Standardized management system for aviation enterprises

Abstract

The invention relates to the technical field of enterprise management, and particularly discloses an aviation enterprise standardized management system which is characterized in that when an approval request is received, the natural language processing technology is used to analyze the approval request to extract key information such as initiator information, request type, approval content details and the like; semantic embedding coding and local context semantic association optimization based on word granularity are carried out on an examination and approval request analysis result to realize deep understanding of the examination and approval request, so that a proper first-level approver type is intelligently matched based on context semantic information of the examination and approval request analysis result. Through the mode, the approval path can be dynamically adjusted and the most suitable approver can be selected according to the specific content and background of the approval request, so that various approval requests can be flexibly handled, and the approval efficiency and the decision-making quality are improved.

Description

Technical Field

[0001] The present application relates to the technical field of enterprise management, and more specifically, to a standardized management system for aviation enterprises. Background Art

[0002] Aviation enterprise management refers to the management work for the operation and development of airlines, involving flight scheduling, aircraft maintenance, route development and other aspects to ensure the realization of corporate goals and the improvement of customer satisfaction. In the daily operation of aviation enterprises, standardized enterprise management is essential to ensure efficient, safe and compliant operations. As the complexity and scale of business continue to expand, traditional management methods have been unable to meet the needs of modern aviation enterprises in a rapidly changing market environment. In order to meet this challenge, many companies have begun to use digital means to optimize their internal processes, improve decision-making efficiency, and ensure coordination between departments.

[0003] For example, the invention patent with publication number CN115271294A proposes an enterprise standardization management system, which creates standardized departments and positions by loading a standardized organizational structure tree and using the parent ID to associate the upper and lower levels. At the same time, a similar structure tree is also established in the original organizational structure module. By matching the nodes in the standardized organizational structure tree with the nodes in the original organizational structure, new projects or changes in the standardized template will be automatically updated to the original organizational structure module to maintain consistency among departments and positions.

[0004] In the prior art, in terms of the approval process, standardized positions are directly and uniformly configured, and the project leader of the project under the approval request initiator is automatically captured and matched as the first-level approver according to the project where the approval request initiator is located, so as to meet the requirements of standardized management. This approval process management mainly relies on pre-set fixed approval paths. For example, "flight dispatcher submits -> maintenance engineer reviews -> aviation safety director approves".

[0005] However, in actual application, this fixed approval path has some limitations. First, the fixed approval path lacks flexibility and is difficult to adapt to the specific circumstances and urgency of different approval requests. For example, some emergency maintenance requests may need to skip the regular review steps and be quickly approved by higher-level decision makers to minimize the impact on flight operations. However, under the existing fixed approval path, such flexible adjustments are often difficult to achieve, resulting in low approval efficiency. Second, it is difficult for the fixed approval path to fully consider the differences between approval requests. Different approval requests may involve different professional fields, risk levels or urgency, and require approvers with different backgrounds and professional skills to evaluate. However, under the fixed approval path, the selection of approvers is often based on job level rather than the specific content of the approval request, which may lead to uneven quality of approval decisions and even approval errors in some cases.

[0006] Therefore, an optimized standardized management system for aviation enterprises is expected. Summary of the invention

[0007] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an aviation enterprise standardization management system, which uses natural language processing technology to parse the approval request when receiving the approval request to extract key information such as the initiator information, request type, approval content details, etc. Then, the approval request parsing result is subjected to semantic embedding encoding based on word granularity and local context semantic association optimization to achieve a deep understanding of the approval request, thereby intelligently matching the appropriate first-level approver type based on the contextual semantic information of the approval request parsing result. In this way, the approval path can be dynamically adjusted according to the specific content and background of the approval request, and the most appropriate approver can be selected, so as to flexibly respond to various approval requests and improve approval efficiency and decision-making quality.

[0008] Accordingly, according to one aspect of the present application, there is provided an aviation enterprise standardization management system, which includes: a standardization module for loading a standardized organizational structure tree, wherein the organizational structure in the standardized organizational structure tree is associated with upper and lower levels through a parent ID; an original organizational structure module for loading a company organizational structure tree, wherein the organizational structure in the company organizational structure tree is associated with upper and lower levels through the parent ID, and when a company level or branch level is selected to create a new organizational structure node, subordinate departments and position data are added according to preset nodes in the standardization module; an association module for corresponding nodes in the standardization module to nodes in the original organizational structure module, and through the association relationship between the standardization module and the original organizational structure module, the association operations in the authorization, approval, modification, and review processes in each of the levels are realized.

[0009] In the above aviation enterprise standardization management system, the association module includes:

[0010] An approval request parsing unit, used to parse the received approval request to obtain an approval request parsing result;

[0011] A semantic embedding coding unit, used for performing word-granular semantic embedding coding on the approval request parsing result to obtain a sequence of word-granular semantic embedding coding vectors of the approval request;

[0012] A medium-granularity semantic association optimization unit, used for performing medium-granularity semantic association constraint optimization on the sequence of approval request word granularity semantic embedding coding vectors to obtain a sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding coding vectors;

[0013] The approver matching unit is used to determine the type of the first-level approver based on the contextual semantic features of the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector.

[0014] Compared with the prior art, the aviation enterprise standardization management system provided by this application uses natural language processing technology to parse the approval request when it receives the approval request, so as to extract key information such as the initiator information, request type, and approval content details. Then, the approval request parsing result is subjected to semantic embedding encoding based on word granularity and local context semantic association optimization to achieve a deep understanding of the approval request, so as to intelligently match the appropriate first-level approver type based on the contextual semantic information of the approval request parsing result. In this way, the approval path can be dynamically adjusted according to the specific content and background of the approval request, and the most appropriate approver can be selected, so as to flexibly respond to various approval requests and improve approval efficiency and decision-making quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a block diagram of the aviation enterprise standardization management system according to an embodiment of the present application.

[0017] Figure 2 Schematic diagram of data flow of the aviation enterprise standardization management system according to an embodiment of the present application.

[0018] Figure 3It is a block diagram of a medium-granularity semantic association optimization unit in an aviation enterprise standardization management system according to an embodiment of the present application.

[0019] Figure 4 It is a block diagram of the approver matching unit in the aviation enterprise standardization management system according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0025] As mentioned in the above background technology, patent CN115271294A proposes an enterprise standardization management system, which includes: a standardization module, which is used to load a standardized organizational structure tree, and the organizational structure in the standardized organizational structure tree is associated with the upper and lower levels through the parent ID; an original organizational structure module, which is used to load a company organizational structure tree, and the organizational structure in the company organizational structure tree is associated with the upper and lower levels through the parent ID. When selecting the company level or branch level to create a new organizational structure node, the subordinate department and position data are added according to the preset nodes in the standardization module; an association module, which is used to correspond the nodes in the standardization module to the nodes in the original organizational structure module, and through the association relationship between the standardization module and the original organizational structure module, the association operations in the authorization, approval, modification, and review processes in each of the levels are realized.

[0026] First, loading a standardized organizational structure tree can provide an enterprise with a universal and reusable organizational structure template. This template uses parent IDs to associate upper and lower levels, ensuring that the relationship between each department and position is clear and easy to maintain. Specifically, the system defines the highest-level departments or functional areas of the enterprise as top-level nodes, such as "Head Office", "Finance Department", "Operation Department", etc. These nodes represent the main business areas within the enterprise. Then, the relationship between each level is established through the parent ID, and each child node points to its parent node, thus forming a complete organizational structure tree. This hierarchical association not only simplifies the representation of the organizational structure, but also facilitates subsequent queries and operations. For example, when you need to find the department where an employee is located, you can quickly locate it by tracing back to the parent ID layer by layer. In addition, the standardized organizational structure tree also includes detailed position information, such as job description, scope of responsibilities, required skills, etc., which helps to ensure consistency and accuracy when creating new nodes.

[0027] At the same time, loading the company's organizational structure tree is to map the actual corporate organizational structure into the system. Similarly, this structure tree is also associated with the upper and lower levels through the parent ID, but it reflects the specific department settings and job distribution within the current enterprise. When creating a new organizational structure node, whether you choose the company level or the branch level, the system will add the corresponding subordinate departments and job data according to the preset nodes in the standardized module. This means that whenever a new department or position is added, the system will automatically refer to the corresponding node in the standardized organizational structure tree and fill in relevant information according to the preset rules, such as department name, job description, required skills, etc. The advantage of this is that it ensures the consistency of the new node with the existing structure, while also reducing the possibility of manual input errors.

[0028] In the process of creating a new organizational structure node, if you encounter special needs or specific industry requirements, you can make appropriate adjustments based on the standardized template. For example, some airlines may need to set up additional departments specifically responsible for safety inspections and technical support. At this time, these specific nodes can be added outside the standardized template. In this way, the advantages of standardized modules are maintained while being able to flexibly respond to different business scenarios. At the same time, the system will also take into account the size and development stage of the enterprise. For large enterprises, a more detailed hierarchical structure may be required, while for start-ups, a simpler architectural design can be adopted. This flexibility ensures that no matter what stage of development the enterprise is in, it can have an organizational structure that adapts to its needs.

[0029] In addition, in order to ensure the real-time update and effectiveness of the organizational structure, the system needs to have a powerful change management function. Whenever there are major changes within the enterprise, such as merging departments, adjusting job responsibilities, etc., the system should reflect these changes in a timely manner to ensure that all relevant parties have access to the latest information. Change management not only involves the modification of the organizational structure tree itself, but also includes the synchronous adjustment of the associated approval process, permission settings, etc. For example, if a department is disbanded, the approval path related to it also needs to be re-evaluated and optimized; if an employee is promoted to a higher position, his or her access rights should be adjusted accordingly. Through such a mechanism, the system can always maintain a high degree of consistency with the actual situation of the enterprise, avoiding decision-making errors or inefficiency caused by information lags.

[0030] In the approval process of the above-mentioned enterprise standardization management system, by configuring standardized positions, the project leader of the project automatically captured and matched according to the project where the initiator of the approval request is located is used as the first-level approver, so as to meet the requirements of standardized management. However, this approval process management mainly relies on pre-set fixed approval paths, which has some limitations. First, the fixed approval process lacks flexibility and is difficult to adapt to the specific circumstances and urgency of different approval requests. For example, some emergency maintenance requests may need to skip the regular review steps and be quickly approved by higher-level decision makers to reduce the impact on flight operations. However, under the fixed approval process, such flexible adjustments are often difficult to achieve, resulting in reduced approval efficiency. Second, the fixed approval process is difficult to fully consider the differences between approval requests. Different approval requests may involve different professional fields, risk levels or urgency, and require approvers with different backgrounds and professional skills to evaluate. However, under the fixed approval process, the selection of approvers is often based on the job level rather than the specific content of the approval request, which may lead to inconsistent quality of approval decisions and even approval errors in some cases.

[0031] In response to the above technical problems, this application proposes an optimized aviation enterprise standardization management system, which uses natural language processing technology to parse the approval request when receiving the approval request to extract key information such as the initiator information, request type, and approval content details. Then, the approval request parsing results are subjected to semantic embedding encoding based on word granularity and local context semantic association optimization to achieve a deep understanding of the approval request, thereby intelligently matching the appropriate first-level approver type based on the contextual semantic information of the approval request parsing results. In this way, the approval path can be dynamically adjusted according to the specific content and background of the approval request, and the most appropriate approver can be selected, so as to flexibly respond to various approval requests and improve approval efficiency and decision-making quality.

[0032] Figure 1 It is a block diagram of the aviation enterprise standardization management system according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of aviation enterprise standardization management system according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the aviation enterprise standardization management system 100 includes: an approval request parsing unit 110, which is used to parse the received approval request to obtain an approval request parsing result; a semantic embedding coding unit 120, which is used to perform word-granularity semantic embedding coding on the approval request parsing result to obtain a sequence of approval request word-granularity semantic embedding coding vectors; a medium-granularity semantic association optimization unit 130, which is used to perform medium-granularity semantic association constraint optimization on the sequence of approval request word-granularity semantic embedding coding vectors to obtain a sequence of medium-granularity semantically enhanced approval request word-granularity semantic embedding coding vectors; an approver matching unit 140, which is used to determine the type of the first-level approver based on the contextual semantic features of the sequence of medium-granularity semantically enhanced approval request word-granularity semantic embedding coding vectors.

[0033] In the above aviation enterprise standardization management system, the approval request parsing unit 110 is used to parse the received approval request to obtain the approval request parsing result. It should be understood that considering that the approval request usually contains information in various formats such as forms and text descriptions, in order to accurately extract the key information in the approval request and conduct targeted approval process guidance, this application first uses natural language processing (NLP) technology to perform structured parsing on the text information in the approval request to extract key information such as initiator information, request type, approval content details, etc., so as to obtain the approval request parsing result. In specific implementation, a rule-based approach can be adopted to define in advance a series of grammatical rules related to the approval request format, such as stipulating that the initiator information is located at the beginning of the request text and follows the format of "Initiator: [Name / Department Name]"; the request type is matched through a keyword list, such as "procurement approval" and "project approval", etc.; the approval content details are extracted from the paragraphs or sentences in the text that describe specific matters, and the text is scanned word by word to identify and extract the corresponding information according to the rules, and it is organized into a structured data format, such as JSON or XML, to form the approval request parsing result.

[0034] Specifically, in order to accurately extract the key information in the approval request and provide targeted approval process guidance, considering that the approval request usually contains information in various formats such as forms and text descriptions, this application first uses natural language processing (NLP) technology to perform structured analysis on the received approval request. The application of NLP technology is intended to ensure that no matter what the source and form of the information is, it can effectively parse and extract key information such as the initiator information, request type, approval content details, etc., so as to obtain a comprehensive and accurate approval request analysis result.

[0035] First, the system needs to pre-process the approval request. Approval requests may come from various business systems within the aviation enterprise, such as flight scheduling systems, maintenance management systems, or financial management systems. Users of these systems include but are not limited to flight dispatchers, maintenance engineers, aviation safety directors, project managers, etc. Each approval request carries information about the required decision and is crucial to determining the approval path. The preprocessing stage includes removing irrelevant characters, punctuation, and converting the text to a unified format, such as all lowercase or standardized abbreviations. In addition, for requests in multilingual environments, language detection and translation are required to ensure that all requests can be parsed correctly.

[0036] Next is the text segmentation and tagging stage. NLP's word segmentation tools are usually used to segment the text into words or phrases, that is, "word granularity". Then, grammatical tags such as nouns, verbs, etc. are added to each vocabulary through part-of-speech tagging. This helps to understand the sentence structure and lays the foundation for the next step of information extraction. Named entity recognition (NER) technology can automatically identify specific types of entities from the text, such as names of people, places, dates, amounts and other key information. This is crucial for determining the parties involved, time frames and other important details of the approval request. For example, if "Zhang San" and "January 5, 2025" are mentioned in the approval request, it can be recognized that this is the name of the initiator and the estimated completion time.

[0037] The information extraction (IE) stage uses relation extraction and event extraction algorithms to further mine the implicit information in the text. For example, find out who initiated the request, which departments or projects are involved, what the specific requirements are, etc. This information is the key factor in determining the approval path. In practice, rule-based methods are widely used for approval request parsing. This method relies on a series of pre-defined grammatical rules related to the format of approval requests. For example, the initiator information is located at the beginning of the request text and follows the format of "Initiator: [Name / Department Name]"; the request type is matched by a keyword list, such as "procurement approval", "project approval", etc. The extraction of approval content details involves in-depth analysis of paragraphs or sentences in the text that describe specific matters. By scanning the text word by word, the system identifies and extracts the corresponding information according to pre-set rules. For example, if the text contains a sentence such as "need to purchase the following equipment", the system may regard it as the content of procurement approval and further search for a specific equipment list and other related details.

[0038] After completing the identification and extraction of information, the next task is to organize this information into a structured data format, such as JSON or XML. This step not only helps to maintain the consistency and readability of the data, but also facilitates subsequent processing and storage. The use of NLP technology is not limited to simple keyword matching, but also includes more advanced functions such as named entity recognition (NER), relationship extraction, event extraction, etc. These functions can help the system better understand the overall semantics of the text, rather than just focusing on the meaning of individual words. For example, NER can identify specific types of entities such as names, places, dates, etc. mentioned in the text; while relationship extraction and event extraction can capture the connections between different entities and the events that have occurred, which is particularly important for understanding complex approval requests.

[0039] In the above-mentioned aviation enterprise standardization management system, the semantic embedding coding unit 120 is used to perform word-granular semantic embedding coding on the approval request parsing result to obtain a sequence of word-granular semantic embedding coding vectors of the approval request. In a specific example of the present application, the semantic embedding coding unit 120 is used to: perform word segmentation processing on the approval request parsing result and then input it into a word semantic embedding encoder based on the Bert model to obtain a sequence of word-granular semantic embedding coding vectors of the approval request. It should be understood that since the text information of the approval request often contains a large number of professional terms and complex expressions, in order to accurately capture the semantic features of the approval request, the present application further uses the Bert model, which performs excellent performance in the field of text semantic understanding, to perform semantic encoding processing on the approval request parsing result, so as to convert each word in the approval request parsing result into a high-dimensional semantic vector representation. Specifically, first, use an existing Chinese word segmentation tool, such as Jieba word segmentation, to perform word segmentation operation on the approval request parsing result to split the continuous text into independent words. Then, each word after word segmentation processing is sequentially input into the pre-trained Bert model. The Bert model is trained through a large amount of corpus. For each word input, it can output a corresponding high-dimensional semantic vector based on the rich language knowledge and semantic representation learned in the pre-training process to represent the semantic features of the word. In this way, the text information of the approval request is converted into a sequence of semantic embedding encoding vectors at the approval request word granularity, thereby providing an accurate semantic basis for subsequent matching of approvers.

[0040] In the above-mentioned aviation enterprise standardization management system, the medium-granularity semantic association optimization unit 130 is used to perform medium-granularity semantic association constraint optimization on the sequence of the approval request word granularity semantic embedding coding vectors to obtain a sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding coding vectors. It should be understood that, considering that in the text information of the approval request parsing result, each word may have different semantic meanings in different contextual environments, therefore, in order to more accurately understand the complete semantics of the approval request, the present application proposes a medium-granularity semantic association constraint optimization method, which further performs grammatical analysis on the sequence of the approval request word granularity semantic embedding coding vectors to identify the local context windows associated with each approval request word granularity semantic embedding coding vector, and based on the contextual context within the local window, performs semantic enhancement processing on each approval request word granularity semantic embedding coding vector to enhance the accuracy and richness of the semantic representation of the approval request. Among them, Figure 3 FIG. 1 is a block diagram of a medium-granularity semantic association optimization unit in an aviation enterprise standardization management system according to an embodiment of the present application. Figure 3As shown, the medium-granularity semantic association optimization unit 130 includes: a grammatical depth analysis subunit 131, which is used to perform grammatical depth analysis on each approval request word granularity semantic embedding coding vector in the sequence of the approval request word granularity semantic embedding coding vector to obtain a sequence distribution of approval request word granularity grammatical depth implicit representation values; a semantic association window search subunit 132, which is used to determine the medium-granularity semantic association window of each approval request word granularity semantic embedding coding vector in the sequence of the approval request word granularity semantic embedding coding vector based on the sequence distribution of the approval request word granularity grammatical depth implicit representation values; a contextual semantic association strengthening subunit 133, which is used to perform medium-granularity contextual semantic association strengthening on each approval request word granularity semantic embedding coding vector based on the medium-granularity semantic association window of each approval request word granularity semantic embedding coding vector to obtain a sequence of the medium-granularity semantically strengthened approval request word granularity semantic embedding coding vectors.

[0041] Specifically, in a specific example of the present application, the syntax depth analysis subunit 131 is used to: first, map each approval request word granularity semantic embedding coding vector in the sequence of approval request word granularity semantic embedding coding vectors to a hyperbolic space to obtain a sequence of hyperbolic space approval request word granularity semantic embedding coding vectors, which is expressed by the formula:

[0042] T={v1,v2,...,v n}

[0043] h i =f hyp (v i )=W1v i W2

[0044] Where T represents the sequence of the granular semantic embedding encoding vectors of the approval request word, v1, v2, v i 、v n Respectively represent the first, second, i-th, and n-th approval request word granularity semantic embedding coding vectors in the sequence of the approval request word granularity semantic embedding coding vectors, f hyp (·) is the hyperbolic space mapping function, W1 and Q2 represent the first mapping weight matrix and the second mapping weight matrix respectively, h i Indicates the v i The corresponding hyperbolic space approval request word granularity semantic embedding encoding vector.

[0045] That is, when processing text data, the present application takes into account the complex hierarchical relationships between words, including but not limited to hyponyms, synonyms and antonyms, etc. Therefore, in order to better represent the hierarchical structure of the approval request parsing results, the present application adopts an advanced mapping strategy to further map the granular semantic embedding encoding vector of each approval request word to the hyperbolic space. This method utilizes the unique properties of hyperbolic geometry and can more effectively express the hierarchical relationship between data, thereby better revealing the semantic hierarchy and correlation between words in the approval request parsing results.

[0046] Then, the grammatical depth implicit representation value of each hyperbolic space approval request word granularity semantic embedding coding vector in the sequence of the hyperbolic space approval request word granularity semantic embedding coding vector is calculated to obtain the sequence distribution of the approval request word granularity grammatical depth implicit representation value, which is expressed by the formula:

[0047]

[0048] in,‖·‖ 2 represents the square of the norm of the vector, log2(·) represents the logarithmic function with base 2, f(·) represents the syntax depth measurement function, e i Indicates the v i The corresponding approval request word granularity syntax depth implicitly represents the value.

[0049] That is, by calculating the implicit representation value of the grammatical depth of the granular semantic embedding encoding vector of each approval request word mapped to the hyperbolic space, the position of these words in the syntactic tree structure is evaluated, thereby analyzing the grammatical role they play in the specific context. This not only reveals the importance of each word in the sentence construction, but also shows the relationship between each word and other language elements. For example, some words or phrases may occupy the core position of the sentence and convey the main semantic content, while other words may play a modifying or supplementary role, and have relatively less impact on the overall semantics. In this way, the actual meaning of the words can be understood more deeply based on their grammatical characteristics, the understanding of the text content can be strengthened, and it can help improve the accuracy of information interpretation in the approval process. Using this analysis method based on grammatical depth, the approval request processing process can be further optimized to ensure that key information is given due attention.

[0050] Specifically, in a specific example of the present application, the semantic association window search subunit 132 is used to: first, extract the grammatical depth implicit representation value of the first approval request word granularity semantic embedding coding vector in the sequence of the approval request word granularity semantic embedding coding vector as the starting position of the medium-granularity semantic association window; then, along the sequence distribution of the approval request word granularity grammatical depth implicit representation value, find the approval request word granularity grammatical depth implicit representation value that is closest to the grammatical depth implicit representation value of the first approval request word granularity semantic embedding coding vector as the ending position of the medium-granularity semantic association window; finally, based on the starting position of the medium-granularity semantic association window and the ending position of the medium-granularity semantic association window, determine the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector from the sequence of the approval request word granularity semantic embedding coding vector, which is expressed by the formula:

[0051] w i～j = arg min j {|e i -e k |}

[0052] Among them, e k is the grammatical depth implicit representation value of the kth approval request word granular semantic embedding encoding vector in the sequence of the approval request word granular semantic embedding encoding vector, |·| represents taking the absolute value, arg min represents the index corresponding to the minimum value, w i～j Indicates the v i The medium-grained semantic association window, i is the v i The position index, j, is the same as v i The grammatical depth implicitly represents the position index of the approval request word granularity value that is closest to the grammatical depth implicitly represents the value.

[0053] It should be understood that by setting the semantic association window reasonably, it is possible to strengthen the semantic features of words while ensuring that key contextual information is not lost and avoiding interference caused by introducing too much irrelevant information. This helps to accurately capture the semantic connection of a word with a moderate scale between surrounding words in a specific context, thereby enhancing the model's ability to understand complex semantic structures and simplifying the calculation process.

[0054] Specifically, in a specific example of the present application, the contextual semantic association strengthening subunit 133 is used to: first, calculate the semantic association scores of each approval request word granularity semantic embedding coding vector in the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector relative to the first approval request word granularity semantic embedding coding vector to obtain a sequence of first approval request word granularity semantic association scores; then, normalize the sequence of the first approval request word granularity semantic association scores to obtain a sequence of normalized first approval request word granularity semantic association scores; finally, using the sequence of normalized first approval request word granularity semantic association scores as a sequence of weights, calculate the position-weighted sum between each approval request word granularity semantic embedding coding vector in the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector to obtain the medium-granularity semantically strengthened approval request word granularity semantic embedding coding vector corresponding to the first approval request word granularity semantic embedding coding vector, which is expressed as follows:

[0055]

[0056] in, represents matrix multiplication operation, v k is the kth approval request word granularity semantic embedding encoding vector in the sequence representing the approval request word granularity semantic embedding encoding vector, v t is the score reference vector, w t is the scoring reference weight matrix, b t is the score bias vector, exp(·) is the natural exponential function, and v i ' indicates that the v i The corresponding medium-granularity semantically enhanced approval request word-granularity semantic embedding encoding vector.

[0057] Here, after determining the medium-granularity semantic association window, the context information in the window is further used to optimize the semantic representation of each word, thereby achieving medium-granularity contextual semantic enhancement of the granularity semantic embedding encoding vector of each approval request word. That is, based on the semantic and grammatical connection between each word in the approval request parsing result and other words in a specific window, the feature representation of these words is adjusted to more accurately reflect the actual meaning carried in the current context. In this way, the ability to understand the long-range semantic dependency relationship in the approval request parsing result can be significantly improved, thereby improving the accuracy of the semantic expression of each word.

[0058] In the above aviation enterprise standardization management system, the approver matching unit 140 is used to determine the type of the first-level approver based on the contextual semantic features of the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector. Figure 4FIG. 1 is a block diagram of an approver matching unit in an aviation enterprise standardization management system according to an embodiment of the present application. Figure 4 As shown, the approver matching unit 140 includes: a global context semantic encoding subunit 141, which is used to perform global context semantic association encoding on the sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding encoding vectors to obtain an approval request context semantic encoding vector; an approver type determination subunit 142, which is used to input the approval request context semantic encoding vector into a classifier-based intelligent approval module to obtain an approval result, and the approval result is used to represent the type label of the first-level approver.

[0059] Specifically, in a specific example of the present application, the global context semantic encoding subunit 141 is used to: input the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding encoding vector into the context encoder based on the converter module to obtain the approval request context semantic encoding vector. It should be understood that the present application takes into account that the semantic information representation based on word granularity alone cannot fully capture the more complex semantic structure and contextual relationship in the approval request parsing result. Therefore, in order to further understand the complete semantics of the approval request from a global perspective, the present application introduces a context encoder based on the converter module to perform global context association encoding and information integration on the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding encoding vector. Those of ordinary skill in the art should know that the converter module can simultaneously focus on different positions in the input sequence through the self-attention mechanism and position encoding, and perform parallel calculations on them, so as to capture the long-distance semantic dependency and context information in the text sequence, and perform comprehensive semantic interaction and information integration on each word in the entire approval request parsing result, thereby achieving a comprehensive understanding and representation of the approval request context information and generating an approval request context semantic encoding vector.

[0060] Specifically, in a specific example of the present application, the approver type determination subunit 142 is used to: use the fully connected layer of the intelligent approval module to fully connect the approval request context semantic encoding vector to obtain the approval request context semantic fully connected encoding vector; input the approval request context semantic fully connected encoding vector into the Softmax classification function of the intelligent approval module to obtain the probability value of the approval request context semantic encoding vector belonging to each classification label, wherein the classification label is used to represent the type of the first-level approver; and determine the classification label corresponding to the largest probability value as the approval result. Specifically, the classifier establishes a mapping relationship model between the semantic features of the approval request and the type of the first-level approver by learning a large amount of annotated approval request data. In actual application, when the approval request context semantic encoding vector is input into the classifier, the classifier classifies and predicts the approval request context semantic encoding vector by using the mapping relationship model learned in the training process, so as to accurately infer the type label of the first-level approver that best matches the current approval request, such as "Purchasing Department Manager", "Technical Director", "Financial Director", etc. In this way, the system can automatically route the approval request to the corresponding approver based on the approval results, realize the automation of the approval process, and thus greatly improve the approval efficiency and accuracy.

[0061] In a preferred example of the present application, inputting the approval request context semantic encoding vector into a classifier-based intelligent approval module to obtain an approval result includes:

[0062] First, the distance between each pair of feature values ​​of the approval request context semantic encoding vector is calculated, such as the L2 distance, and the square root of the distance is taken to obtain the approval request context semantic encoding distance representation matrix, which is expressed as follows:

[0063]

[0064] Among them, D i,j represents the element value of the (i, j)th position in the semantic encoding distance representation matrix of the approval request context, x i 、x j denote the feature values ​​of the i-th position and the j-th position in the approval request context semantic encoding vector, d(·,·) denotes the distance metric function, and X denotes the approval request context semantic encoding vector;

[0065] Secondly, the approval request context semantic coding auto-association matrix of the approval request context semantic coding vector as a row vector is obtained, which is expressed by the formula:

[0066]

[0067] Where D′ represents the self-association matrix of the context semantic encoding of the approval request, and X is a row vector, (·) T represents the transpose of a vector, Represents matrix multiplication;

[0068] Then, the approval request context semantic coding vector is matrix-multiplied with the approval request context semantic coding distance representation matrix to obtain the approval request context semantic coding primary mapping vector, which is expressed as:

[0069]

[0070] Among them, X′ represents the first-level mapping vector of the approval request context semantic encoding, and D represents the distance representation matrix of the approval request context semantic encoding;

[0071] Next, the approval request context semantic coding primary mapping vector is matrix-multiplied with the matrix product of the approval request context semantic coding distance representation matrix and the approval request context semantic coding self-association matrix to obtain the approval request context semantic coding multi-level mapping vector, which is expressed as follows:

[0072]

[0073] Where X″ represents the multi-level mapping vector of the semantic encoding of the approval request context;

[0074] Then, the approval request context semantic coding multi-level mapping vector is interpolated with the approval request context semantic coding associated eigenvector composed of the eigenvalues ​​of the approval request context semantic coding self-association matrix to obtain an optimized approval request context semantic coding vector, wherein interpolation or zero padding is performed when the eigenvalue is insufficient;

[0075] Finally, the optimized approval request context semantic encoding vector is input into a classifier-based intelligent approval module to obtain an approval result.

[0076] Specifically, the present application takes into account that each medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector in the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector respectively represents the approval request word granularity semantic embedding coding features based on local attention enhancement. When performing context encoding based on the converter module, the multi-head self-attention mechanism is essentially equivalent to a secondary attention mechanism, which will lead to redundant attention encoding and cause the loss of contextual fine-grained semantic feature instance decision of the approval request context semantic coding vector, thereby affecting the accuracy of the approval result obtained by the classifier-based intelligent approval module.

[0077] Therefore, the present application uses a linear target mapping representation based on the similarity distance representation matrix of the approval request context semantic coding vector to perform a secondary target mapping representation based on a multi-level distribution hierarchy for the self-correlation complete similarity instantiation of the approval request context semantic coding vector, and compensates for the negative impact factor of association mismatch through the association fusion kernel bias to improve the degree of instance determination of the feature value of the approval request context semantic coding vector under similarity constraints, that is, the degree of significance of the feature value as an instance for classification regression determination, thereby improving the accuracy of the approval result obtained by the approval request context semantic coding vector through a classifier-based intelligent approval module.

[0078] After obtaining the approval result, that is, determining the type label of the first-level approver, the system needs to screen out qualified candidates from the company's internal database based on this label. This not only relies on a role-matching approach, but also uses the company's internal organizational structure tree and job information in the standardized module to find roles or positions that match the label. For example, if the label is "maintenance engineer", the system will find all employees with this title; it also considers the candidate's professional skills and past experience. By analyzing historical data, the system can identify which approvers have performed well in handling similar requests and recommend these candidates first. In addition, in order to avoid overloading individual approvers, the system will also check the current workload of candidates and select those who have enough time and energy to handle new requests.

[0079] After the approvers are identified, an effective information delivery mechanism must be established to ensure that the approval request can be delivered to the relevant personnel in a timely manner. Push notification is an important part of this. Use email, instant messaging tools or a dedicated approval management platform to send notifications to the selected approvers to inform them of pending requests. The notification content should contain the necessary background information and operation instructions so that the approvers can quickly understand the situation and take action. At the same time, task allocation is also crucial. The approval request is formally assigned to the designated approver and marked as a to-do item in the company's task management system, so that the approver will not miss any important request. Permission settings should also not be ignored. Ensure that the approver has all the permissions required to view and process the request, including access to relevant documents, modification of data, etc., and set appropriate restrictions to prevent unauthorized operations. The entire information delivery mechanism is designed to ensure that approval requests can reach the correct approvers quickly and accurately, and ensure that the approvers have sufficient resources and support to complete the task.

[0080] In summary, the aviation enterprise standardization management system based on the embodiment of the present application is explained. When receiving an approval request, it uses natural language processing technology to parse the approval request to extract key information such as the initiator information, request type, and approval content details. Then, the approval request parsing result is subjected to semantic embedding encoding based on word granularity and local context semantic association optimization to achieve a deep understanding of the approval request, thereby intelligently matching the appropriate first-level approver type based on the contextual semantic information of the approval request parsing result. In this way, the approval path can be dynamically adjusted according to the specific content and background of the approval request, and the most appropriate approver can be selected, so as to flexibly respond to various approval requests and improve approval efficiency and decision-making quality.

[0081] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0082] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0083] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0084] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0085] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A standardized management system for aviation enterprises, comprising: A standardization module, used to load a standardized organizational structure tree, in which the organizational structures in the standardized organizational structure tree are associated with upper and lower levels through parent IDs; The original organizational structure module is used to load the company organizational structure tree. The organizational structure in the company organizational structure tree is associated with the upper and lower levels through the parent ID. When selecting the company level or branch level to create a new organizational structure node, the subordinate department and position data are added according to the preset nodes in the standardization module; the association module is used to correspond the nodes in the standardization module to the nodes in the original organizational structure module. Through the association relationship between the standardization module and the original organizational structure module, the association operations in the authorization, approval, modification, and review processes in each level are realized. It is characterized in that the association module includes: An approval request parsing unit, used to parse the received approval request to obtain an approval request parsing result; A semantic embedding coding unit, used for performing word-granular semantic embedding coding on the approval request parsing result to obtain a sequence of word-granular semantic embedding coding vectors of the approval request; A medium-granularity semantic association optimization unit, used for performing medium-granularity semantic association constraint optimization on the sequence of approval request word granularity semantic embedding coding vectors to obtain a sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding coding vectors; The approver matching unit is used to determine the type of the first-level approver based on the contextual semantic features of the sequence of the medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector.

2. The aviation enterprise standardization management system according to claim 1, characterized in that: The semantic embedding encoding unit is used to: After word segmentation processing is performed on the approval request parsing result, the result is input into a word semantic embedding encoder based on the Bert model to obtain a sequence of word granularity semantic embedding encoding vectors of the approval request.

3. The aviation enterprise standardization management system according to claim 2, characterized in that: The medium-granularity semantic association optimization unit includes: A syntax depth analysis subunit, used for performing syntax depth analysis on each approval request word granularity semantic embedding coding vector in the sequence of approval request word granularity semantic embedding coding vectors to obtain a sequence distribution of approval request word granularity syntax depth implicit representation values; A semantic association window search subunit, used to determine the medium-granularity semantic association window of each approval request word granularity semantic embedding coding vector in the sequence of the approval request word granularity semantic embedding coding vector based on the sequence distribution of the approval request word granularity grammatical depth implicit representation value; The context semantic association strengthening subunit is used to perform medium-granularity context semantic association strengthening on each approval request word granularity semantic embedding coding vector based on the medium-granularity semantic association window of each approval request word granularity semantic embedding coding vector to obtain a sequence of the medium-granularity semantically strengthened approval request word granularity semantic embedding coding vectors.

4. The aviation enterprise standardization management system according to claim 3, characterized in that: The syntax depth analysis subunit is used to: Mapping each approval request word granularity semantic embedding coding vector in the sequence of approval request word granularity semantic embedding coding vectors to a hyperbolic space to obtain a sequence of hyperbolic space approval request word granularity semantic embedding coding vectors; The grammatical depth implicit representation value of each hyperbolic space approval request word granularity semantic embedding coding vector in the sequence of the hyperbolic space approval request word granularity semantic embedding coding vector is calculated to obtain the sequence distribution of the approval request word granularity grammatical depth implicit representation value.

5. The aviation enterprise standardization management system according to claim 4, characterized in that: The semantic association window search subunit is used to: Extracting the grammatical depth implicit representation value of the first approval request word granularity semantic embedding coding vector in the sequence of approval request word granularity semantic embedding coding vectors as the starting position of the medium granularity semantic association window; Along the sequence distribution of the grammatical depth implicit representation value of the approval request word granularity, find the grammatical depth implicit representation value of the approval request word granularity that is closest to the grammatical depth implicit representation value of the first approval request word granularity semantic embedding coding vector as the termination position of the medium granularity semantic association window; Based on the starting position of the medium-granularity semantic association window and the ending position of the medium-granularity semantic association window, the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector is determined from the sequence of the approval request word granularity semantic embedding coding vectors.

6. The aviation enterprise standardization management system according to claim 5, characterized in that: The context semantic association strengthening subunit is used to: Calculating the semantic association scores of each approval request word granularity semantic embedding coding vector in the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector relative to the first approval request word granularity semantic embedding coding vector to obtain a sequence of first approval request word granularity semantic association scores; Normalizing the sequence of the first approval request word granularity semantic association scores to obtain a sequence of normalized first approval request word granularity semantic association scores; Taking the sequence of normalized first approval request word granularity semantic association scores as the sequence of weights, the position-weighted sum between each approval request word granularity semantic embedding coding vector in the medium-granularity semantic association window of the first approval request word granularity semantic embedding coding vector is calculated to obtain the medium-granularity semantically enhanced approval request word granularity semantic embedding coding vector corresponding to the first approval request word granularity semantic embedding coding vector.

7. The aviation enterprise standardization management system according to claim 6, characterized in that: The approver matching unit includes: A global context semantic encoding subunit, used for performing global context semantic association encoding on the sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding encoding vectors to obtain an approval request context semantic encoding vector; The approver type determination subunit is used to input the approval request context semantic coding vector into the classifier-based intelligent approval module to obtain an approval result, and the approval result is used to represent the type label of the first-level approver.

8. The aviation enterprise standardization management system according to claim 7, characterized in that: The global context semantic encoding subunit is used to: The sequence of medium-granularity semantically enhanced approval request word granularity semantic embedding encoding vectors is input into a context encoder based on a converter module to obtain the approval request context semantic encoding vector.

9. The aviation enterprise standardization management system according to claim 8, characterized in that: The approving personnel type determination subunit is used to: Using the fully connected layer of the intelligent approval module to perform fully connected encoding on the approval request context semantic encoding vector to obtain the approval request context semantic fully connected encoding vector; Inputting the approval request context semantic fully connected encoding vector into the Softmax classification function of the intelligent approval module to obtain the probability value of the approval request context semantic encoding vector belonging to each classification label, wherein the classification label is used to indicate the type of the first-level approver; The classification label corresponding to the largest probability value among the probability values ​​is determined as the approval result.

Images