: An acquisition module (210) is used to acquire a petroleum business data document group provided by each database; the petroleum business data document group includes a plurality of petroleum business data documents and document label data; the document label data includes the number and type of labels included in the petroleum business data document; A determination module (220) is used to determine the basic label impact data and label integrity impact data of each of the oil business data documents according to the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data; the basic label impact data is calculated by multiplying each basic label by the corresponding impact data, and then accumulating the above data to obtain a sum value, which is the basic label impact data; the label integrity impact data is calculated by dividing the number of labels in the document by the preset standard label number value and then multiplying it by the preset label integrity impact coefficient; An analysis module (230) is used to analyze the human operation impact data of each of the oil business data documents according to a preset human operation label operation table and the number of labels contained in the document label data; the human operation impact data is associated with the number of labels contained in the document label data; A calculation module (240), configured to calculate document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data, wherein the document processing priority data is intended to indicate a processing order of the oil business data document group; The system is further configured such that the calculating of the document processing priority data of the oil business data document group according to the basic label impact data, the label integrity impact data and the human operation impact data comprises calculating a single document processing priority data according to the basic label impact data, the label integrity impact data and the human operation impact data of each of the oil business data documents; Determine the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group according to the single document processing priority data and a preset first threshold; the important petroleum business document is a petroleum business data document whose single document processing priority data is higher than the preset first threshold; the unimportant petroleum business document is a petroleum business data document whose single document processing priority data is not higher than the preset first threshold; calculate the document processing priority data of the petroleum business data document group based on the single document processing priority data of each petroleum business data document included in the petroleum business data document group, the number of important petroleum business documents and the number of unimportant petroleum business documents included in the petroleum business data document group; The step of analyzing the human operation impact data of each of the oil business data documents according to the preset human operation label operation table and the number of labels included in the document label data; associating the human operation impact data with the number of labels included in the document label data includes determining the number of human operation labels included in the oil business data document according to the preset human operation label operation table and the types of labels included in the document label data; the preset human operation label operation table includes labels of oil business data documents involving documents that require human operation; Analyzing the human operation impact data of each of the oil business data files according to the number of human operation tags; The method for calculating the single document processing priority data includes: ; In the formula, Processing priority data for a single document; The basic label affects the data. The label integrity affects the data; e is a natural constant, To manually manipulate the number of labels, Affecting data for human manipulation; , are respectively a preset first weight and a preset second weight; wherein; ; The calculation method of the document processing priority data includes: assuming that there are p important oil business documents and q non-important oil business documents in any oil business data document group, the single document processing priority data of the u-th important oil business document is: , the single document processing priority data of the vth non-important petroleum business document is ; ; In the formula, Processing priority data for documentation; is the first preset judgment function, is a second preset determination function; in, ; In the formula, To set a threshold for the number of non-critical petroleum business documents; The basic label impact data and label integrity impact data of each of the petroleum business data documents are determined based on the document label data and a preset label impact database; the label integrity impact data is associated with the number of labels contained in the document label data, including: determining the basic label impact data based on a preset label impact database and the types of labels contained in the document label data; and calculating the label integrity impact data based on the number of labels contained in the document label data and a preset standard number of labels.

Images