Process approval method and system based on attached multi-dimensional structure data

Abstract

The invention discloses a process approval method and system based on attached multi-dimensional structure data. The method comprises the steps of obtaining a to-be-approved process and corresponding attached approval data; determining data structure information of the approval attached data based on a multi-dimensional data structure algorithm; based on a data assembly algorithm, generating multi-dimensional structure data corresponding to the approval attached data according to the data structure information; and according to the to-be-approved process and the multi-dimensional structure data, based on an approval rule, determining an approval result corresponding to the to-be-approved process. Therefore, data can be accurately extracted and structured in a complex approval process, and automation, accuracy and high efficiency of an approval result are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a process approval method and system based on attached multi-dimensional structure data. Background Art

[0002] Process approval business is an unavoidable requirement in the process of information system construction. In a process approval business, a process generally needs to be bound to specific approval data to help the approver understand its business content and approval requirements, so as to assist in the efficient completion of the approval business. However, in the existing process approval technology, the approval data attached to the approval process is often too simple in data structure to represent more complex and multi-dimensional data content, or requires a file with a higher data volume to represent the data content. Obviously, the accuracy and efficiency of its process approval are low, and the overall automation of the process approval business is lacking. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a process approval method and system based on attached multi-dimensional structured data, which can accurately extract and structure data in complex approval processes to ensure the automation, accuracy and efficiency of approval results.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a process approval method based on attached multi-dimensional structure data, the method comprising: Get the pending approval process and the corresponding approval accompanying data; Determine the data structure information of the approval accompanying data based on a multi-dimensional data structure algorithm; Based on the data assembly algorithm, generate multi-dimensional structure data corresponding to the approval accompanying data according to the data structure information; According to the pending approval process and the multi-dimensional structure data, based on approval rules, an approval result corresponding to the pending approval process is determined.

[0005] As an optional implementation, in the first aspect of the present invention, the determining the data structure information of the approval accompanying data based on the multi-dimensional data structure algorithm includes: Determine all data types corresponding to the approval accompanying data; Determine a structure recognition neural network corresponding to each of the data types; Inputting the approval accompanying data into each of the structure recognition neural networks to obtain a plurality of structure recognition results; According to the multiple structure recognition results, data structure information of the approval accompanying data is determined.

[0006] As an optional implementation manner, in the first aspect of the present invention, determining the data structure information of the approval attachment data according to the multiple structure recognition results includes: Calculate the intersection in all the structure recognition results to obtain basic structure information; For each non-intersection recognition result that is not in the intersection among all the structure recognition results, calculate the number of occurrences of this non-intersection recognition result in all the structure recognition results; Calculate the ratio of the number of occurrences to the total number of structures in all the structure recognition results to obtain the priority parameter corresponding to this non-intersection recognition result; Filter out the non-intersection recognition results with the priority parameter greater than the parameter threshold from all the non-intersection recognition results to obtain multiple priority recognition results; Calculate the union of all the priority recognition results and the basic structure information to obtain the data structure information of the approval attachment data; the data structure information includes data dimension, dimension annotation rule, in-dimension normalization parameter, and in-dimension encryption parameter.

[0007] As an optional implementation manner, in the first aspect of the present invention, the data type is PDF data, image data, text data, audio data, or video data; the structure recognition neural network is trained by a training data set including multiple corresponding training input data of the data types and corresponding structure parameter annotations.

[0008] As an optional implementation manner, in the first aspect of the present invention, generating the multi-dimensional structure data corresponding to the approval attachment data based on the data assembly algorithm includes: According to the data structure information and the corresponding relationship between the preset structure and data grouping rules, determine the corresponding grouping rule information; Group the approval attachment data according to the grouping rule information to obtain multiple data groups; Process each data group according to the annotation rule, normalization parameter, and encryption parameter corresponding to the data structure information to obtain processed data groups; Assemble all the processed data groups to obtain the multi-dimensional structure data corresponding to the approval attachment data.

[0009] As an optional implementation manner, in the first aspect of the present invention, the multi-dimensional structure data is data in YAML format, JSON format, XML format, or binary form.

[0010] As an optional implementation manner, in the first aspect of the present invention, determining the approval result corresponding to the to-be-approved process based on the approval rules according to the to-be-approved process and the multi-dimensional structure data includes: Determine the process information corresponding to the to-be-approved process; Input the process information into a preset process classifier network to obtain the approval rule type corresponding to the to-be-approved process; Determine the approval prediction neural network corresponding to the approval rule type from multiple preset models; Input the multi-dimensional structure data and the process information into the approval prediction neural network to obtain the output approval result; the approval result is sent to the terminal device of the approver for display and reference by the approver.

[0011] As an optional implementation manner, in the first aspect of the present invention, the process information includes historical approval records, historical approvers, process request content, and process-related business information; the process classifier network is trained through a training data set including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained through a training data set including multiple training multi-dimensional structure data corresponding to the approval rule type and corresponding approval result annotations.

[0012] A second aspect of the embodiments of the present invention discloses a process approval system based on attached multi-dimensional structure data, and the system includes: An acquisition module, configured to acquire a to-be-approved process and corresponding approval attached data; An identification module, configured to determine the data structure information of the approval attached data based on a multi-dimensional data structure algorithm; A generation module, configured to generate multi-dimensional structure data corresponding to the approval attached data according to the data structure information based on a data assembly algorithm; An approval module, configured to determine the approval result corresponding to the to-be-approved process based on the approval rules according to the to-be-approved process and the multi-dimensional structure data.

[0013] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the identification module determines the data structure information of the approval attached data based on a multi-dimensional data structure algorithm includes: Determine all data types corresponding to the approval attached data; Determine the structure identification neural network corresponding to each data type; Input the approval attached data into each structure identification neural network to obtain multiple structure identification results; Determine the data structure information of the approval attached data according to the multiple structure recognition results.

[0014] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the recognition module determines the data structure information of the approval attached data according to the multiple structure recognition results includes: Calculate the intersection in all the structure recognition results to obtain the basic structure information; For each non-intersection recognition result that is not in the intersection among all the structure recognition results, calculate the number of occurrences of this non-intersection recognition result in all the structure recognition results; Calculate the ratio of the number of occurrences to the total number of structures in all the structure recognition results to obtain the priority parameter corresponding to this non-intersection recognition result; Screen out the non-intersection recognition results with the priority parameter greater than the parameter threshold from all the non-intersection recognition results to obtain multiple priority recognition results; Calculate the union of all the priority recognition results and the basic structure information to obtain the data structure information of the approval attached data; the data structure information includes data dimension, dimension annotation rule, in-dimension normalization parameter, and in-dimension encryption parameter.

[0015] As an optional implementation manner, in the second aspect of the present invention, the data type is PDF data, image data, text data, audio data, or video data; the structure recognition neural network is trained by a training data set including multiple corresponding training input data of the data types and corresponding structure parameter annotations.

[0016] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the generation module generates the multi-dimensional structure data corresponding to the approval attached data based on the data assembly algorithm according to the data structure information includes: Determine the corresponding grouping rule information according to the data structure information and the corresponding relationship between the preset structure and data grouping rules; Group the approval attached data according to the grouping rule information to obtain multiple data groups; Process each data group according to the annotation rule, normalization parameter, and encryption parameter corresponding to the data structure information to obtain the processed data group; Assemble all the processed data groups to obtain the multi-dimensional structure data corresponding to the approval attached data.

[0017] As an optional implementation manner, in the second aspect of the present invention, the multi-dimensional structure data is in the form of YAML format, JSON format, XML format, or binary.

[0018] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the approval module determines the approval result corresponding to the to-be-approved process based on the approval rules according to the to-be-approved process and the multi-dimensional structured data includes: Determine the process information corresponding to the to-be-approved process; Input the process information into a preset process classifier network to obtain the approval rule type corresponding to the to-be-approved process; Determine the approval prediction neural network corresponding to the approval rule type from multiple preset models; Input the multi-dimensional structured data and the process information into the approval prediction neural network to obtain the output approval result; the approval result is sent to the terminal device of the approver for display and reference by the approver.

[0019] As an optional implementation manner, in the second aspect of the present invention, the process information includes historical approval records, historical approvers, process request content, and process-related business information; the process classifier network is trained through a training data set including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained through a training data set including multiple corresponding training multi-dimensional structured data corresponding to the approval rule type and corresponding approval result annotations.

[0020] The third aspect of the present invention discloses another process approval system based on attached multi-dimensional structured data, and the system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes some or all of the steps in the process approval method based on attached multi-dimensional structured data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute some or all of the steps in the process approval method based on attached multi-dimensional structured data disclosed in the first aspect of the present invention when called.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: By obtaining the to-be-approved process and the corresponding approval attached data, combining the multi-dimensional data structure algorithm to determine the data structure information of the approval attached data, generating multi-dimensional structured data through the data assembly algorithm, and processing the to-be-approved process based on the approval rules, the present invention can accurately extract and structure data in a complex approval process, ensuring the automation, accuracy, and efficiency of the approval result. Brief Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 It is a flowchart of a process approval method based on attaching multi-dimensional structure data disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural diagram of a process approval system based on attaching multi-dimensional structure data disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural diagram of another process approval system based on attaching multi-dimensional structure data disclosed in an embodiment of the present invention. Detailed Embodiments

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0029] Referring to "embodiments" herein means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0030] The present invention discloses a process approval method and system based on attached multi-dimensional structured data. By obtaining the process to be approved and the corresponding approval attached data, combining with the multi-dimensional data structure algorithm to determine the data structure information of the approval attached data, and generating multi-dimensional structured data through the data assembly algorithm, and processing the process to be approved based on the approval rules, it can accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of the approval results. The following will be described in detail respectively.

[0031] Embodiment 1 Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a process approval method based on attached multi-dimensional structured data disclosed in an embodiment of the present invention. Among them, Figure 1 the described process approval method based on attached multi-dimensional structured data can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the process approval method based on attached multi-dimensional structured data may include the following operations: 101. Obtain the process to be approved and the corresponding approval attached data.

[0032] 102. Based on the multi-dimensional data structure algorithm, determine the data structure information of the approval attached data. 103. Based on the data assembly algorithm, generate the multi-dimensional structured data corresponding to the approval attached data according to the data structure information. 104. According to the process to be approved and the multi-dimensional structured data, based on the approval rules, determine the approval result corresponding to the process to be approved.

[0033] It can be seen that the above-mentioned invention embodiment obtains the process to be approved and the corresponding approval attached data, combines with the multi-dimensional data structure algorithm to determine the data structure information of the approval attached data, and generates multi-dimensional structured data through the data assembly algorithm, and processes the process to be approved based on the approval rules, so as to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of the approval results.

[0034] As an optional embodiment, in the above steps, based on the multi-dimensional data structure algorithm, determining the data structure information of the approval attached data includes: Determine all data types corresponding to the approval attached data; Determine the structure recognition neural network corresponding to each data type; Input the approval attached data into each structure recognition neural network to obtain multiple structure recognition results; According to the multiple structure recognition results, determine the data structure information of the approval attached data.

[0035] It can be seen that through the above optional embodiments, by determining all data types of the approval attached data and using the corresponding structure recognition neural network to perform structure parsing on the data to obtain multiple structure recognition results and comprehensively determine the data structure information of the approval attached data, it is possible to automatically recognize and extract the structural features of complex approval data based on the neural network, improve the accuracy and intelligence level of data structuring processing, assist in accurately extracting and structuring data in complex approval processes, and ensure the automation, accuracy, and efficiency of approval results.

[0036] As an optional embodiment, in the above steps, determining the data structure information of the approval attached data according to multiple structure recognition results includes: Calculating the intersection in all structure recognition results to obtain basic structure information; For each non-intersection recognition result that is not in the intersection in all structure recognition results, calculating the number of occurrences of this non-intersection recognition result in all structure recognition results; Calculating the ratio of the number of occurrences to the total number of structures in all structure recognition results to obtain the priority parameter corresponding to this non-intersection recognition result; Filtering out non-intersection recognition results with a priority parameter greater than the parameter threshold from all non-intersection recognition results to obtain multiple priority recognition results; Calculating the union of all priority recognition results and the basic structure information to obtain the data structure information of the approval attached data; the data structure information includes data dimension, dimension annotation rule, in-dimension normalization parameter, and in-dimension encryption parameter.

[0037] It can be seen that through the above optional embodiments, calculating the intersection of all structure recognition results to obtain basic structure information, calculating priority parameters in combination with the occurrence frequencies of non-intersection recognition results, filtering out high-priority recognition results and merging them with the basic structure information to determine the data structure information of the approval attached data can, in the case of differences in multi-model recognition results, improve the accuracy and stability of data structure recognition based on statistical features and priority screening mechanisms, thereby ensuring the rationality and consistency of data dimension, annotation rule, normalization parameter, and encryption parameter, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy, and efficiency of approval results.

[0038] As an optional embodiment, in the above steps, the data type is PDF data, image data, text data, audio data, or video data; the structure recognition neural network is trained through a training data set including multiple training input data corresponding to the data types and corresponding structure parameter annotations.

[0039] It can be seen that through the above optional embodiments, by predefining PDF data, image data, text data, audio data, or video data as data types, and training a structure recognition neural network using a training data set containing training input data corresponding to the data types and structure parameter annotations, it is possible to ensure that the neural network has accurate structure recognition capabilities for different types of data, thereby improving the adaptability and accuracy of extracting data structure information from approval attachment data, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy, and efficiency of approval results.

[0040] As an optional embodiment, in the above steps, based on a data assembly algorithm, generating multi-dimensional structure data corresponding to approval attachment data according to data structure information includes: Determining corresponding grouping rule information according to the data structure information and the corresponding relationship between preset structures and data grouping rules; Grouping the approval attachment data according to the grouping rule information to obtain multiple data groups; Processing each data group according to the annotation rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain processed data groups; Assembling all the processed data groups to obtain multi-dimensional structure data corresponding to the approval attachment data.

[0041] It can be seen that through the above optional embodiments, by combining data structure information with preset grouping rules, grouping, annotating, normalizing, and encrypting approval attachment data according to data assembly and processing rules, and finally generating multi-dimensional structure data by assembling the processed data groups, it is possible to efficiently normalize and standardize complex data and ensure data security, thereby improving the structuring and operability of approval attachment data, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy, and efficiency of approval results.

[0042] As an optional embodiment, in the above steps, the multi-dimensional structure data is data in YAML format, JSON format, XML format, or binary form.

[0043] In a specific implementation, generating multi-dimensional structure data corresponding to approval attachment data based on a data assembly algorithm can be: Extracting the attachment data in the initiated process, displaying the multi-dimensional data in the form of a two-dimensional table, and then assembling the attachment data into any one of the texts in YAML, JSON, XML, or binary form M vector values (x11, x12, …, x1n), X2(x21, x22, …, x2n), …, Xm(xm1, xm2, …, xmn) of an N-dimensional vector variable X (x1, x2, …, xn) can be described respectively using YAML, JSON, and XML technologies as follows: (A) The YAML notation is as follows: X: - x1: x11 x 2:x12 .................... x n:x1n - x1: x21 x 2:x22 .................... x n:x2n ………………………… - x1: xm1 x 2:xm2 .................... x n:xmn (B) The JSON notation is as follows: { X : {x 1: x 11, x 2: x12, ..............., x n: x1n } {x 1: x 21, x 2: x22, ..............., x n: x2n } …………………… {x 1: x m1, x 2: xm2, ..............., x n: xmn } } (C) The XML notation is as follows: <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE xml>​​ <xml> <x> <x1> x11< / x1> <x2> x12< / x2> ............... <xn>x1n< / xn> < / x> <x> <x1> x21< / x1> <x2> x22< / x2> ............... <xn>x2n< / xn> < / x> ............... <x> <x1>xm1< / x1> <x2>xm2< / x2> ............... <xn>xmn< / xn> < / x> < / xml> While using the three technologies of YAML, JSON, and XML to describe the above data, the data described between any two of them can be converted into each other. That is, the data described in YAML can be converted into the data described in JSON and XML, and vice versa.

[0044] Furthermore, during the approval process, the attached data can be stored in a single binary data item (a single field in a database table), and then the approval process with attached multi-dimensional data is sent to the approver. Specifically, when the approver approves, the attached data is extracted from the binary data item, and the data described in YAML, JSON, and XML is converted into a two-dimensional table for display.

[0045] It can be seen that through the above optional embodiments, the data types of multi-dimensional structured data are defined, which can provide flexible data storage and transmission methods, meet the data interaction requirements between different systems, improve data compatibility and portability, assist in accurately extracting and structuring data in complex approval processes, and ensure the automation, accuracy, and efficiency of approval results.

[0046] As an optional embodiment, in the above steps, according to the approval process and multi-dimensional structured data, based on the approval rules, determining the approval result corresponding to the approval process includes: Determining the process information corresponding to the approval process; Inputting the process information into a preset process classifier network to obtain the approval rule type corresponding to the approval process; Determining the approval prediction neural network corresponding to the approval rule type from multiple preset models; Inputting the multi-dimensional structured data and process information into the approval prediction neural network to obtain the output approval result; the approval result is sent to the terminal device of the approver for display and reference by the approver.

[0047] It can be seen that through the above optional embodiments, by obtaining the process information of the approval process, identifying the corresponding approval rule type through a preset process classifier network, then selecting a suitable approval prediction neural network according to the rule type, inputting the multi-dimensional structured data and process information into the network for prediction, automatically generating the approval result, and sending the result to the terminal device of the approver for display and reference, it realizes accurately extracting and structuring data in complex approval processes, improves the automation degree and approval efficiency of the approval process, reduces manual intervention, and ensures the accuracy and timeliness of the approval result.

[0048] As an alternative embodiment, in the above steps, the process information includes historical approval records, historical approvers, process request content, and business information to which the process belongs; the process classifier network is trained through a training data set including multiple pieces of training process information and corresponding approval rule annotations; the approval prediction neural network is trained through a training data set including multiple pieces of training multi-dimensional structure data corresponding to the corresponding approval rule types and corresponding approval result annotations.

[0049] It can be seen that through the above alternative embodiment, the content of the process information and the training details of the process classification network and the approval prediction network are defined, which helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0050] Embodiment 2 Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a process approval system based on attached multi-dimensional structure data disclosed in an embodiment of the present invention. Among them, Figure 2 the described process approval system based on attached multi-dimensional structure data can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the process approval system based on attached multi-dimensional structure data may include: An acquisition module 201, configured to acquire a process to be approved and corresponding approval attached data.

[0051] An identification module 202, configured to determine the data structure information of the approval attached data based on a multi-dimensional data structure algorithm. A generation module 203, configured to generate multi-dimensional structure data corresponding to the approval attached data according to the data structure information based on a data assembly algorithm. An approval module 204, configured to determine an approval result corresponding to the process to be approved based on the process to be approved and the multi-dimensional structure data and based on approval rules.

[0052] It can be seen that through the above embodiment of the invention, by acquiring a process to be approved and corresponding approval attached data, combining a multi-dimensional data structure algorithm to determine the data structure information of the approval attached data, and generating multi-dimensional structure data through a data assembly algorithm, and processing the process to be approved based on approval rules, it is possible to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0053] As an alternative embodiment, the specific manner in which the identification module determines the data structure information of the approval attached data based on a multi-dimensional data structure algorithm includes: Determine all data types corresponding to the approval attached data; Determine the structure recognition neural network corresponding to each data type; Input the approval attached data into each structure recognition neural network to obtain multiple structure recognition results; Determine the data structure information of the approval attached data according to multiple structure recognition results.

[0054] It can be seen that through the above optional embodiments, by determining all data types of the approval attached data and using the corresponding structure recognition neural network to perform structure analysis on the data to obtain multiple structure recognition results and comprehensively determine the data structure information of the approval attached data, the structural features of complex approval data can be automatically recognized and extracted based on the neural network, improving the accuracy and intelligent level of data structuring processing, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy, and efficiency of approval results.

[0055] As an optional embodiment, the specific manner in which the recognition module determines the data structure information of the approval attached data according to multiple structure recognition results includes: Calculate the intersection in all structure recognition results to obtain the basic structure information; For each non-intersection recognition result that is not in the intersection among all structure recognition results, calculate the number of occurrences of the non-intersection recognition result in all structure recognition results; Calculate the ratio of the number of occurrences to the total number of structures in all structure recognition results to obtain the priority parameter corresponding to the non-intersection recognition result; Screen out the non-intersection recognition results with priority parameters greater than the parameter threshold from all non-intersection recognition results to obtain multiple priority recognition results; Calculate the union of all priority recognition results and the basic structure information to obtain the data structure information of the approval attached data; the data structure information includes data dimension, dimension annotation rule, in-dimension normalization parameter, and in-dimension encryption parameter.

[0056] It can be seen that through the above optional embodiments, calculating the intersection of all structure recognition results to obtain the basic structure information, calculating the priority parameter in combination with the occurrence frequency of non-intersection recognition results, screening out high-priority recognition results and merging them with the basic structure information to determine the data structure information of the approval attached data, can improve the accuracy and stability of data structure recognition based on statistical features and priority screening mechanisms in the case of differences in multi-model recognition results, thereby ensuring the rationality and consistency of data dimension, annotation rule, normalization parameter, and encryption parameter, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy, and efficiency of approval results.

[0057] As an optional embodiment, the data type is PDF data, image data, text data, audio data or video data; the structure recognition neural network is trained by a training data set including training input data of multiple corresponding data types and corresponding structure parameter annotations.

[0058] It can be seen that through the above optional embodiments, by predefining PDF data, image data, text data, audio data or video data as the data type, and training the structure recognition neural network with a training data set including training input data of the corresponding data type and structure parameter annotations, it can ensure that the neural network has accurate structure recognition ability for different types of data, thereby improving the adaptability and accuracy of the extraction of data structure information of the approval attached data, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy and efficiency of approval results.

[0059] As an optional embodiment, the specific manner in which the generation module generates multi-dimensional structure data corresponding to the approval attached data based on the data assembly algorithm includes: Determine the corresponding grouping rule information according to the data structure information and the corresponding relationship between the preset structure and data grouping rules; Group the approval attached data according to the grouping rule information to obtain multiple data groups; Process each data group according to the annotation rules, normalization parameters and encryption parameters corresponding to the data structure information to obtain processed data groups; Assemble all the processed data groups to obtain multi-dimensional structure data corresponding to the approval attached data.

[0060] It can be seen that through the above optional embodiments, by combining the data structure information with the preset grouping rules, grouping, annotating, normalizing and encrypting the approval attached data according to the data assembly and processing rules, and finally generating multi-dimensional structure data by assembling the processed data groups, it can efficiently normalize and standardize complex data and ensure the security of the data, thereby improving the structuring and operability of the approval attached data, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy and efficiency of approval results.

[0061] As an optional embodiment, the multi-dimensional structure data is data in YAML format, JSON format, XML format or binary form.

[0062] It can be seen that through the above optional embodiments, the data types of multi-dimensional structure data are defined, which can provide flexible data storage and transmission methods, meet the data interaction requirements between different systems, improve data compatibility and portability, assist in accurately extracting and structuring data in complex approval processes, and ensure the automation, accuracy and efficiency of approval results.

[0063] As an optional embodiment, the approval module determines the specific manner of the approval result corresponding to the to-be-approved process based on the to-be-approved process and the multi-dimensional structure data according to the approval rules, including: Determine the process information corresponding to the to-be-approved process; Input the process information into a preset process classifier network to obtain the approval rule type corresponding to the to-be-approved process; Determine the approval prediction neural network corresponding to the approval rule type from multiple preset models; Input the multi-dimensional structure data and the process information into the approval prediction neural network to obtain the output approval result; the approval result is sent to the terminal device of the approver for display and reference by the approver.

[0064] It can be seen that through the above optional embodiments, by obtaining the process information of the to-be-approved process, identifying the corresponding approval rule type through a preset process classifier network, then selecting a suitable approval prediction neural network according to the rule type, inputting the multi-dimensional structure data and the process information into the network for prediction, thereby automatically generating the approval result and sending the result to the terminal device of the approver for display and reference, realizing accurate extraction and structuring of data in complex approval processes, improving the automation degree and approval efficiency of the approval process, reducing manual intervention and ensuring the accuracy and timeliness of the approval result.

[0065] As an optional embodiment, the process information includes historical approval records, historical approvers, process request content, and process-related business information; the process classifier network is trained through a training data set including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained through a training data set including multiple training multi-dimensional structure data corresponding to the corresponding approval rule types and corresponding approval result annotations.

[0066] It can be seen that through the above optional embodiments, the content of the process information and the training details of the process classification network and the approval prediction network are defined, assisting in accurately extracting and structuring data in complex approval processes, and ensuring the automation, accuracy and efficiency of approval results.

[0067] Embodiment III Please refer to Figure 3 , Figure 3It is another process approval system based on attached multi-dimensional structure data disclosed in the embodiments of the present invention. Figure 3 The described process approval system based on attached multi-dimensional structure data is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the process approval system based on attached multi-dimensional structure data may include: A memory 301 storing executable program code; A processor 302 coupled to the memory 301; Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the process approval method based on attached multi-dimensional structure data described in Embodiment 1.

[0068] Embodiment 4 The embodiments of the present invention disclose a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the process approval method based on attached multi-dimensional structure data described in Embodiment 1.

[0069] Embodiment 5 The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the process approval method based on attached multi-dimensional structure data described in Embodiment 1.

[0070] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be performed in the particular order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0072] For the convenience of description, when describing the above device, it is divided into various units according to functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0073] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification 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.

[0074] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can 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, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0075] 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, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0078] The memory may include non-permanent storage 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.

[0079] 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 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.

[0080] 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.

[0081] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0082] Each embodiment in this specification is described in a progressive manner. For the identical or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the corresponding parts of the method embodiment.

[0083] Finally, it should be noted that the method and system for process approval based on attached multi-dimensional structure data disclosed in the embodiments of the present invention are only the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A process approval method based on multi-dimensional structure data, characterized in that: The method comprises: Get the pending approval process and the corresponding approval accompanying data; Determine the data structure information of the approval accompanying data based on a multi-dimensional data structure algorithm; Based on the data assembly algorithm, generate multi-dimensional structure data corresponding to the approval accompanying data according to the data structure information; According to the pending approval process and the multi-dimensional structure data, based on approval rules, an approval result corresponding to the pending approval process is determined.

2. The process approval method based on multi-dimensional structure data according to claim 1 is characterized in that: The method of determining the data structure information of the approval accompanying data based on the multi-dimensional data structure algorithm includes: Determine all data types corresponding to the approval accompanying data; Determine a structure recognition neural network corresponding to each of the data types; Inputting the approval accompanying data into each of the structure recognition neural networks to obtain a plurality of structure recognition results; According to the multiple structure recognition results, data structure information of the approval accompanying data is determined.

3. The process approval method based on multi-dimensional structure data according to claim 2 is characterized in that: Determining the data structure information of the approval accompanying data according to the multiple structure recognition results includes: Calculating the intersection of all the structure recognition results to obtain basic structure information; For each non-intersection recognition result that is not in the intersection among all the structure recognition results, calculating the number of occurrences of the non-intersection recognition result among all the structure recognition results; Calculate the ratio of the number of occurrences to the total number of structures in all the structure recognition results to obtain a priority parameter corresponding to the non-intersection recognition result; Filter out non-intersection recognition results whose priority parameters are greater than a parameter threshold from all the non-intersection recognition results to obtain a plurality of priority recognition results; The union of all the priority recognition results and the basic structure information is calculated to obtain the data structure information of the approval accompanying data; the data structure information includes data dimensions, dimension labeling rules, normalization parameters within dimensions, and encryption parameters within dimensions.

4. The process approval method based on multi-dimensional structure data according to claim 2 is characterized in that: The data type is PDF data, image data, text data, audio data or video data; the structure recognition neural network is trained by a training data set including a plurality of corresponding training input data of the data type and corresponding structural parameter annotations.

5. The process approval method based on multi-dimensional structure data according to claim 1 is characterized in that: The method of generating multi-dimensional structure data corresponding to the approval accompanying data based on the data assembly algorithm according to the data structure information includes: Determine corresponding grouping rule information according to the data structure information and the correspondence between the preset structure and the data grouping rule; Grouping the approval-attached data according to the grouping rule information to obtain multiple data groups; Processing each of the data groups according to the labeling rules, normalization parameters and encryption parameters corresponding to the data structure information to obtain a processed data group; All the processed data groups are assembled to obtain multi-dimensional structure data corresponding to the approval accompanying data.

6. The process approval method based on multi-dimensional structure data according to claim 5 is characterized in that: The multidimensional structure data is in YAML format, JSON format, XML format or binary form.

7. The process approval method based on multi-dimensional structure data according to claim 1 is characterized in that: The step of determining the approval result corresponding to the process to be approved based on the process to be approved and the multi-dimensional structure data and based on the approval rules includes: Determine the process information corresponding to the process to be approved; Inputting the process information into a preset process classifier network to obtain the approval rule type corresponding to the process to be approved; Determine an approval prediction neural network corresponding to the approval rule type from a plurality of preset models; The multi-dimensional structure data and the process information are input into the approval prediction neural network to obtain the output approval result; the approval result is sent to the terminal device of the approver for display and reference by the approver.

8. The process approval method based on multi-dimensional structure data according to claim 7 is characterized in that: The process information includes historical approval records, historical approval personnel, process request content and business information to which the process belongs; the process classifier network is trained by a training data set including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained by a training data set including multiple corresponding training multidimensional structure data corresponding to the approval rule types and corresponding approval result annotations.

9. A process approval system based on multi-dimensional structure data, characterized in that: The system comprises: The acquisition module is used to obtain the pending approval process and the corresponding approval accompanying data; An identification module, used to determine the data structure information of the approval accompanying data based on a multi-dimensional data structure algorithm; A generating module, used for generating multi-dimensional structure data corresponding to the approval accompanying data according to the data structure information based on a data assembly algorithm; The approval module is used to determine the approval result corresponding to the process to be approved based on the approval rules according to the process to be approved and the multi-dimensional structure data.

10. A process approval system based on multi-dimensional structure data, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the process approval method based on attached multi-dimensional structure data as described in any one of claims 1-8.

Images