Process Approval Method and System Based on Accompanying Multidimensional Structured Data

Abstract

This invention discloses a process approval method and system based on accompanying multidimensional structured data. The method includes: acquiring a process to be approved and corresponding approval-related data; determining the data structure information of the approval-related data based on a multidimensional data structure algorithm; generating multidimensional structured data corresponding to the approval-related data based on the data structure information using a data assembly algorithm; and determining the approval result corresponding to the process to be approved based on the process to be approved and the multidimensional structured data, and based on approval rules. Therefore, this invention can accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of the approval results.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a process approval method and system based on accompanying multidimensional structured data. Background Technology

[0002] Workflow approval is an unavoidable requirement in the construction of information systems. In a workflow approval process, each process typically needs to be linked to specific approval data to help approvers understand the business content and approval requirements, thus facilitating efficient completion of the approval process. However, in existing workflow approval technologies, the approval data attached to the process to be approved often has an overly simple data structure, unable to represent more complex and multi-dimensional data content, or requires files with larger data volumes to represent the data content. Clearly, the accuracy and efficiency of workflow approval are low, and the overall automation level of workflow approval is lacking. Therefore, existing technologies have shortcomings that urgently need to be addressed. 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 accompanying multi-dimensional structured data, which can accurately extract and structure data in complex approval processes, and ensure the automation, accuracy and efficiency of approval results.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a process approval method based on accompanying multidimensional structured data, the method comprising:

[0005] Obtain the pending approval process and the corresponding approval-related data;

[0006] Based on a multidimensional data structure algorithm, the data structure information of the approval-related data is determined.

[0007] Based on the data assembly algorithm, multi-dimensional structured data corresponding to the approval-related data is generated according to the data structure information;

[0008] Based on the pending approval process and the multidimensional structure data, and based on the approval rules, the approval result corresponding to the pending approval process is determined.

[0009] As an optional implementation, in the first aspect of the present invention, determining the data structure information of the approval-related data based on a multidimensional data structure algorithm includes:

[0010] Determine all data types corresponding to the approval-related data;

[0011] Determine the structure recognition neural network corresponding to each of the aforementioned data types;

[0012] The approval-related data is input into each of the structure recognition neural networks to obtain multiple structure recognition results;

[0013] Based on the multiple structure identification results, the data structure information of the approval-related data is determined.

[0014] As an optional implementation, in the first aspect of the present invention, determining the data structure information of the approval ancillary data based on the plurality of structure identification results includes:

[0015] Calculate the intersection of all the structure identification results to obtain the basic structure information;

[0016] For each non-intersection identification result that is not in the intersection among all the structure identification results, calculate the number of times that non-intersection identification result appears in all the structure identification results;

[0017] Calculate the ratio of the occurrence frequency to the total number of structures in all structure recognition results to obtain the priority parameter corresponding to the non-intersection recognition result;

[0018] From all the non-intersection recognition results, non-intersection recognition results with priority parameters greater than the parameter threshold are selected to obtain multiple priority recognition results;

[0019] Calculate the union of all the priority identification results and the basic structure information to obtain the data structure information of the approval-related data; the data structure information includes data dimensions, dimension labeling rules, intra-dimensional normalization parameters, and intra-dimensional encryption parameters.

[0020] As an optional implementation, 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 using a training dataset that includes multiple training input data corresponding to the data type and corresponding structural parameter annotations.

[0021] As an optional implementation, in the first aspect of the present invention, the step of generating multi-dimensional structured data corresponding to the approval ancillary data based on the data structure information using a data assembly algorithm includes:

[0022] Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, the corresponding grouping rule information is determined;

[0023] The approval-related data is grouped according to the grouping rules to obtain multiple data groups;

[0024] Each data group is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data group.

[0025] All the processed data groups are assembled to obtain the multidimensional structured data corresponding to the approval-related data.

[0026] As an optional implementation, in the first aspect of the invention, the multidimensional structured data is data in YAML format, JSON format, XML format, or binary form.

[0027] As an optional implementation, in the first aspect of the present invention, determining the approval result corresponding to the approval process based on the approval rules according to the approval process to be approved and the multidimensional structure data includes:

[0028] Determine the process information corresponding to the process to be approved;

[0029] The process information is input into a preset process classifier network to obtain the approval rule type corresponding to the process to be approved;

[0030] The approval prediction neural network corresponding to the approval rule type is determined from multiple preset models;

[0031] The multidimensional 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.

[0032] As an optional implementation, in the first aspect of the present invention, 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 using a training dataset including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained using a training dataset including multiple training multidimensional structure data corresponding to the approval rule types and corresponding approval result annotations.

[0033] A second aspect of this invention discloses a workflow approval system based on accompanying multidimensional structured data, the system comprising:

[0034] The acquisition module is used to acquire the pending approval process and the corresponding approval-related data;

[0035] The identification module is used to determine the data structure information of the approval-related data based on a multidimensional data structure algorithm.

[0036] A generation module is used to generate multi-dimensional structured data corresponding to the approval-related data based on the data structure information, using a data assembly algorithm.

[0037] The approval module is used to determine the approval result corresponding to the pending approval process based on the pending approval process and the multidimensional structure data, and on the basis of approval rules.

[0038] As an optional implementation, in a second aspect of the invention, the identification module determines the specific method of the data structure information of the approval-related data based on a multidimensional data structure algorithm, including:

[0039] Determine all data types corresponding to the approval-related data;

[0040] Determine the structure recognition neural network corresponding to each of the aforementioned data types;

[0041] The approval-related data is input into each of the structure recognition neural networks to obtain multiple structure recognition results;

[0042] Based on the multiple structure identification results, the data structure information of the approval-related data is determined.

[0043] As an optional implementation, in a second aspect of the invention, the identification module determines the specific method of the data structure information of the approval-related data based on the plurality of structure identification results, including:

[0044] Calculate the intersection of all the structure identification results to obtain the basic structure information;

[0045] For each non-intersection identification result that is not in the intersection among all the structure identification results, calculate the number of times that non-intersection identification result appears in all the structure identification results;

[0046] Calculate the ratio of the occurrence frequency to the total number of structures in all structure recognition results to obtain the priority parameter corresponding to the non-intersection recognition result;

[0047] From all the non-intersection recognition results, non-intersection recognition results with priority parameters greater than the parameter threshold are selected to obtain multiple priority recognition results;

[0048] Calculate the union of all the priority identification results and the basic structure information to obtain the data structure information of the approval-related data; the data structure information includes data dimensions, dimension labeling rules, intra-dimensional normalization parameters, and intra-dimensional encryption parameters.

[0049] As an optional implementation, 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 using a training dataset that includes multiple training input data corresponding to the data type and corresponding structural parameter annotations.

[0050] As an optional implementation, in a second aspect of the invention, the specific method by which the generation module generates multi-dimensional structured data corresponding to the approval ancillary data based on the data structure information using a data assembly algorithm includes:

[0051] Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, the corresponding grouping rule information is determined;

[0052] The approval-related data is grouped according to the grouping rules to obtain multiple data groups;

[0053] Each data group is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data group.

[0054] All the processed data groups are assembled to obtain the multidimensional structured data corresponding to the approval-related data.

[0055] As an optional implementation, in the second aspect of the invention, the multidimensional structured data is data in YAML format, JSON format, XML format, or binary form.

[0056] As an optional implementation, in a second aspect of the present invention, the approval module determines the specific method of the approval result corresponding to the approval process based on the approval rules, according to the process to be approved and the multidimensional structure data, including:

[0057] Determine the process information corresponding to the process to be approved;

[0058] The process information is input into a preset process classifier network to obtain the approval rule type corresponding to the process to be approved;

[0059] The approval prediction neural network corresponding to the approval rule type is determined from multiple preset models;

[0060] The multidimensional 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.

[0061] As an optional implementation, in the second aspect of the present invention, 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 using a training dataset including multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained using a training dataset including multiple training multidimensional structure data corresponding to the approval rule types and corresponding approval result annotations.

[0062] A third aspect of this invention discloses another workflow approval system based on accompanying multidimensional structured data, the system comprising:

[0063] Memory containing executable program code;

[0064] A processor coupled to the memory;

[0065] The processor calls the executable program code stored in the memory to execute some or all of the steps in the process approval method based on accompanying multidimensional structured data disclosed in the first aspect of the present invention.

[0066] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the process approval method based on accompanying multidimensional structured data disclosed in the first aspect of the present invention.

[0067] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0068] This invention obtains the approval process and corresponding approval-related data, determines the data structure information of the approval-related data by combining a multi-dimensional data structure algorithm, generates multi-dimensional structured data by using a data assembly algorithm, and processes the approval process based on approval rules. This enables accurate extraction and structuring of data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results. Attached Figure Description

[0069] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 This is a flowchart illustrating a process approval method based on accompanying multidimensional structured data disclosed in an embodiment of the present invention.

[0071] Figure 2 This is a schematic diagram of the structure of a process approval system based on accompanying multi-dimensional structured data disclosed in an embodiment of the present invention.

[0072] Figure 3 This is a schematic diagram of another process approval system based on accompanying multi-dimensional structured data disclosed in an embodiment of the present invention. Detailed Implementation

[0073] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0074] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0075] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0076] This invention discloses a process approval method and system based on accompanying multidimensional structured data. By acquiring the process to be approved and the corresponding accompanying approval data, and combining a multidimensional data structure algorithm to determine the data structure information of the accompanying approval data, multidimensional structured data is generated through a data assembly algorithm. Based on approval rules, the process to be approved is processed, thereby accurately extracting and structuring data in complex approval processes, ensuring the automation, accuracy, and efficiency of the approval results. Detailed descriptions follow.

[0077] Example 1

[0078] Please see Figure 1 , Figure 1 This is a flowchart illustrating a workflow approval method based on accompanying multi-dimensional structured data, as disclosed in an embodiment of the present invention. Figure 1 The described workflow approval method based on accompanying multi-dimensional structured data can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, the process approval method based on accompanying multidimensional structured data may include the following operations:

[0079] 101. Obtain the pending approval process and the corresponding approval-related data.

[0080] 102. Based on the multidimensional data structure algorithm, determine the data structure information of the approval-related data.

[0081] 103. Based on the data assembly algorithm, generate multi-dimensional structured data corresponding to the approval-related data according to the data structure information.

[0082] 104. Based on the pending approval process and multidimensional structure data, and according to the approval rules, determine the approval result corresponding to the pending approval process.

[0083] As can be seen, the above-described embodiments of the invention obtain the approval process and the corresponding approval-related data, determine the data structure information of the approval-related data by combining a multi-dimensional data structure algorithm, generate multi-dimensional structured data by a data assembly algorithm, and process the approval process based on the approval rules. This enables accurate extraction and structuring of data in complex approval processes, ensuring the automation, accuracy and efficiency of approval results.

[0084] As an optional embodiment, the step above, determining the data structure information of the approval-related data based on a multidimensional data structure algorithm, includes:

[0085] Determine all data types corresponding to the data attached to the approval process;

[0086] Determine the structure recognition neural network corresponding to each data type;

[0087] The approval-related data is input into each structure recognition neural network to obtain multiple structure recognition results;

[0088] Based on the results of multiple structure identifications, the data structure information of the approval-related data is determined.

[0089] As can be seen, through the above optional embodiments, by determining all data types of the approval-related data and using the corresponding structure recognition neural network to perform structure analysis on the data, multiple structure recognition results are obtained and the data structure information of the approval-related data is comprehensively determined. This enables the automatic identification and extraction of structural features of complex approval data based on neural networks, improving the accuracy and intelligence level of data structuring processing, assisting in the accurate extraction and structuring of data in complex approval processes, and ensuring the automation, accuracy and efficiency of approval results.

[0090] As an optional embodiment, the step described above, determining the data structure information of the approval-related data based on multiple structure identification results, includes:

[0091] Calculate the intersection of all structure identification results to obtain basic structure information;

[0092] For each non-intersection recognition result that is not in the intersection of all structure recognition results, calculate the number of times that non-intersection recognition result appears in all structure recognition results;

[0093] 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;

[0094] From all non-intersection recognition results, select the non-intersection recognition results whose priority parameter is greater than the parameter threshold to obtain multiple priority recognition results;

[0095] Calculate the union of all priority identification results and basic structure information to obtain the data structure information of the approval-related data; the data structure information includes data dimensions, dimension labeling rules, intra-dimensional normalization parameters, and intra-dimensional encryption parameters.

[0096] As can be seen, by calculating the intersection of all structure recognition results to obtain basic structure information through the above optional embodiments, and combining the occurrence frequency of non-intersection recognition results to calculate priority parameters, high-priority recognition results are selected and merged with basic structure information to determine the data structure information of the approval-related data. This can improve the accuracy and stability of data structure recognition based on statistical features and priority screening mechanisms when there are differences in the recognition results of multiple models. This ensures the rationality and consistency of data dimensions, annotation rules, normalization parameters and encryption parameters, and helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy and efficiency of approval results.

[0097] As an optional embodiment, the data type in the above steps is PDF data, image data, text data, audio data, or video data; the structural recognition neural network is trained using a training dataset that includes training input data of multiple corresponding data types and corresponding structural parameter annotations.

[0098] As can be seen, through the above optional embodiments, predefined PDF data, image data, text data, audio data, or video data are used as data types. The structure recognition neural network is trained using training input data containing the corresponding data types and a training dataset with structural parameter annotations. This ensures 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-related data. This helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0099] As an optional embodiment, the step described above, generating multi-dimensional structured data corresponding to the approval-related data based on the data structure information using a data assembly algorithm, includes:

[0100] Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, determine the corresponding grouping rule information;

[0101] The data attached to the approval process is grouped according to the grouping rules to obtain multiple data groups;

[0102] Each data set is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data set;

[0103] All processed data groups are assembled to obtain multidimensional structured data corresponding to the approval-related data.

[0104] As can be seen, through the above optional embodiments, by combining data structure information with preset grouping rules, the approval-related data is grouped, labeled, normalized, and encrypted according to data assembly and processing rules. Finally, multi-dimensional structured data is generated through the assembled and processed data groups. This can efficiently standardize and process complex data and ensure data security, thereby improving the structure and operability of the approval-related data. It also helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0105] As an optional embodiment, the multidimensional structured data in the above steps is data in YAML format, JSON format, XML format, or binary form.

[0106] In a specific implementation plan, the multi-dimensional structured data corresponding to the approval-related data generated based on the data structure information using the data assembly algorithm can be as follows:

[0107] Extract the accompanying data from the initiation process, display the multidimensional data in the form of a two-dimensional table, and then assemble the accompanying data into any text or binary form such as YAML, JSON, or XML.

[0108] A given N-dimensional vector variable X(x1, x2, ..., xn) has M vector values ​​(x11, x12, ..., x1n), X2(x21, x22, ..., x2n), ..., Xm(xm1, xm2, ..., xmn) that can be described using YAML, JSON, and XML technologies respectively:

[0109] (A) The YAML notation is as follows:

[0110] X:

[0111] - x1: x11

[0112] x 2:x12 ................... xn:x1n - x1: x21 x 2:x22 ................... xn:x2n ……………………… - x1: xm1 x 2:xm2 ................... xn:xmn (B) The JSON representation is as follows: { X : [ {x 1 : x 11, x 2 : x12, ............... xn: x1n } {x 1 : x 21, x 2 : x22, ............... xn: x2n } ……………… {x 1: x m1, x 2: xm2, ...............

[0113] xn: xmn

[0114] } ]

[0116] }

[0117] (C) The XML representation is as follows:

[0118] <?xml version="1.0" encoding="UTF-8"?>

[0119] <!DOCTYPE xml>

[0120] <xml>

[0121] <x>

[0122] <x1> x11< / x1>

[0123] <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> ..........................

[0124] <xn> xmn< / xn>

[0125] < / x>

[0126] < / xml>

[0127] While using YAML, JSON, and XML to describe the above data, data described by any two of these technologies can be converted to each other. That is, data described in YAML can be converted to data described in JSON and XML, and vice versa.

[0128] Furthermore, during the approval process, the accompanying data can be stored in a single binary data item (a single field in a database table), and then the pending approval process with accompanying multidimensional data is sent to the approver. Specifically, when the approver approves, they extract the accompanying data from the binary data item and convert the data described in YAML, JSON, or XML into a two-dimensional table for display.

[0129] As can be seen, the above optional embodiments define the data type of multidimensional structured data, provide flexible data storage and transmission methods, meet the data interaction needs 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.

[0130] As an optional embodiment, the step above, determining the approval result corresponding to the process to be approved based on the approval rules, according to the process to be approved and the multidimensional structure data, includes:

[0131] Determine the process information corresponding to the process pending approval;

[0132] Input the process information into the preset process classifier network to obtain the approval rule type corresponding to the process to be approved;

[0133] Determine the approval prediction neural network corresponding to the approval rule type from multiple preset models;

[0134] Multidimensional structural data and 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.

[0135] As can be seen, through the above optional embodiments, by acquiring the process information of the process to be approved, identifying the corresponding approval rule type through a preset process classifier network, and then selecting an appropriate approval prediction neural network according to the rule type, the multi-dimensional structured data and process information are input 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. This achieves accurate extraction and structured data in complex approval processes, improves the automation level and efficiency of the approval process, reduces manual intervention, and ensures the accuracy and timeliness of the approval result.

[0136] As an optional 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 using a training dataset that includes multiple training process information and corresponding approval rule annotations; and the approval prediction neural network is trained using a training dataset that includes multiple corresponding approval rule types, corresponding training multidimensional structure data, and corresponding approval result annotations.

[0137] As can be seen, the above optional embodiments limit the content of process information and the training details of the process classification network and the approval prediction network, which helps to accurately extract and structure data in complex approval processes, and ensure the automation, accuracy and efficiency of approval results.

[0138] Example 2

[0139] Please see Figure 2 , Figure 2 This is a schematic diagram of a workflow approval system based on accompanying multi-dimensional structured data, as disclosed in an embodiment of the present invention. Figure 2 The described workflow approval system based on accompanying multi-dimensional structured data can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the process approval system based on accompanying multidimensional structured data may include:

[0140] Module 201 is used to obtain the pending approval process and the corresponding approval-related data.

[0141] The identification module 202 is used to determine the data structure information of the approval-related data based on a multidimensional data structure algorithm.

[0142] The generation module 203 is used to generate multi-dimensional structured data corresponding to the approval-related data based on the data structure information using a data assembly algorithm.

[0143] The approval module 204 is used to determine the approval result corresponding to the pending approval process based on the approval rules and the pending approval process and multi-dimensional structure data.

[0144] As can be seen, the above-described embodiments of the invention obtain the approval process and the corresponding approval-related data, determine the data structure information of the approval-related data by combining a multi-dimensional data structure algorithm, generate multi-dimensional structured data by a data assembly algorithm, and process the approval process based on the approval rules. This enables accurate extraction and structuring of data in complex approval processes, ensuring the automation, accuracy and efficiency of approval results.

[0145] As an optional embodiment, the identification module determines the specific method of data structure information of the approval-related data based on a multi-dimensional data structure algorithm, including:

[0146] Determine all data types corresponding to the data attached to the approval process;

[0147] Determine the structure recognition neural network corresponding to each data type;

[0148] The approval-related data is input into each structure recognition neural network to obtain multiple structure recognition results;

[0149] Based on the results of multiple structure identifications, the data structure information of the approval-related data is determined.

[0150] As can be seen, through the above optional embodiments, by determining all data types of the approval-related data and using the corresponding structure recognition neural network to perform structure analysis on the data, multiple structure recognition results are obtained and the data structure information of the approval-related data is comprehensively determined. This enables the automatic identification and extraction of structural features of complex approval data based on neural networks, improving the accuracy and intelligence level of data structuring processing, assisting in the accurate extraction and structuring of data in complex approval processes, and ensuring the automation, accuracy and efficiency of approval results.

[0151] As an optional embodiment, the identification module determines the specific method of data structure information of the approval-related data based on multiple structure identification results, including:

[0152] Calculate the intersection of all structure identification results to obtain basic structure information;

[0153] For each non-intersection recognition result that is not in the intersection of all structure recognition results, calculate the number of times that non-intersection recognition result appears in all structure recognition results;

[0154] 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;

[0155] From all non-intersection recognition results, select the non-intersection recognition results whose priority parameter is greater than the parameter threshold to obtain multiple priority recognition results;

[0156] Calculate the union of all priority identification results and basic structure information to obtain the data structure information of the approval-related data; the data structure information includes data dimensions, dimension labeling rules, intra-dimensional normalization parameters, and intra-dimensional encryption parameters.

[0157] As can be seen, by calculating the intersection of all structure recognition results to obtain basic structure information through the above optional embodiments, and combining the occurrence frequency of non-intersection recognition results to calculate priority parameters, high-priority recognition results are selected and merged with basic structure information to determine the data structure information of the approval-related data. This can improve the accuracy and stability of data structure recognition based on statistical features and priority screening mechanisms when there are differences in the recognition results of multiple models. This ensures the rationality and consistency of data dimensions, annotation rules, normalization parameters and encryption parameters, and helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy and efficiency of approval results.

[0158] As an optional embodiment, the data type is PDF data, image data, text data, audio data, or video data; the structural recognition neural network is trained using a training dataset that includes training input data of multiple corresponding data types and corresponding structural parameter annotations.

[0159] As can be seen, through the above optional embodiments, predefined PDF data, image data, text data, audio data, or video data are used as data types. The structure recognition neural network is trained using training input data containing the corresponding data types and a training dataset with structural parameter annotations. This ensures 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-related data. This helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0160] As an optional embodiment, the generation module generates multi-dimensional structured data corresponding to the approval-related data based on the data assembly algorithm and the data structure information in the following specific ways:

[0161] Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, determine the corresponding grouping rule information;

[0162] The data attached to the approval process is grouped according to the grouping rules to obtain multiple data groups;

[0163] Each data set is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data set;

[0164] All processed data groups are assembled to obtain multidimensional structured data corresponding to the approval-related data.

[0165] As can be seen, through the above optional embodiments, by combining data structure information with preset grouping rules, the approval-related data is grouped, labeled, normalized, and encrypted according to data assembly and processing rules. Finally, multi-dimensional structured data is generated through the assembled and processed data groups. This can efficiently standardize and process complex data and ensure data security, thereby improving the structure and operability of the approval-related data. It also helps to accurately extract and structure data in complex approval processes, ensuring the automation, accuracy, and efficiency of approval results.

[0166] As an optional embodiment, the multidimensional structured data is in YAML, JSON, XML, or binary format.

[0167] As can be seen, the above optional embodiments define the data type of multidimensional structured data, provide flexible data storage and transmission methods, meet the data interaction needs 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.

[0168] As an optional implementation, the approval module determines the specific method of 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 structured data, including:

[0169] Determine the process information corresponding to the process pending approval;

[0170] Input the process information into the preset process classifier network to obtain the approval rule type corresponding to the process to be approved;

[0171] Determine the approval prediction neural network corresponding to the approval rule type from multiple preset models;

[0172] Multidimensional structural data and 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.

[0173] As can be seen, through the above optional embodiments, by acquiring the process information of the process to be approved, identifying the corresponding approval rule type through a preset process classifier network, and then selecting an appropriate approval prediction neural network according to the rule type, the multi-dimensional structured data and process information are input 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. This achieves accurate extraction and structured data in complex approval processes, improves the automation level and efficiency of the approval process, reduces manual intervention, and ensures the accuracy and timeliness of the approval result.

[0174] As an optional embodiment, 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 using a training dataset that includes multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained using a training dataset that includes multiple training multidimensional structure data corresponding to multiple corresponding approval rule types and corresponding approval result annotations.

[0175] As can be seen, the above optional embodiments limit the content of process information and the training details of the process classification network and the approval prediction network, which helps to accurately extract and structure data in complex approval processes, and ensure the automation, accuracy and efficiency of approval results.

[0176] Example 3

[0177] Please see Figure 3 , Figure 3 This is another workflow approval system based on accompanying multidimensional structured data disclosed in the embodiments of the present invention. Figure 3 The described workflow approval system based on accompanying multi-dimensional structured data is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the process approval system based on accompanying multidimensional structured data may include:

[0178] Memory 301 storing executable program code;

[0179] Processor 302 coupled to memory 301;

[0180] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the process approval method based on accompanying multidimensional structure data described in Embodiment 1.

[0181] Example 4

[0182] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the process approval method based on accompanying multidimensional structured data described in Embodiment 1.

[0183] Example 5

[0184] This invention discloses 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 perform the steps of the process approval method based on accompanying multidimensional structured data described in Embodiment 1.

[0185] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0186] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0187] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0188] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, 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.

[0189] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0190] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0191] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0192] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0193] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0194] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0195] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0196] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0197] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0198] Finally, it should be noted that the process approval method and system based on accompanying multidimensional structured data disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to 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 accompanying multidimensional structured data, characterized in that, The method includes: Obtain the pending approval process and the corresponding approval-related data; Based on a multidimensional data structure algorithm, the data structure information of the approval-related data is determined, including: Determine all data types corresponding to the approval-related data; Determine the structure recognition neural network corresponding to each of the aforementioned data types; The approval-related data is input into each of the structure recognition neural networks to obtain multiple structure recognition results; Based on the multiple structure recognition results, the data structure information of the approval-related data is determined; Based on the data assembly algorithm, multi-dimensional structured data corresponding to the approval-related data is generated according to the data structure information, including: Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, the corresponding grouping rule information is determined; The approval-related data is grouped according to the grouping rules to obtain multiple data groups; Each data group is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data group. All the processed data groups are assembled to obtain the multidimensional structured data corresponding to the approval-related data. Based on the pending approval process and the multidimensional structure data, and based on the approval rules, the approval result corresponding to the pending approval process is determined.

2. The process approval method based on accompanying multi-dimensional structured data according to claim 1, characterized in that, The step of determining the data structure information of the approval-related data based on the multiple structure recognition results includes: Calculate the intersection of all the structure identification results to obtain the basic structure information; For each non-intersection identification result that is not in the intersection among all the structure identification results, calculate the number of times that non-intersection identification result appears in all the structure identification results; Calculate the ratio of the occurrence frequency to the total number of structures in all structure recognition results to obtain the priority parameter corresponding to the non-intersection recognition result; From all the non-intersection recognition results, non-intersection recognition results with priority parameters greater than the parameter threshold are selected to obtain multiple priority recognition results; Calculate the union of all the priority identification results and the basic structure information to obtain the data structure information of the approval-related data; the data structure information includes data dimensions, dimension labeling rules, intra-dimensional normalization parameters, and intra-dimensional encryption parameters.

3. The process approval method based on accompanying multidimensional structured data according to claim 1, characterized in that, The data types are PDF data, image data, text data, audio data, or video data; the structure recognition neural network is trained using a training dataset that includes multiple training input data corresponding to the data types and corresponding structural parameter annotations.

4. The process approval method based on accompanying multi-dimensional structured data according to claim 1, characterized in that, The multidimensional structured data is in YAML, JSON, XML, or binary format.

5. The workflow approval method based on accompanying multi-dimensional structured data according to claim 1, characterized in that, The step of determining the approval result corresponding to the pending approval process based on the pending approval process and the multidimensional structure data, and based on approval rules, includes: Determine the process information corresponding to the process to be approved; The process information is input into a preset process classifier network to obtain the approval rule type corresponding to the process to be approved; The approval prediction neural network corresponding to the approval rule type is determined from multiple preset models; The multidimensional 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.

6. The process approval method based on accompanying multidimensional structured data according to claim 5, characterized in that, 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 using a training dataset that includes multiple training process information and corresponding approval rule annotations; the approval prediction neural network is trained using a training dataset that includes multiple training multidimensional structure data corresponding to the approval rule types and corresponding approval result annotations.

7. A workflow approval system based on accompanying multidimensional structured data, characterized in that, The system includes: The acquisition module is used to acquire the pending approval process and the corresponding approval-related data; The identification module is used to determine the data structure information of the approval-related data based on a multidimensional data structure algorithm, including: Determine all data types corresponding to the approval-related data; Determine the structure recognition neural network corresponding to each of the aforementioned data types; The approval-related data is input into each of the structure recognition neural networks to obtain multiple structure recognition results; Based on the multiple structure recognition results, the data structure information of the approval-related data is determined; The generation module is used to generate multi-dimensional structured data corresponding to the approval-related data based on the data structure information using a data assembly algorithm, including: Based on the data structure information and the pre-defined correspondence between the structure and data grouping rules, the corresponding grouping rule information is determined; The approval-related data is grouped according to the grouping rules to obtain multiple data groups; Each data group is processed according to the labeling rules, normalization parameters, and encryption parameters corresponding to the data structure information to obtain the processed data group. All the processed data groups are assembled to obtain the multidimensional structured data corresponding to the approval-related data. The approval module is used to determine the approval result corresponding to the pending approval process based on the pending approval process and the multidimensional structure data, and on the basis of approval rules.

8. A workflow approval system based on accompanying multi-dimensional structured data, characterized in that, The system includes: Memory containing 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 accompanying multidimensional structured data as described in any one of claims 1-6.

Images