Instruction Approval Data Processing Method and System Based on Multiple Neural Networks

Abstract

This invention discloses a method and system for processing instruction approval data based on a multi-neural network. The method includes: acquiring multiple pending instruction data issued by multiple approval users within the same time period; determining at least one set of emergency instruction data based on an association clustering grouping algorithm and the multiple pending instruction data; predicting the type of emergency event corresponding to each set of emergency instruction data based on a neural network algorithm; and determining the approval priority of each pending instruction data according to the type of emergency event corresponding to the emergency instruction data set and the user type of the approval user. Therefore, this invention can fully combine instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for processing instruction approval data based on multiple neural networks. Background Technology

[0002] With the development of data processing technology and the promotion of paperless office policies, an increasing number of instruction approval needs are being met through data-driven approval systems. Data-driven approval reduces paper usage and improves efficiency and accuracy, thus gaining widespread adoption. However, existing instruction data approval schemes generally rely on pre-defined hierarchical approval rules and data communication processes, failing to adequately consider using neural network algorithms to classify and predict instruction data in unforeseen circumstances to determine the specific event and priority of the instruction. Consequently, their automation and intelligence levels for handling unforeseen events are lacking, and approval efficiency cannot be guaranteed. Clearly, 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 method and system for processing instruction approval data based on multiple neural networks, which can fully combine instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent determination of approval priorities, so as to improve the efficiency and accuracy of instruction approval.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a method for processing instruction approval data based on a multi-neural network, the method comprising:

[0005] Retrieve data of multiple pending approval instructions issued by multiple approval users within the same time period;

[0006] Based on the association clustering grouping algorithm and the multiple pending approval instruction data, at least one set of emergency instruction data is determined;

[0007] Based on neural network algorithms, predict the type of emergency event corresponding to each set of emergency instruction data;

[0008] Based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user, the approval priority of each instruction data to be approved is determined.

[0009] As an optional implementation, in the first aspect of the present invention, the instruction data to be approved includes instruction text, instruction type, instruction issuance time, and instruction attachments.

[0010] As an optional implementation, in the first aspect of the present invention, determining at least one set of emergency instruction data based on the association clustering grouping algorithm and the plurality of pending approval instruction data includes:

[0011] Based on the prediction algorithm, the urgency level of each pending instruction data is determined.

[0012] Based on a similarity clustering algorithm, the multiple instruction data to be approved are grouped to obtain multiple instruction data sets;

[0013] Calculate the average urgency level of all pending instruction data in each instruction data set to obtain the set urgency parameter corresponding to each instruction data set;

[0014] Based on the set of emergency parameters, at least one emergency instruction data set is selected from the plurality of instruction data sets.

[0015] As an optional implementation, in the first aspect of the invention, determining the urgency level corresponding to each of the pending instruction data based on a prediction algorithm includes:

[0016] The instruction text and instruction attachments of each instruction data to be approved are input into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels;

[0017] and / or,

[0018] For each of the pending instruction data, based on a preset text matching template, the instruction text and the instruction attachment of the pending instruction data are matched to obtain multiple urgent related texts;

[0019] The urgency level of each urgent-related text is determined based on semantic analysis algorithms.

[0020] Calculate the average of the text urgency levels corresponding to all the aforementioned urgency-related texts to obtain the urgency level of the instruction data to be approved.

[0021] As an optional implementation, in the first aspect of the present invention, the grouping of the plurality of pending approval instruction data based on a similarity clustering algorithm to obtain a plurality of instruction data sets includes:

[0022] For any two pending instruction data, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instruction data;

[0023] Calculate the type similarity between the instruction types corresponding to the two pending instruction data;

[0024] Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data;

[0025] Calculate the weighted average of the data similarity, the type similarity, and the time similarity to obtain the correlation similarity between the two pending approval instruction data.

[0026] Based on the association similarity, the multiple pending instruction data are grouped using a clustering grouping algorithm to obtain multiple instruction data sets; wherein, the association similarity between any two pending instruction data in each instruction data set is greater than a first similarity threshold, and the association similarity between any two pending instruction data belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0027] As an optional implementation, in a first aspect of the invention, the step of selecting at least one emergency instruction data set from the plurality of instruction data sets based on the set of emergency parameters includes:

[0028] Sort all the instruction data sets from largest to smallest according to the set emergency parameters to obtain a set sequence;

[0029] Filter out the first preset number of instruction data sets in the set sequence whose emergency parameters are greater than a parameter threshold to obtain at least one emergency instruction data set.

[0030] As an optional implementation, in the first aspect of the present invention, the step of predicting the type of emergency event corresponding to each set of emergency command data based on a neural network algorithm includes:

[0031] For each set of emergency instruction data, each instruction data to be approved in the set of emergency instruction data is input into a trained event prediction neural network to obtain the data event type corresponding to each instruction data to be approved; the event prediction neural network is trained using a training dataset that includes multiple training instruction data and corresponding event type labels.

[0032] The most frequent item among the data event types corresponding to all pending approval instructions in the emergency instruction data set is counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0033] As an optional implementation, in the first aspect of the present invention, determining the approval priority of each pending instruction data according to the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user includes:

[0034] For each pending instruction data, determine the user type of the approving user corresponding to the pending instruction data and determine the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data; when the pending instruction data does not have a corresponding emergency instruction data set, its corresponding emergency event type is an empty identifier;

[0035] Based on the preset correspondence between user types and levels, and the user type corresponding to the instruction data to be approved, determine the user level parameter corresponding to the instruction data to be approved;

[0036] Based on the preset correspondence between event types and levels, and the type of emergency event corresponding to the pending instruction data, determine the event level parameter corresponding to the pending instruction data;

[0037] Calculate the weighted average of the user-level parameters and the event-level parameters to obtain the priority parameter corresponding to the pending approval instruction data;

[0038] The approval priority of each pending instruction is determined based on the priority parameters corresponding to all the pending instruction data; the priority level is directly proportional to the magnitude of the priority parameter.

[0039] A second aspect of this invention discloses an instruction approval data processing system based on a multi-neural network, the system comprising:

[0040] The acquisition module is used to acquire multiple pending approval instructions issued by multiple approval users within the same time period;

[0041] The grouping module is used to determine at least one set of emergency instruction data based on the association clustering grouping algorithm and the multiple pending instruction data;

[0042] The prediction module is used to predict the type of emergency event corresponding to each set of emergency instructions based on a neural network algorithm.

[0043] The determination module is used to determine the approval priority of each instruction data to be approved based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user.

[0044] As an optional implementation, in a second aspect of the present invention, the instruction data to be approved includes instruction text, instruction type, instruction issuance time, and instruction attachments.

[0045] As an optional implementation, in a second aspect of the invention, the grouping module determines at least one set of emergency instruction data based on an association clustering grouping algorithm and the plurality of pending approval instruction data in a specific manner, including:

[0046] Based on the prediction algorithm, the urgency level of each pending instruction data is determined.

[0047] Based on a similarity clustering algorithm, the multiple instruction data to be approved are grouped to obtain multiple instruction data sets;

[0048] Calculate the average urgency level of all pending instruction data in each instruction data set to obtain the set urgency parameter corresponding to each instruction data set;

[0049] Based on the set of emergency parameters, at least one emergency instruction data set is selected from the plurality of instruction data sets.

[0050] As an optional implementation, in a second aspect of the invention, the grouping module determines the specific method by which it determines the urgency level of each pending instruction data based on a prediction algorithm, including:

[0051] The instruction text and instruction attachments of each instruction data to be approved are input into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels;

[0052] and / or,

[0053] For each of the pending instruction data, based on a preset text matching template, the instruction text and the instruction attachment of the pending instruction data are matched to obtain multiple urgent related texts;

[0054] The urgency level of each urgent-related text is determined based on semantic analysis algorithms.

[0055] Calculate the average of the text urgency levels corresponding to all the aforementioned urgency-related texts to obtain the urgency level of the instruction data to be approved.

[0056] As an optional implementation, in the second aspect of the present invention, the grouping module groups the multiple sets of instructions to be approved based on a similarity clustering algorithm to obtain multiple sets of instruction data, including:

[0057] For any two pending instruction data, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instruction data;

[0058] Calculate the type similarity between the instruction types corresponding to the two pending instruction data;

[0059] Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data;

[0060] Calculate the weighted average of the data similarity, the type similarity, and the time similarity to obtain the correlation similarity between the two pending approval instruction data.

[0061] Based on the association similarity, the multiple pending instruction data are grouped using a clustering grouping algorithm to obtain multiple instruction data sets; wherein, the association similarity between any two pending instruction data in each instruction data set is greater than a first similarity threshold, and the association similarity between any two pending instruction data belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0062] As an optional implementation, in a second aspect of the invention, the specific method by which the grouping module selects at least one emergency instruction data set from the plurality of instruction data sets based on the set emergency parameter includes:

[0063] Sort all the instruction data sets from largest to smallest according to the set emergency parameters to obtain a set sequence;

[0064] Filter out the first preset number of instruction data sets in the set sequence whose emergency parameters are greater than a parameter threshold to obtain at least one emergency instruction data set.

[0065] As an optional implementation, in a second aspect of the invention, the prediction module predicts the specific method by which it predicts the type of emergency event corresponding to each set of emergency command data based on a neural network algorithm, including:

[0066] For each set of emergency instruction data, each instruction data to be approved in the set of emergency instruction data is input into a trained event prediction neural network to obtain the data event type corresponding to each instruction data to be approved; the event prediction neural network is trained using a training dataset that includes multiple training instruction data and corresponding event type labels.

[0067] The most frequent item among the data event types corresponding to all pending approval instructions in the emergency instruction data set is counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0068] As an optional implementation, in a second aspect of the invention, the determining module determines the approval priority of each pending instruction data in a specific manner based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user, including:

[0069] For each pending instruction data, determine the user type of the approving user corresponding to the pending instruction data and determine the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data; when the pending instruction data does not have a corresponding emergency instruction data set, its corresponding emergency event type is an empty identifier;

[0070] Based on the preset correspondence between user types and levels, and the user type corresponding to the instruction data to be approved, determine the user level parameter corresponding to the instruction data to be approved;

[0071] Based on the preset correspondence between event types and levels, and the type of emergency event corresponding to the pending instruction data, determine the event level parameter corresponding to the pending instruction data;

[0072] Calculate the weighted average of the user-level parameters and the event-level parameters to obtain the priority parameter corresponding to the pending approval instruction data;

[0073] The approval priority of each pending instruction is determined based on the priority parameters corresponding to all the pending instruction data; the priority level is directly proportional to the magnitude of the priority parameter.

[0074] A third aspect of this invention discloses another instruction approval data processing system based on multiple neural networks, the system comprising:

[0075] Memory containing executable program code;

[0076] A processor coupled to the memory;

[0077] The processor calls the executable program code stored in the memory to execute some or all of the steps in the instruction approval data processing method based on multiple neural networks disclosed in the first aspect of the present invention.

[0078] 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 instruction approval data processing method based on multiple neural networks disclosed in the first aspect of the present invention.

[0079] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0080] This invention can determine at least one set of emergency instructions from multiple pending instructions based on an association clustering grouping algorithm. Then, it predicts the type of emergency event corresponding to each set of emergency instructions based on a neural network algorithm. Based on the type of emergency event and the user type of the approving user, it determines the approval priority of each pending instruction. This invention can fully combine the association of instruction data and the prediction of event type in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval. Attached Figure Description

[0081] 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.

[0082] Figure 1 This is a flowchart illustrating an instruction approval data processing method based on a multi-neural network disclosed in an embodiment of the present invention.

[0083] Figure 2 This is a schematic diagram of the structure of an instruction approval data processing system based on a multi-neural network disclosed in an embodiment of the present invention.

[0084] Figure 3 This is a schematic diagram of another instruction approval data processing system based on a multi-neural network disclosed in an embodiment of the present invention. Detailed Implementation

[0085] 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.

[0086] 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.

[0087] 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.

[0088] This invention discloses a method and system for processing instruction approval data based on multiple neural networks. It can determine at least one set of emergency instructions from multiple pending instruction data using an association clustering grouping algorithm. Then, it predicts the type of emergency event corresponding to each set of emergency instructions based on a neural network algorithm. Finally, it determines the approval priority of each pending instruction based on the type of emergency event and the user type of the approving user. This fully combines the association of instruction data and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval. Detailed explanations follow.

[0089] Example 1

[0090] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for processing instruction approval data based on a multi-neural network, as disclosed in an embodiment of the present invention. Figure 1 The described multi-neural network-based instruction approval data processing method 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 instruction approval data processing method based on multiple neural networks may include the following operations:

[0091] 101. Obtain data of multiple pending approval instructions issued by multiple approval users within the same time period.

[0092] 102. Based on the association clustering grouping algorithm and multiple pending approval instruction data, at least one set of emergency instruction data is determined.

[0093] 103. Based on neural network algorithms, predict the type of emergency event corresponding to each emergency instruction data set.

[0094] 104. Determine the approval priority of each pending instruction data based on the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

[0095] As can be seen, the above-described embodiments of the invention can determine at least one set of emergency instructions from multiple pending instructions based on the association clustering grouping algorithm, then predict the type of emergency event corresponding to each set of emergency instructions based on the neural network algorithm, and determine the approval priority of each pending instructions based on the type of emergency event and the user type of the approving user. This can fully combine the association of instructions data and the prediction of event type in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instructions approval.

[0096] As an optional embodiment, the data of the instruction to be approved in the above steps includes the instruction text, instruction type, instruction issuance time, and instruction attachments.

[0097] As can be seen, the content of the instruction data to be approved is defined through the above optional embodiments to comprehensively characterize the features and characteristics of the instruction data to be approved, which facilitates the subsequent priority determination and helps to fully combine the association of instruction data in emergency situations and the prediction of event types to achieve a more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0098] As an optional embodiment, in the above steps, based on the association clustering grouping algorithm and multiple pending approval instruction data, at least one emergency instruction data set is determined, including:

[0099] Based on the prediction algorithm, the urgency level of each pending instruction data is determined.

[0100] Based on the similarity clustering algorithm, multiple instruction data to be approved are grouped to obtain multiple instruction data sets;

[0101] Calculate the average urgency level of all pending instructions in each instruction data set to obtain the set urgency parameter for each instruction data set;

[0102] Based on the emergency parameters of the set, at least one emergency instruction data set is selected from multiple instruction data sets.

[0103] As can be seen, through the above optional embodiments, the urgency of instruction data can be predicted based on the prediction algorithm, and then multiple instruction data sets can be grouped based on the similarity clustering algorithm. At least one urgent instruction data set can be selected according to the urgency level, which facilitates subsequent priority determination. This helps to fully combine the association of instruction data in emergency situations and the prediction of event types to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0104] As an optional embodiment, the step above, determining the urgency level of each pending instruction data based on a prediction algorithm, includes:

[0105] The instruction text and instruction attachments of each instruction data to be approved are input into the trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; optionally, the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels.

[0106] and / or,

[0107] For each instruction data to be approved, based on a preset text matching template, the instruction text and instruction attachments of the instruction data to be approved are matched to obtain multiple urgent related texts;

[0108] The urgency level of each urgent-related text is determined based on semantic analysis algorithms.

[0109] Calculate the average of the text urgency levels corresponding to all urgency-related texts to obtain the urgency level of the instruction data to be approved.

[0110] As can be seen, the above optional embodiments define a method for predicting or analyzing the urgency level. This method can accurately predict the urgency level of instruction data based on the instruction text and attachments of the instruction data to be approved and a trained instruction urgency prediction neural network, or based on text matching and semantic analysis algorithms. This facilitates subsequent priority determination and helps to fully combine the association of instruction data and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0111] As an optional embodiment, in the above steps, the multiple instruction data to be approved are grouped based on a similarity clustering algorithm to obtain multiple instruction data sets, including:

[0112] For any two pending instructions, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instructions.

[0113] Calculate the type similarity between the instruction types corresponding to the two pending instruction data;

[0114] Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data;

[0115] The weighted average of data similarity, type similarity, and time similarity is calculated to obtain the correlation similarity between the two pending approval instructions.

[0116] Based on association similarity, multiple pending instruction data are grouped using a clustering grouping algorithm to obtain multiple instruction data sets; optionally, the association similarity between any two pending instruction data in each instruction data set is greater than a first similarity threshold, and the association similarity between any two pending instruction data belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0117] As can be seen, through the above optional embodiments, it is possible to calculate the correlation and similarity between the data content of the instruction data to be approved, and to group multiple more related instruction data sets based on the clustering grouping algorithm, which facilitates subsequent priority determination. This helps to fully combine the correlation of instruction data in emergency situations and the prediction of event types to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0118] As an optional embodiment, the step described above, selecting at least one emergency instruction data set from multiple instruction data sets based on the set emergency parameter, includes:

[0119] The set sequence is obtained by sorting all instruction data sets from largest to smallest according to the set emergency parameter;

[0120] Filter out the first preset number of instruction data sets in the set sequence that have an emergency parameter greater than the parameter threshold, and obtain at least one emergency instruction data set.

[0121] As can be seen, through the above optional embodiments, at least one set of emergency instruction data can be selected based on the sorting and filtering of the set of emergency parameters, which facilitates subsequent priority determination and helps to achieve more automatic and intelligent approval priority determination by fully combining instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0122] As an optional embodiment, the step above, predicting the type of emergency event corresponding to each emergency instruction dataset based on a neural network algorithm, includes:

[0123] For each set of emergency instruction data, each instruction data to be approved in the set of emergency instruction data is input into the trained event prediction neural network to obtain the data event type corresponding to each instruction data to be approved; optionally, the event prediction neural network is trained using a training dataset that includes multiple training instruction data and corresponding event type labels.

[0124] The most frequent item among the data event types corresponding to all pending instructions in the emergency instruction dataset is counted to obtain the emergency event type corresponding to the emergency instruction dataset.

[0125] As can be seen, through the above optional embodiments, the data event type corresponding to each instruction data to be approved can be predicted based on the trained event prediction neural network, and the emergency event type corresponding to the emergency instruction data set can be obtained based on the mode statistical filtering, which facilitates the subsequent priority determination. This helps to fully combine the association of instruction data and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0126] As an optional embodiment, the step above, determining the approval priority of each pending instruction data based on the emergency event type corresponding to the emergency instruction data set and the user type of the approving user, includes:

[0127] For each pending instruction data, determine the user type of the approving user corresponding to the pending instruction data and determine the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data; optionally, if the pending instruction data does not have a corresponding emergency instruction data set, its corresponding emergency event type is an empty identifier.

[0128] Based on the preset correspondence between user types and levels, and the user type corresponding to the instruction data to be approved, determine the user level parameter corresponding to the instruction data to be approved;

[0129] Based on the preset correspondence between event types and levels, and the type of emergency event corresponding to the pending instruction data, determine the event level parameter corresponding to the pending instruction data;

[0130] Calculate the weighted average of the user-level parameters and the event-level parameters to obtain the priority parameter corresponding to the pending approval instruction data;

[0131] The approval priority of each pending instruction is determined based on the priority parameters corresponding to all pending instruction data; the priority level is directly proportional to the magnitude of the priority parameter.

[0132] As can be seen, through the above optional embodiments, user-level parameters and event-level parameters can be determined according to the user type of the approving user corresponding to the pending instruction data and the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data. The corresponding priority parameters are then calculated to determine the approval priority. This achieves a more automatic and intelligent approval priority determination by fully combining instruction data association and event type prediction in emergency situations, thereby improving the efficiency and accuracy of instruction approval.

[0133] Example 2

[0134] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an instruction approval data processing system based on a multi-neural network, as disclosed in an embodiment of the present invention. Figure 2 The described multi-neural network-based instruction approval data processing system can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 2 As shown, the instruction approval data processing system based on multiple neural networks may include:

[0135] The acquisition module 201 is used to acquire multiple pending approval instructions issued by multiple approval users within the same time period.

[0136] Grouping module 202 is used to determine at least one set of emergency instruction data based on the association clustering grouping algorithm and multiple pending instruction data.

[0137] The prediction module 203 is used to predict the type of emergency event corresponding to each emergency instruction data set based on a neural network algorithm.

[0138] The determination module 204 is used to determine the approval priority of each pending instruction data based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user.

[0139] As can be seen, the above-described embodiments of the invention can determine at least one set of emergency instructions from multiple pending instructions based on the association clustering grouping algorithm, then predict the type of emergency event corresponding to each set of emergency instructions based on the neural network algorithm, and determine the approval priority of each pending instructions based on the type of emergency event and the user type of the approving user. This can fully combine the association of instructions data and the prediction of event type in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instructions approval.

[0140] As an optional embodiment, the data of the instruction to be approved includes the instruction text, instruction type, instruction issuance time, and instruction attachments.

[0141] As can be seen, the content of the instruction data to be approved is defined through the above optional embodiments to comprehensively characterize the features and characteristics of the instruction data to be approved, which facilitates the subsequent priority determination and helps to fully combine the association of instruction data in emergency situations and the prediction of event types to achieve a more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0142] As an optional embodiment, the grouping module determines at least one set of emergency instruction data based on an association clustering grouping algorithm and multiple pending instruction data in a specific manner, including:

[0143] Based on the prediction algorithm, the urgency level of each pending instruction data is determined.

[0144] Based on the similarity clustering algorithm, multiple instruction data to be approved are grouped to obtain multiple instruction data sets;

[0145] Calculate the average urgency level of all pending instructions in each instruction data set to obtain the set urgency parameter for each instruction data set;

[0146] Based on the emergency parameters of the set, at least one emergency instruction data set is selected from multiple instruction data sets.

[0147] As can be seen, through the above optional embodiments, the urgency of instruction data can be predicted based on the prediction algorithm, and then multiple instruction data sets can be grouped based on the similarity clustering algorithm. At least one urgent instruction data set can be selected according to the urgency level, which facilitates subsequent priority determination. This helps to fully combine the association of instruction data in emergency situations and the prediction of event types to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0148] As an optional embodiment, the grouping module determines the specific method for urgency of each pending instruction data based on a prediction algorithm, including:

[0149] The instruction text and instruction attachments of each instruction data to be approved are input into the trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; optionally, the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels.

[0150] and / or,

[0151] For each instruction data to be approved, based on a preset text matching template, the instruction text and instruction attachments of the instruction data to be approved are matched to obtain multiple urgent related texts;

[0152] The urgency level of each urgent-related text is determined based on semantic analysis algorithms.

[0153] Calculate the average of the text urgency levels corresponding to all urgency-related texts to obtain the urgency level of the instruction data to be approved.

[0154] As can be seen, the above optional embodiments define a method for predicting or analyzing the urgency level. This method can accurately predict the urgency level of instruction data based on the instruction text and attachments of the instruction data to be approved and a trained instruction urgency prediction neural network, or based on text matching and semantic analysis algorithms. This facilitates subsequent priority determination and helps to fully combine the association of instruction data and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0155] As an optional embodiment, the grouping module uses a similarity clustering algorithm to group multiple sets of instruction data to obtain multiple instruction data sets. The specific methods include:

[0156] For any two pending instructions, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instructions.

[0157] Calculate the type similarity between the instruction types corresponding to the two pending instruction data;

[0158] Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data;

[0159] The weighted average of data similarity, type similarity, and time similarity is calculated to obtain the correlation similarity between the two pending approval instructions.

[0160] Based on association similarity, multiple pending instruction data are grouped using a clustering grouping algorithm to obtain multiple instruction data sets; optionally, the association similarity between any two pending instruction data in each instruction data set is greater than a first similarity threshold, and the association similarity between any two pending instruction data belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0161] As can be seen, through the above optional embodiments, it is possible to calculate the correlation and similarity between the data content of the instruction data to be approved, and to group multiple more related instruction data sets based on the clustering grouping algorithm, which facilitates subsequent priority determination. This helps to fully combine the correlation of instruction data in emergency situations and the prediction of event types to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0162] As an optional embodiment, the specific method by which the grouping module selects at least one emergency instruction data set from multiple instruction data sets based on the set emergency parameters includes:

[0163] The set sequence is obtained by sorting all instruction data sets from largest to smallest according to the set emergency parameter;

[0164] Filter out the first preset number of instruction data sets in the set sequence that have an emergency parameter greater than the parameter threshold, and obtain at least one emergency instruction data set.

[0165] As can be seen, through the above optional embodiments, at least one set of emergency instruction data can be selected based on the sorting and filtering of the set of emergency parameters, which facilitates subsequent priority determination and helps to achieve more automatic and intelligent approval priority determination by fully combining instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0166] As an optional embodiment, the prediction module, based on a neural network algorithm, predicts the specific method by which it predicts the type of emergency event corresponding to each emergency instruction dataset, including:

[0167] For each set of emergency instruction data, each instruction data to be approved in the set of emergency instruction data is input into the trained event prediction neural network to obtain the data event type corresponding to each instruction data to be approved; optionally, the event prediction neural network is trained using a training dataset that includes multiple training instruction data and corresponding event type labels.

[0168] The most frequent item among the data event types corresponding to all pending instructions in the emergency instruction dataset is counted to obtain the emergency event type corresponding to the emergency instruction dataset.

[0169] As can be seen, through the above optional embodiments, the data event type corresponding to each instruction data to be approved can be predicted based on the trained event prediction neural network, and the emergency event type corresponding to the emergency instruction data set can be obtained based on the mode statistical filtering, which facilitates the subsequent priority determination. This helps to fully combine the association of instruction data and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, thereby improving the efficiency and accuracy of instruction approval.

[0170] As an optional embodiment, the determining module determines the approval priority of each pending instruction data according to the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user, including:

[0171] For each pending instruction data, determine the user type of the approving user corresponding to the pending instruction data and determine the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data; optionally, if the pending instruction data does not have a corresponding emergency instruction data set, its corresponding emergency event type is an empty identifier.

[0172] Based on the preset correspondence between user types and levels, and the user type corresponding to the instruction data to be approved, determine the user level parameter corresponding to the instruction data to be approved;

[0173] Based on the preset correspondence between event types and levels, and the type of emergency event corresponding to the pending instruction data, determine the event level parameter corresponding to the pending instruction data;

[0174] Calculate the weighted average of the user-level parameters and the event-level parameters to obtain the priority parameter corresponding to the pending approval instruction data;

[0175] The approval priority of each pending instruction is determined based on the priority parameters corresponding to all pending instruction data; the priority level is directly proportional to the magnitude of the priority parameter.

[0176] As can be seen, through the above optional embodiments, user-level parameters and event-level parameters can be determined according to the user type of the approving user corresponding to the pending instruction data and the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data. The corresponding priority parameters are then calculated to determine the approval priority. This achieves a more automatic and intelligent approval priority determination by fully combining instruction data association and event type prediction in emergency situations, thereby improving the efficiency and accuracy of instruction approval.

[0177] Example 3

[0178] Please see Figure 3 , Figure 3 This is another instruction approval data processing system based on multiple neural networks disclosed in the embodiments of the present invention. Figure 3 The described multi-neural network-based instruction approval data processing system is applied in data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the instruction approval data processing system based on multiple neural networks may include:

[0179] Memory 301 storing executable program code;

[0180] Processor 302 coupled to memory 301;

[0181] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the instruction approval data processing method based on multiple neural networks described in Embodiment 1.

[0182] Example 4

[0183] 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 instruction approval data processing method based on a multi-neural network described in Embodiment 1.

[0184] Example 5

[0185] 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 instruction approval data processing method based on multiple neural networks described in Embodiment 1.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0194] 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.

[0195] 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.

[0196] 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 limitations, 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.

[0197] 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.

[0198] 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.

[0199] Finally, it should be noted that the instruction approval data processing method and system based on multiple neural networks 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 method for processing instruction approval data based on multiple neural networks, characterized in that, The method includes: Retrieve data on multiple pending approval instructions issued by multiple approval users within the same time period; the pending approval instruction data includes instruction text, instruction type, instruction issuance time, and instruction attachments; Based on the association clustering grouping algorithm and the multiple pending approval instruction data, at least one set of emergency instruction data is determined, including: Based on a prediction algorithm, the urgency level corresponding to each of the pending approval instruction data is determined; the determination of the urgency level corresponding to each of the pending approval instruction data based on the prediction algorithm includes: The instruction text and instruction attachments of each instruction data to be approved are input into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels; And / or, For each of the pending instruction data, based on a preset text matching template, the instruction text and the instruction attachment of the pending instruction data are matched to obtain multiple urgent related texts; The urgency level of each urgent-related text is determined based on semantic analysis algorithms. Calculate the average of the urgency levels of all the aforementioned urgency-related texts to obtain the urgency level of the instruction data to be approved; For any two pending instruction data, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instruction data; Calculate the type similarity between the instruction types corresponding to the two pending instruction data; Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data; Calculate the weighted average of the data similarity, the type similarity, and the time similarity to obtain the correlation similarity between the two pending approval instruction data. Based on the association similarity, the multiple instruction data to be approved are grouped according to the clustering grouping algorithm to obtain multiple instruction data sets; Calculate the average urgency level of all pending instruction data in each instruction data set to obtain the set urgency parameter corresponding to each instruction data set; Based on the set of emergency parameters, at least one emergency instruction data set is selected from the plurality of instruction data sets; Based on neural network algorithms, predict the type of emergency event corresponding to each set of emergency instruction data; Based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user, the approval priority of each instruction data to be approved is determined.

2. The instruction approval data processing method based on multiple neural networks according to claim 1, characterized in that, The correlation similarity between any two pending instruction data in each instruction data set is greater than a first similarity threshold, and the correlation similarity between any two pending instruction data belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

3. The instruction approval data processing method based on multiple neural networks according to claim 1, characterized in that, The step of selecting at least one emergency instruction data set from the plurality of instruction data sets based on the set of emergency parameters includes: Sort all the instruction data sets from largest to smallest according to the set emergency parameters to obtain a set sequence; Filter out the first preset number of instruction data sets in the set sequence whose emergency parameters are greater than a parameter threshold to obtain at least one emergency instruction data set.

4. The instruction approval data processing method based on multiple neural networks according to claim 3, characterized in that, The method of predicting the type of emergency event corresponding to each set of emergency instruction data based on a neural network algorithm includes: For each set of emergency instruction data, each instruction data to be approved in the set of emergency instruction data is input into a trained event prediction neural network to obtain the data event type corresponding to each instruction data to be approved; the event prediction neural network is trained using a training dataset that includes multiple training instruction data and corresponding event type labels. The most frequent item among the data event types corresponding to all pending approval instructions in the emergency instruction data set is counted to obtain the emergency event type corresponding to the emergency instruction data set.

5. The instruction approval data processing method based on multiple neural networks according to claim 1, characterized in that, The step of determining the approval priority of each pending instruction data based on the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each pending instruction data, determine the user type of the approving user corresponding to the pending instruction data and determine the emergency event type corresponding to the emergency instruction data set corresponding to the pending instruction data; when the pending instruction data does not have a corresponding emergency instruction data set, its corresponding emergency event type is an empty identifier; Based on the preset correspondence between user types and levels, and the user type corresponding to the instruction data to be approved, determine the user level parameter corresponding to the instruction data to be approved; Based on the preset correspondence between event types and levels, and the type of emergency event corresponding to the pending instruction data, determine the event level parameter corresponding to the pending instruction data; Calculate the weighted average of the user-level parameters and the event-level parameters to obtain the priority parameter corresponding to the pending approval instruction data; The approval priority of each pending instruction is determined based on the priority parameters corresponding to all the pending instruction data; the priority level is directly proportional to the magnitude of the priority parameters.

6. A data processing system for instruction approval based on a multi-neural network, characterized in that, The system includes: The acquisition module is used to acquire multiple pending approval instructions issued by multiple approval users within the same time period; the pending approval instruction data includes instruction text, instruction type, instruction issuance time, and instruction attachments; The grouping module is used to determine at least one set of emergency instruction data based on an association clustering grouping algorithm and the multiple pending approval instruction data, including: Based on a prediction algorithm, the urgency level corresponding to each of the pending instruction data is determined; the specific method by which the grouping module determines the urgency level corresponding to each of the pending instruction data based on the prediction algorithm includes: The instruction text and instruction attachments of each instruction data to be approved are input into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each instruction data to be approved; the instruction urgency prediction neural network is trained using a training dataset that includes multiple training instruction texts, training instruction attachments and corresponding urgency level labels; And / or, For each of the pending instruction data, based on a preset text matching template, the instruction text and the instruction attachment of the pending instruction data are matched to obtain multiple urgent related texts; The urgency level of each urgent-related text is determined based on semantic analysis algorithms. Calculate the average of the urgency levels of all the aforementioned urgency-related texts to obtain the urgency level of the instruction data to be approved; For any two pending instruction data, calculate the data similarity between the instruction text and instruction attachment corresponding to the two pending instruction data; Calculate the type similarity between the instruction types corresponding to the two pending instruction data; Calculate the time similarity between the instruction issuance times corresponding to the two pending instruction data; Calculate the weighted average of the data similarity, the type similarity, and the time similarity to obtain the correlation similarity between the two pending approval instruction data. Based on the association similarity, the multiple instruction data to be approved are grouped according to the clustering grouping algorithm to obtain multiple instruction data sets; Calculate the average urgency level of all pending instruction data in each instruction data set to obtain the set urgency parameter corresponding to each instruction data set; Based on the set of emergency parameters, at least one emergency instruction data set is selected from the plurality of instruction data sets; The prediction module is used to predict the type of emergency event corresponding to each set of emergency instructions based on a neural network algorithm. The determination module is used to determine the approval priority of each instruction data to be approved based on the type of emergency event corresponding to the emergency instruction data set and the user type of the approving user.

7. A data processing system for instruction approval based on a multi-neural network, 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 instruction approval data processing method based on multiple neural networks as described in any one of claims 1-5.

Images