Mapping association method and system for operation process activities under multiple standards

Abstract

The embodiment of the invention provides a mapping association method and system for operation process activities under multiple standards, and belongs to the technical field of Internet and cloud computing. The method comprises the following steps: acquiring a standard process file to be mapped and associated; determining a standard set of each corresponding standard process file by taking each standard process file as a unit; comparing each standard set to determine an association set between the standards; determining a first association relationship between the standards according to the association set; performing causal relationship decomposition on the standard process files to obtain standard decomposition information in each standard process file; constructing a standard directed graph according to the standard decomposition information; obtaining a second association relationship of each standard according to the standard directed graph; and constructing a mapping association relationship between the standards according to the first association relationship and the second association relationship.

Description

Technical Field

[0001] The present invention relates to the technical fields of the Internet and cloud computing, and particularly relates to a mapping association method and system for operation process activities under multiple standards. Background Art

[0002] Standard text resources are an indispensable and important part of project documents. They involve the quantitative regulations of various indicators in the project and play a role in precise quantitative monitoring for subsequent project implementation.

[0003] In the prior art, for standard text resources in a project, generally, based on existing experience, corresponding standard types are directly determined manually for various project contents in the project engineering, and then standard documents are formulated.

[0004] With the development of artificial intelligence technology, there have currently emerged AI models that can automatically generate such standard text resources within a small range. However, for a large volume of standard documents, since the AI model is required to have high feature data processing capabilities, it is difficult to meet the requirements for constructing the AI model.

[0005] To meet the requirements for constructing such an AI model, there are currently two known possible methods: One is to roughly increase the complexity of the network model first to make it have higher feature data processing capabilities, which requires higher computing power and more training time; the other is to preprocess the standard documents before training the model. By establishing mapping association relationships between different standards, the dimension of the standard documents after being input into the model is reduced, thereby reducing the requirements for the feature data processing capabilities of the network model. This solution is relatively efficient, but there is currently no such method. Summary of the Invention

[0006] The purpose of the embodiments of the present invention is to provide a mapping association method and system for operation process activities under multiple standards, which can mine the mapping relationships between standards, thereby reducing the requirements for the feature data processing capabilities of the subsequent network model.

[0007] To achieve the above purpose, the embodiments of the present invention provide a mapping association method for operation process activities under multiple standards, including:

[0008] Obtain standard process files to be mapped and associated;

[0009] Taking each of the standard process files as a unit, determine the standard set corresponding to each standard process file;

[0010] Compare each of the standard sets to determine the association set between the standards;

[0011] Determine a first association relationship between the standards according to the associated set;

[0012] Perform causal relationship decomposition on the standard process file to obtain standard decomposition information in each standard process file;

[0013] Construct a standard directed graph according to the standard decomposition information;

[0014] Obtain a second association relationship of each standard according to the standard directed graph;

[0015] Construct a mapping association relationship between the standards according to the first association relationship and the second association relationship.

[0016] Optionally, taking each standard process file as a unit, determine a standard set corresponding to each standard process file, including:

[0017] Perform keyword retrieval on the set of standard process files according to a preset standard process library to determine a list of standards included in the standard process files.

[0018] Optionally, compare each standard set to determine an associated set between the standards, including:

[0019] Initialize the association degree value;

[0020] Select a corresponding intersection in the standard set according to the association degree value according to a preset percentage value of the associated set;

[0021] Judge whether an intersection can still be obtained currently;

[0022] In the case of judging that the intersection can be obtained currently, update the association degree value;

[0023] Update the percentage value and return to execute the step of selecting a corresponding intersection in the standard set according to the association degree value according to a preset percentage value of the associated set;

[0024] In the case of judging that the intersection cannot be obtained currently, associate the standards corresponding to all the intersections to obtain the associated set.

[0025] Optionally, update the association degree value, including:

[0026] Update the association degree value according to formula (1):

[0027] t i+1 =t i +1, (1)

[0028] where t i+1 is the association degree value after the i-th update, ti is the correlation value before the i-th update;

[0029] Updating the percentage value includes:

[0030] Updating the percentage value according to formula (2):

[0031] p i+1 = p i -(i + 1)·δ, (2)

[0032] where p i+1 is the percentage value after the i-th update, p i is the percentage value before the i-th update, and δ is a non-zero number between 0 and 0.1.

[0033] Optionally, perform causal relationship decomposition on the standard process file to obtain standard decomposition information in each standard process file, including:

[0034] Perform word segmentation on the standard process file;

[0035] Search for words or phrases that match the standard process file in a preset standard library to determine the standards included in the standard process file;

[0036] Determine the causal relationship before and after each standard in the standard process file;

[0037] Classify the causal relationship before and after to obtain multiple causal relationship classes;

[0038] Determine the weight of each causal relationship class according to the level of the causal relationship class;

[0039] Determine the standard decomposition information with the weight, the causal relationship before and after, and the corresponding standards.

[0040] Optionally, determining the causal relationship before and after each standard in the standard process file includes:

[0041] Determine whether there is a keyword between every two standards;

[0042] In the case where it is determined that there is no keyword between two standards, determine that the classification of the keyword between the two standards is the lowest level;

[0043] In the case where it is determined that there is a keyword between two standards, classify the keyword between the standards according to a preset keyword library to obtain the causal relationship before and after.

[0044] Optionally, classifying the causal relationship before and after to obtain multiple causal relationship classes includes:

[0045] Classify the front-back causal relationship according to a preset hierarchical difference, where the lowest-level front-back causal relationship is of one category, and the remaining front-back causal relationships are divided respectively according to the preset hierarchical difference.

[0046] Optionally, determine the weight of each causal relationship category according to the level of the causal relationship category, including:

[0047] Calculate the average level of each causal relationship category respectively;

[0048] Determine the weight according to the principle of ascending order of the average level.

[0049] On the other hand, the present invention also provides a mapping association system for operation process activities under multiple criteria. The system includes a processor, and the processor is configured to execute the method as described in any one of the above.

[0050] Through the above technical solution, the embodiments of the present invention provide a mapping association method and system for operation process activities under multiple criteria. By decomposing the association characteristics of criteria in two dimensions of frequency and semantics, the mapping association relationships of multiple criteria are obtained. And based on this mapping association relationship, the dimension after the standard file is input into the model can be reduced, thereby reducing the requirement for the feature data processing ability of the network model.

[0051] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. Brief Description of the Drawings

[0052] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. Together with the following specific implementation, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0053] Figure 1 is a flowchart of a mapping association method for operation process activities under multiple criteria according to an embodiment of the present invention;

[0054] Figure 2 is a flowchart of a method for obtaining an association set according to an embodiment of the present invention;

[0055] Figure 3 is a flowchart of a method for obtaining standard decomposition information according to an embodiment of the present invention. Detailed Description of the Invention

[0056] The following will describe in detail the specific implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiments of the present invention, and is not used to limit the embodiments of the present invention.

[0057] In the embodiments of the present application, certain industry-existing solutions such as software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0058] As Figure 1 shown is a flowchart of a method for mapping and associating operation process activities under multiple standards according to an embodiment of the present invention. In this Figure 1 method, the method may include the following steps:

[0059] In step S10, obtain the standard process file to be mapped and associated;

[0060] In step S11, taking each standard process file as a unit, determine the standard set corresponding to each standard process file;

[0061] In step S12, compare each standard set to determine the association set between the standards;

[0062] In step S13, determine the first association relationship between the standards according to the association set;

[0063] In step S14, perform causal relationship decomposition on the standard process file to obtain the standard decomposition information in each standard process file;

[0064] In step S15, construct a standard directed graph according to the standard decomposition information;

[0065] In step S16, obtain the second association relationship of each standard according to the standard directed graph;

[0066] In step S17, construct the mapping and association relationship between the standards according to the first association relationship and the second association relationship.

[0067] Among them, step S10 can be used to obtain the standard process file to be mapped and associated. Among them, the standard process file may be a standard document generated in the historical project data.

[0068] Step S11 is used to determine the standard set corresponding to each standard process file in units of each standard process file. Specifically, in this embodiment, this step S11 may be to perform keyword retrieval on the set of standard process files according to a preset standard process library to determine the list of standards included in the standard process files. Among them, the standard process library may include multiple standards and the retrieval keywords corresponding to each standard. When performing keyword retrieval, this step S11 may retrieve by extracting the retrieval keywords in the standard process library and the current set of standard process files, so as to obtain the standards corresponding to each standard file.

[0069] Step S12 is used to compare each standard set to determine the associated set between the standards. Among them, the standard set may be the set of standards included in each standard process file. And the associated set may be the set of standards representing the interrelated standards. Specifically, in this embodiment, the method for obtaining this associated set may include the steps as Figure 2 shown. In this Figure 2 , the method for obtaining this associated set may include the following steps:

[0070] In step S20, the association degree value is initialized. Among them, the association degree value may be used to represent the number of interrelated standards. In an example of the present invention, the initial association degree value may be 2.

[0071] In step S21, according to the preset percentage value of the associated set, the corresponding intersection is selected from the standard set according to the association degree value.

[0072] In step S22, it is judged whether an intersection can still be obtained currently;

[0073] In step S23, when it is judged that an intersection can be obtained currently, the association degree value is updated. Among them, for the method of updating this association degree value, there may be various forms known to those skilled in the art. In an example of the present invention, it may be updated by using the following formula (1):

[0074] t i+1 =t i +1, (1)

[0075] Among them, t i+1 is the association degree value after the i-th update, and t i is the association degree value before the i-th update.

[0076] In step S24, update the percentage value, and return to execute the step of selecting the corresponding intersection in the standard set according to the percentage value of the preset association set according to the association degree value, that is, return to execute step S21. Among them, for the method of updating the percentage value, it can be various forms known to those skilled in the art. In an example of the present invention, it can be updated by using the following formula (2):

[0077] p i+1 = p i -(i + 1)·δ, (2)

[0078] Wherein, p i+1 is the percentage value after the i-th update, p i is the percentage value before the i-th update, and δ is a non-zero number between 0 and 0.1.

[0079] In step S25, when it is determined that the intersection cannot be obtained currently, associate the corresponding criteria in all intersections to obtain an association set.

[0080] Step S14 can be used to decompose the causal relationship of the standard process file to obtain the standard decomposition information in each standard process file. Specifically, in this embodiment, this step S14 can further include the method shown in Figure 3 As shown. In this Figure 3 The method of obtaining the standard decomposition information may include the following steps:

[0081] In step S30, perform word segmentation processing on the standard process file;

[0082] In step S31, search for words or phrases that match the standard process file in the preset standard library to determine the standards included in the standard process file;

[0083] In step S32, determine the front-back causal relationship of each standard in the standard process file;

[0084] In step S33, classify the front-back causal relationship to obtain multiple causal relationship classes;

[0085] In step S34, determine the weight of each causal relationship class according to the level of the causal relationship class;

[0086] In step S35, determine the standard decomposition information by using the weight, the front-back causal relationship, and the corresponding standard.

[0087] In this such as Figure 3In the method shown, steps S30 and S31 can be used to obtain the standards in each standard process file. Step S32 can be used to determine the causal relationship before and after each standard in the standard process file. Specifically, in this embodiment, for the causal relationship before and after different standards, the standards of two keywords that are relatively close and have a connection can be directly recognized as having a strong causal relationship. Conversely, if the distance between two standards is far (the number of words between them exceeds the threshold), it is considered that the causal relationship before and after these two standards is weak. That is, step S32 can first determine whether there are keywords between every two standards. In the case where it is determined that there are no keywords between two standards, the classification of the keywords between the two standards is determined to be the lowest level. Conversely, in the case where it is determined that there are keywords between two standards, the keywords between the standards can be further classified according to a preset keyword library to obtain the causal relationship before and after. Among them, for the specific method of this classification, it can be various forms known to those skilled in the art. In an example of the present invention, the specific method of this classification can be to separately divide according to the number of keywords and the type of keywords between the standards. First, divide by the number of keywords. The more the number of keywords, the weaker the causal relationship before and after the two standards. Then, the type of keywords can be divided. The keywords are sorted according to the preset semantics expressing strong association and weak association, and then the keywords between the two standards are decomposed according to the sorting result to obtain the corresponding causal relationship before and after.

[0088] Step S33 can be to classify the causal relationship before and after to obtain multiple causal relationship classes. Specifically, this step S33 can classify the causal relationship before and after according to a preset grade difference. Among them, the lowest-level causal relationship before and after is one class, and the remaining causal relationships before and after are divided respectively according to the preset grade difference.

[0089] Step S34 can be used to determine the weight of each causal relationship class according to the level of the causal relationship class. Specifically, this step S34 can first calculate the average level of each causal relationship class respectively, and then determine the corresponding weight according to the principle of ascending order of this average level.

[0090] After determining the first association relationship and the second association relationship, step S17 can be used to construct a mapping association relationship between the standards according to the first association relationship and the second association relationship. Since the first association relationship is an association relationship obtained based on the occurrence frequency between the standards and can accurately express the frequency characteristics between the standards; while the second association relationship is an association relationship obtained based on semantic retrieval and can accurately express the semantic association relationship between the standards in the standard process file. Therefore, through this step S17, the two are combined with each other to obtain a more accurate mapping association relationship.

[0091] On the other hand, the present invention also provides a mapping and association system for operation process activities under multiple standards. The system includes a processor configured to execute the method described in any one of the above.

[0092] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0096] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0097] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0100] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A mapping and association method for operation process activities under multiple standards, characterized in that: The method comprises: Obtain the standard process file to be mapped; Taking each of the standard process files as a unit, determining a standard set corresponding to each standard process file; comparing each of the standard sets to determine a set of associations between the standards; Determining a first association relationship between the standards according to the association set; Performing causal relationship decomposition on the standard process files to obtain standard decomposition information in each of the standard process files; constructing a standard directed graph according to the standard decomposition information; Acquire a second association relationship of each standard according to the standard directed graph; A mapping association relationship between the standards is constructed according to the first association relationship and the second association relationship.

2. The method according to claim 1, characterized in that Taking each of the standard process files as a unit, determining a standard set of each corresponding standard process file includes: A keyword search is performed on the set of standard process files according to a preset standard process library to determine a list of standards included in the standard process files.

3. The method according to claim 1, characterized in that Comparing each of the standard sets to determine a set of associations between the standards, including: Initialize the relevance value; Selecting a corresponding intersection in the standard set according to the association value according to the percentage value of the preset association set; Determine whether the intersection can still be obtained at present; When it is determined that the intersection can be obtained currently, updating the association value; updating the percentage value, and returning to execute the step of selecting a corresponding intersection in the standard set according to the association value according to the preset percentage value of the association set; When it is determined that the intersection cannot be obtained currently, the corresponding standards in all intersections are associated to obtain the associated set.

4. The method according to claim 3, characterized in that Updating the association value includes: Update the association value according to formula (1): t i+1 =t i +1, (1) Among them, t i+1 is the correlation value after the i-th update, t i is the correlation value before the i-th update; Updating the percentage value includes: Update the percentage value according to formula (2): p i+1 =p i -(i+1)·δ, (2) Among them, p i+1 is the percentage value after the i-th update, p i is the percentage value before the i-th update, and δ is a non-zero number between 0 and 0.

1.

5. The method according to claim 1, characterized in that Performing causal relationship decomposition on the standard process files to obtain standard decomposition information in each of the standard process files, including: Performing word segmentation processing on the standard process file; Searching for words or phrases matching the standard process file in a preset standard library to determine the standards included in the standard process file; Determine the cause-and-effect relationship between the various standards in the standard process document; Classifying the preceding and following causal relationships to obtain a plurality of causal relationship classes; Determining the weight of each of the causal relationship classes according to the level of the causal relationship classes; The weights, causal relationships and corresponding standards are used to determine the standard decomposition information.

6. The method according to claim 5, characterized in that Determine the cause-and-effect relationship between the standards in the standard process document, including: Determining whether a keyword exists between each two of the criteria; In the case where it is determined that there is no keyword between the two criteria, determining the classification of the keyword between the two criteria to be the lowest level; When it is determined that there are keywords between two standards, the keywords between the standards are graded according to a preset keyword library to obtain the causal relationship.

7. The method according to claim 6, characterized in that The causal relationships are classified to obtain multiple causal relationship classes, including: The causal relationships are classified according to preset level differences, wherein the lowest level of causal relationships is classified into one category, and the remaining causal relationships are divided according to preset level differences.

8. The method according to claim 7, characterized in that Determining the weight of each causal relationship class according to the level of the causal relationship class includes: calculating the average rank of each of said causal relationship classes respectively; The weight is determined according to the principle of the average level from small to large.

9. A mapping and association system for work process activities under multiple standards, characterized in that: The system comprises a processor configured to execute the method according to any one of claims 1 to 8.

Images