Instruction approval data processing method and system based on multiple neural networks

Abstract

The invention discloses an instruction approval data processing method and system based on multiple neural networks. The method comprises the steps of obtaining multiple pieces of to-be-approved instruction data sent by multiple approval users in the same time period; determining at least one emergency instruction data set based on an association clustering grouping algorithm and the plurality of pieces of to-be-approved instruction data; predicting an emergency event type corresponding to each emergency instruction data set based on a neural network algorithm; and determining the approval priority of each piece of to-be-approved instruction data according to the emergency event type corresponding to the emergency instruction data set and the user type of the approval user. Therefore, more automatic and intelligent approval priority determination can be realized by fully combining instruction data association and event type prediction under an emergency, so that the efficiency and accuracy of instruction approval are improved.

Description

Technical Field

[0001] The present 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 Art

[0002] With the development of data processing technology and the promotion of paperless office policies, more and more instruction approval needs are beginning to be implemented through approval within the data system. Data approval can reduce the use of paper and improve the efficiency and accuracy of approval, so it has been widely used. However, in the existing instruction data approval scheme, it is generally only implemented based on preset hierarchical approval rules and data communication processes, and does not fully consider the classification and prediction of instruction data in emergency situations based on neural network algorithms to determine the emergency events and priorities targeted by the instructions. Therefore, the automation and intelligence of the approval for emergencies are lacking, and the approval efficiency cannot be guaranteed. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an instruction approval data processing method and system based on multi-neural networks, which can fully combine the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing instruction approval data based on multiple neural networks, the method comprising: Obtain data on multiple pending approval instructions issued by multiple approval users within the same time period; Based on the association clustering grouping algorithm and the plurality of pending instruction data, determining at least one urgent instruction data set; Based on a neural network algorithm, predict the type of emergency event corresponding to each of the emergency instruction data sets; The approval priority of each of the instruction data to be approved is determined according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

[0005] 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.

[0006] As an optional implementation, in the first aspect of the present invention, the at least one urgent instruction data set is determined based on the association clustering grouping algorithm and the plurality of instruction data to be approved, including: Determine the urgency level of each of the pending approval instruction data based on the prediction algorithm; Based on a similarity clustering algorithm, the plurality of instruction data to be approved are grouped to obtain a plurality of instruction data sets; Calculating the average of the urgency levels corresponding to all the pending instruction data in each instruction data set to obtain a set urgency parameter corresponding to each instruction data set; At least one urgent instruction data set is selected from the plurality of instruction data sets according to the set urgent parameter.

[0007] As an optional implementation, in the first aspect of the present invention, determining the urgency level corresponding to each of the pending approval instruction data based on the prediction algorithm includes: Inputting the instruction text and instruction attachment of each of the pending instruction data into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each of the pending instruction data; the instruction urgency prediction neural network is trained by a training data set including a plurality of training instruction texts, training instruction attachments and corresponding urgency level annotations; 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 a plurality of emergency-related texts; Determine the text urgency corresponding to each of the emergency-related texts based on a semantic fan algorithm; The average value of the text urgency levels corresponding to all the emergency-related texts is calculated to obtain the urgency level of the instruction data to be approved.

[0008] As an optional implementation, in the first aspect of the present invention, the plurality of instruction data to be approved are grouped based on a similarity clustering algorithm to obtain a plurality of instruction data sets, including: For any two of the pending approval instruction data, calculating the data similarity between the instruction texts and instruction attachments corresponding to the two pending approval data; Calculating the type similarity between the instruction types corresponding to the two pieces of data to be approved; Calculating the time similarity between the time when the instructions corresponding to the two pieces of data to be approved are issued; Calculating a weighted average of the data similarity, the type similarity and the time similarity to obtain the correlation similarity between the two pieces of data to be approved; Based on the association similarity, the multiple instruction data to be approved are grouped based on a clustering grouping algorithm to obtain multiple instruction data sets; wherein the association similarity between any two instruction data to be approved in each instruction data set is greater than a first similarity threshold, and the association similarity between any two instruction data to be approved belonging to different instruction data sets is less than a second similarity threshold; and the second similarity threshold is less than the first similarity threshold.

[0009] As an optional implementation, in the first aspect of the present invention, the selecting at least one emergency instruction data set from the multiple instruction data sets according to the set emergency parameter comprises: Sorting all the instruction data sets from large to small according to the set emergency parameter to obtain a set sequence; The first preset number of instruction data sets in the set sequence and the set emergency parameters of which are greater than the parameter threshold are screened out to obtain at least one emergency instruction data set.

[0010] As an optional implementation, in the first aspect of the present invention, the predicting the emergency event type corresponding to each of the emergency instruction data sets based on a neural network algorithm includes: For each of the emergency data sets, each of the pending instruction data in the emergency instruction data set is input into a trained event prediction neural network to obtain a data event type corresponding to each of the pending instruction data; the event prediction neural network is trained by a training data set including a plurality of training instruction data and corresponding event type annotations; The majority items of the data event types corresponding to all the pending instruction data in the emergency instruction data set are counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0011] As an optional implementation, in the first aspect of the present invention, determining the approval priority of each of the instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each of the 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, the emergency event type corresponding to the pending instruction data is a null mark; Determine the user level parameter corresponding to the instruction data to be approved according to the preset correspondence between the user type and the level and the user type corresponding to the instruction data to be approved; Determine the event level parameter corresponding to the instruction data to be approved according to the preset correspondence between the event type and the level, and the emergency event type corresponding to the instruction data to be approved; Calculate the weighted average of the user level parameter and the event level parameter to obtain the priority parameter corresponding to the instruction data to be approved; The approval priority of each of the instruction data to be approved is determined according to the priority parameters corresponding to all the instruction data to be approved; the degree of the approval priority is proportional to the size of the priority parameter.

[0012] A second aspect of an embodiment of the present invention discloses an instruction approval data processing system based on multiple neural networks, the system comprising: The acquisition module is used to acquire data of multiple pending approval instructions issued by multiple approval users within the same time period; A grouping module, configured to determine at least one urgent instruction data set based on an association clustering grouping algorithm and the plurality of instruction data to be approved; A prediction module, used for predicting the type of emergency event corresponding to each of the emergency instruction data sets based on a neural network algorithm; The determination module is used to determine the approval priority of each of the instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

[0013] As an optional implementation, in the second aspect of the present invention, the instruction data to be approved includes instruction text, instruction type, instruction issuance time and instruction attachments.

[0014] As an optional implementation, in the second aspect of the present invention, the grouping module determines a specific manner of at least one set of emergency instruction data based on the association clustering grouping algorithm and the plurality of instruction data to be approved, including: Determine the urgency level of each of the pending approval instruction data based on the prediction algorithm; Based on a similarity clustering algorithm, the plurality of instruction data to be approved are grouped to obtain a plurality of instruction data sets; Calculating the average of the urgency levels corresponding to all the pending instruction data in each instruction data set to obtain a set urgency parameter corresponding to each instruction data set; At least one urgent instruction data set is selected from the plurality of instruction data sets according to the set urgent parameter.

[0015] As an optional implementation, in the second aspect of the present invention, the grouping module determines the specific manner of the urgency corresponding to each of the pending instruction data based on the prediction algorithm, including: Inputting the instruction text and instruction attachment of each of the pending instruction data into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each of the pending instruction data; the instruction urgency prediction neural network is trained by a training data set including a plurality of training instruction texts, training instruction attachments and corresponding urgency level annotations; 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 a plurality of emergency-related texts; Determine the text urgency corresponding to each of the emergency-related texts based on a semantic fan algorithm; The average value of the text urgency levels corresponding to all the emergency-related texts is calculated to obtain the urgency level of the instruction data to be approved.

[0016] As an optional implementation, in the second aspect of the present invention, the grouping module groups the plurality of pending instruction data based on a similarity clustering algorithm to obtain a plurality of instruction data sets in a specific manner, including: For any two of the pending approval instruction data, calculating the data similarity between the instruction texts and instruction attachments corresponding to the two pending approval data; Calculating the type similarity between the instruction types corresponding to the two pieces of data to be approved; Calculating the time similarity between the time when the instructions corresponding to the two pieces of data to be approved are issued; Calculating a weighted average of the data similarity, the type similarity and the time similarity to obtain the correlation similarity between the two pieces of data to be approved; Based on the association similarity, the multiple instruction data to be approved are grouped based on a clustering grouping algorithm to obtain multiple instruction data sets; wherein the association similarity between any two instruction data to be approved in each instruction data set is greater than a first similarity threshold, and the association similarity between any two instruction data to be approved belonging to different instruction data sets is less than a second similarity threshold; and the second similarity threshold is less than the first similarity threshold.

[0017] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module selects at least one emergency instruction data set from the multiple instruction data sets according to the set emergency parameter includes: Sorting all the instruction data sets from large to small according to the set emergency parameter to obtain a set sequence; The first preset number of instruction data sets in the set sequence and the set emergency parameters of which are greater than the parameter threshold are screened out to obtain at least one emergency instruction data set.

[0018] As an optional implementation, in the second aspect of the present invention, the prediction module predicts the specific manner of the emergency event type corresponding to each of the emergency instruction data sets based on a neural network algorithm, including: For each of the emergency data sets, each of the pending instruction data in the emergency instruction data set is input into a trained event prediction neural network to obtain a data event type corresponding to each of the pending instruction data; the event prediction neural network is trained by a training data set including a plurality of training instruction data and corresponding event type annotations; The majority items of the data event types corresponding to all the pending instruction data in the emergency instruction data set are counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0019] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the approval priority of each of the to-be-approved instruction data according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each of the 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, the emergency event type corresponding to the pending instruction data is a null mark; Determine the user level parameter corresponding to the instruction data to be approved according to the preset correspondence between the user type and the level and the user type corresponding to the instruction data to be approved; Determine the event level parameter corresponding to the instruction data to be approved according to the preset correspondence between the event type and the level, and the emergency event type corresponding to the instruction data to be approved; Calculate the weighted average of the user level parameter and the event level parameter to obtain the priority parameter corresponding to the instruction data to be approved; The approval priority of each of the instruction data to be approved is determined according to the priority parameters corresponding to all the instruction data to be approved; the degree of the approval priority is proportional to the size of the priority parameter.

[0020] The third aspect of the present invention discloses another instruction approval data processing system based on multiple neural networks, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part 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.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part 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.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can determine at least one emergency instruction data set from multiple instruction data to be approved based on an associated clustering grouping algorithm, and then predict the emergency event type corresponding to each emergency instruction data set based on a neural network algorithm, and determine the approval priority of each instruction data to be approved based on the emergency event type and the user type of the approving user, thereby being able to fully combine the 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for processing instruction approval data based on multiple neural networks disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of an instruction approval data processing system based on multiple neural networks disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another instruction approval data processing system based on multiple neural networks disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

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

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a method and system for processing instruction approval data based on multiple neural networks, which can determine at least one emergency instruction data set from multiple instruction data to be approved based on an associated clustering grouping algorithm, and then predict the emergency event type corresponding to each emergency instruction data set based on a neural network algorithm, and determine the approval priority of each instruction data to be approved based on the emergency event type and the user type of the approving user, so as to fully combine the instruction data association and event type prediction under emergency conditions to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 This is a flow chart of a method for processing instruction approval data based on multiple neural networks disclosed in an embodiment of the present invention. Figure 1 The described instruction approval data processing method based on multiple neural networks can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1As shown, the instruction approval data processing method based on multiple neural networks may include the following operations: 101. Acquire data of multiple pending approval instructions issued by multiple approval users within the same time period.

[0032] 102. Determine at least one urgent instruction data set based on an associated clustering grouping algorithm and a plurality of instruction data to be approved. 103. Based on the neural network algorithm, predict the type of emergency event corresponding to each emergency instruction data set. 104. Determine the approval priority of each instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

[0033] It can be seen that the above-mentioned embodiment of the invention can determine at least one emergency instruction data set from multiple instruction data to be approved based on the associated clustering grouping algorithm, and then predict the emergency event type corresponding to each emergency instruction data set according to the neural network algorithm, and determine the approval priority of each instruction data to be approved based on the emergency event type and the user type of the approving user, so as to fully combine the instruction data association and event type prediction in the emergency situation to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0034] As an optional embodiment, in the above steps, the instruction data to be approved includes instruction text, instruction type, instruction issuance time and instruction attachments.

[0035] It can be seen that through the above optional embodiments, the content of the instruction data to be approved is limited to comprehensively characterize the characteristics and features of the instruction data to be approved, facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0036] As an optional embodiment, in the above steps, based on the association clustering grouping algorithm and the plurality of pending instruction data, at least one urgent instruction data set is determined, including: Based on the prediction algorithm, determine the urgency level of each instruction data to be approved; Based on the similarity clustering algorithm, multiple instruction data to be approved are grouped to obtain multiple instruction data sets; Calculate the average of the urgency levels of all pending instruction data in each instruction data set to obtain a set urgency parameter corresponding to each instruction data set; At least one urgent instruction data set is selected from the plurality of instruction data sets according to the set urgent parameter.

[0037] It can be seen that through the above-mentioned 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 to screen out at least one emergency instruction data set according to the urgency, so as to facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0038] As an optional embodiment, in the above steps, determining the urgency level corresponding to each instruction data to be approved based on the prediction algorithm includes: Input the instruction text and instruction attachment of each instruction data to be approved 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 by a training data set including a plurality of training instruction texts, training instruction attachments and corresponding urgency level annotations; and / or, For each instruction data to be approved, based on a preset text matching template, the instruction text and instruction attachment of the instruction data to be approved are matched to obtain multiple emergency related texts; Determine the text urgency level corresponding to each emergency-related text based on the semantic fans algorithm; The average value of the text urgency levels corresponding to all emergency-related texts is calculated to obtain the urgency level of the instruction data to be approved.

[0039] It can be seen that through the above optional embodiments, the prediction or analysis method of the urgency is limited, which can be based on the instruction text and instruction attachments of the instruction data to be approved and the trained instruction urgency prediction neural network, or based on text matching and semantic analysis algorithms, to accurately predict the urgency of the instruction data, facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0040] As an optional embodiment, in the above steps, based on a similarity clustering algorithm, multiple instruction data to be approved are grouped to obtain multiple instruction data sets, including: For any two pending approval instruction data, calculate the data similarity between the instruction texts and instruction attachments corresponding to the two pending approval data; Calculate the type similarity between the instruction types corresponding to the two pieces of data to be approved; Calculate the time similarity between the time when the instructions corresponding to the two pieces of data to be approved are issued; Calculate the weighted average of data similarity, type similarity and time similarity to obtain the correlation similarity between the two pieces of data to be approved; Based on the association similarity, multiple instruction data to be approved are grouped based on a clustering grouping algorithm to obtain multiple instruction data sets; optionally, the association similarity between any two instruction data to be approved in each instruction data set is greater than a first similarity threshold, and the association similarity between any two instruction data to be approved belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0041] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the correlation similarity between the data contents of the data to be approved and group multiple more relevant instruction data sets based on the clustering grouping algorithm, so as to facilitate the subsequent priority determination, and assist in realizing a more automatic and intelligent approval priority determination by fully combining the instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0042] As an optional embodiment, in the above step, selecting at least one emergency instruction data set from multiple instruction data sets according to the set emergency parameter includes: Sort all instruction data sets from large to small according to the set emergency parameter to obtain a set sequence; The first preset number of instruction data sets in the set sequence and whose set emergency parameters are greater than the parameter threshold are screened out to obtain at least one emergency instruction data set.

[0043] It can be seen that through the above-mentioned optional embodiments, at least one emergency instruction data set can be screened out based on the sorting and screening of the set emergency parameters, so as to facilitate the subsequent priority determination, and assist in realizing a more automatic and intelligent approval priority determination by fully combining the instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0044] As an optional embodiment, in the above steps, predicting the emergency event type corresponding to each emergency instruction data set based on a neural network algorithm includes: For each emergency data set, each pending instruction data in the emergency instruction data set is input into the trained event prediction neural network to obtain the data event type corresponding to each pending instruction data; optionally, the event prediction neural network is trained by a training data set including a plurality of training instruction data and corresponding event type annotations; The majority items in the data event types corresponding to all the instruction data to be approved in the emergency instruction data set are counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0045] It can be seen that through the above-mentioned optional embodiments, it is possible to predict the data event type corresponding to each instruction data to be approved based on the trained event prediction neural network, and then obtain the emergency event type corresponding to the emergency instruction data set based on the statistical screening of the majority items, which is convenient for subsequent priority determination, and assists in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0046] As an optional embodiment, in the above steps, determining the approval priority of each instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each instruction data to be approved, determine the user type of the approving user corresponding to the instruction data to be approved and determine the emergency event type corresponding to the emergency instruction data set corresponding to the instruction data to be approved; optionally, when the instruction data to be approved has no corresponding emergency instruction data set, the emergency event type corresponding to it is a null identifier; Determine the user level parameter corresponding to the instruction data to be approved according to the preset correspondence between the user type and the level and the user type corresponding to the instruction data to be approved; Determine the event level parameter corresponding to the instruction data to be approved according to the preset correspondence between the event type and the level, and the emergency event type corresponding to the instruction data to be approved; Calculate the weighted average of the user-level parameter and the event-level parameter to obtain the priority parameter corresponding to the instruction data to be approved; According to the priority parameters corresponding to all the instruction data to be approved, the approval priority of each instruction data to be approved is determined; the degree of the approval priority is proportional to the size of the priority parameter.

[0047] It can be seen that through the above-mentioned optional embodiments, the user level parameters and the event level parameters can be determined respectively according to the user type of the approving user corresponding to the instruction data to be approved and the emergency event type corresponding to the emergency instruction data set corresponding to the instruction data to be approved, so as to comprehensively calculate the corresponding priority parameters to determine the approval priority, and fully combine the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0048] Embodiment 2 See also Figure 2 , Figure 2 1 is a schematic diagram of the structure of a multi-neural network-based instruction approval data processing system disclosed in an embodiment of the present invention. Figure 2The described instruction approval data processing system based on multiple neural networks can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the instruction approval data processing system based on multiple neural networks may include: The acquisition module 201 is used to acquire a plurality of pending approval instruction data issued by a plurality of approval users in the same time period.

[0049] The grouping module 202 is used to determine at least one urgent instruction data set based on an associated clustering grouping algorithm and a plurality of instruction data to be approved. The prediction module 203 is used to predict the emergency event type corresponding to each emergency instruction data set based on a neural network algorithm. The determination module 204 is used to determine the approval priority of each instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

[0050] It can be seen that the above-mentioned embodiment of the invention can determine at least one emergency instruction data set from multiple instruction data to be approved based on the associated clustering grouping algorithm, and then predict the emergency event type corresponding to each emergency instruction data set according to the neural network algorithm, and determine the approval priority of each instruction data to be approved based on the emergency event type and the user type of the approving user, so as to fully combine the instruction data association and event type prediction in the emergency situation to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0051] As an optional embodiment, the instruction data to be approved includes instruction text, instruction type, instruction issuance time and instruction attachments.

[0052] It can be seen that through the above optional embodiments, the content of the instruction data to be approved is limited to comprehensively characterize the characteristics and features of the instruction data to be approved, facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0053] As an optional embodiment, the grouping module determines a specific method of at least one urgent instruction data set based on the association clustering grouping algorithm and the plurality of instruction data to be approved, including: Based on the prediction algorithm, determine the urgency level of each instruction data to be approved; Based on the similarity clustering algorithm, multiple instruction data to be approved are grouped to obtain multiple instruction data sets; Calculate the average of the urgency levels of all pending instruction data in each instruction data set to obtain a set urgency parameter corresponding to each instruction data set; At least one urgent instruction data set is selected from the plurality of instruction data sets according to the set urgent parameter.

[0054] It can be seen that through the above-mentioned 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 to screen out at least one emergency instruction data set according to the urgency, so as to facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0055] As an optional embodiment, the grouping module determines the specific manner of the urgency of each instruction data to be approved based on the prediction algorithm, including: Input the instruction text and instruction attachment of each instruction data to be approved 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 by a training data set including a plurality of training instruction texts, training instruction attachments and corresponding urgency level annotations; and / or, For each instruction data to be approved, based on a preset text matching template, the instruction text and instruction attachment of the instruction data to be approved are matched to obtain multiple emergency related texts; Determine the text urgency level corresponding to each emergency-related text based on the semantic fans algorithm; The average value of the text urgency levels corresponding to all emergency-related texts is calculated to obtain the urgency level of the instruction data to be approved.

[0056] It can be seen that through the above optional embodiments, the prediction or analysis method of the urgency is limited, which can be based on the instruction text and instruction attachments of the instruction data to be approved and the trained instruction urgency prediction neural network, or based on text matching and semantic analysis algorithms, to accurately predict the urgency of the instruction data, facilitate subsequent priority determination, and assist in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0057] As an optional embodiment, the grouping module groups the multiple instruction data to be approved based on a similarity clustering algorithm to obtain multiple instruction data sets in a specific manner, including: For any two pending approval instruction data, calculate the data similarity between the instruction texts and instruction attachments corresponding to the two pending approval data; Calculate the type similarity between the instruction types corresponding to the two pieces of data to be approved; Calculate the time similarity between the time when the instructions corresponding to the two pieces of data to be approved are issued; Calculate the weighted average of data similarity, type similarity and time similarity to obtain the correlation similarity between the two pieces of data to be approved; Based on the association similarity, multiple instruction data to be approved are grouped based on a clustering grouping algorithm to obtain multiple instruction data sets; optionally, the association similarity between any two instruction data to be approved in each instruction data set is greater than a first similarity threshold, and the association similarity between any two instruction data to be approved belonging to different instruction data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold.

[0058] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the correlation similarity between the data contents of the data to be approved and group multiple more relevant instruction data sets based on the clustering grouping algorithm, so as to facilitate the subsequent priority determination, and assist in realizing a more automatic and intelligent approval priority determination by fully combining the instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0059] As an optional embodiment, the specific manner in which the grouping module selects at least one emergency instruction data set from multiple instruction data sets according to the set emergency parameter includes: All instruction data sets are sorted from large to small according to the set emergency parameter to obtain a set sequence; The first preset number of instruction data sets in the set sequence and whose set emergency parameters are greater than the parameter threshold are screened out to obtain at least one emergency instruction data set.

[0060] It can be seen that through the above-mentioned optional embodiments, at least one emergency instruction data set can be screened out based on the sorting and screening of the set emergency parameters, so as to facilitate the subsequent priority determination, and assist in realizing a more automatic and intelligent approval priority determination by fully combining the instruction data association and event type prediction in emergency situations, so as to improve the efficiency and accuracy of instruction approval.

[0061] As an optional embodiment, the prediction module predicts the specific manner of the emergency event type corresponding to each emergency instruction data set based on a neural network algorithm, including: For each emergency data set, each pending instruction data in the emergency instruction data set is input into the trained event prediction neural network to obtain the data event type corresponding to each pending instruction data; optionally, the event prediction neural network is trained by a training data set including a plurality of training instruction data and corresponding event type annotations; The majority items in the data event types corresponding to all the instruction data to be approved in the emergency instruction data set are counted to obtain the emergency event type corresponding to the emergency instruction data set.

[0062] It can be seen that through the above-mentioned optional embodiments, it is possible to predict the data event type corresponding to each instruction data to be approved based on the trained event prediction neural network, and then obtain the emergency event type corresponding to the emergency instruction data set based on the statistical screening of the majority items, which is convenient for subsequent priority determination, and assists in fully combining the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0063] As an optional embodiment, the specific manner in which the determination module determines the approval priority of each instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each instruction data to be approved, determine the user type of the approving user corresponding to the instruction data to be approved and determine the emergency event type corresponding to the emergency instruction data set corresponding to the instruction data to be approved; optionally, when the instruction data to be approved has no corresponding emergency instruction data set, the emergency event type corresponding to it is a null identifier; Determine the user level parameter corresponding to the instruction data to be approved according to the preset correspondence between the user type and the level and the user type corresponding to the instruction data to be approved; Determine the event level parameter corresponding to the instruction data to be approved according to the preset correspondence between the event type and the level, and the emergency event type corresponding to the instruction data to be approved; Calculate the weighted average of the user-level parameter and the event-level parameter to obtain the priority parameter corresponding to the instruction data to be approved; According to the priority parameters corresponding to all the instruction data to be approved, the approval priority of each instruction data to be approved is determined; the degree of the approval priority is proportional to the size of the priority parameter.

[0064] It can be seen that through the above-mentioned optional embodiments, the user level parameters and the event level parameters can be determined respectively according to the user type of the approving user corresponding to the instruction data to be approved and the emergency event type corresponding to the emergency instruction data set corresponding to the instruction data to be approved, so as to comprehensively calculate the corresponding priority parameters to determine the approval priority, and fully combine the instruction data association and event type prediction in emergency situations to achieve more automatic and intelligent approval priority determination, so as to improve the efficiency and accuracy of instruction approval.

[0065] Embodiment 3 See also Figure 3 , Figure 3 It is another instruction approval data processing system based on multiple neural networks disclosed in an embodiment of the present invention. Figure 3 The described instruction approval data processing system based on multiple neural networks is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the instruction approval data processing system based on multiple neural networks may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; 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 the first embodiment.

[0066] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the instruction approval data processing method based on multiple neural networks described in the first embodiment.

[0067] Embodiment 5 An embodiment of the present 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 enable a computer to execute the steps of the instruction approval data processing method based on multiple neural networks described in Example 1.

[0068] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] Finally, it should be noted that the instruction approval data processing method and system based on multi-neural networks disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes 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 comprises: Obtain data on multiple pending approval instructions issued by multiple approval users within the same time period; Based on the association clustering grouping algorithm and the plurality of pending instruction data, determining at least one urgent instruction data set; Based on a neural network algorithm, predict the type of emergency event corresponding to each of the emergency instruction data sets; The approval priority of each of the instruction data to be approved is determined according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

2. The instruction approval data processing method based on multiple neural networks according to claim 1 is characterized in that: The pending instruction data includes instruction text, instruction type, instruction issuance time and instruction attachments.

3. The instruction approval data processing method based on multiple neural networks according to claim 2 is characterized in that: The method of determining at least one urgent instruction data set based on the association clustering grouping algorithm and the plurality of instruction data to be approved comprises: Determine the urgency level of each of the pending approval instruction data based on the prediction algorithm; Based on a similarity clustering algorithm, the plurality of instruction data to be approved are grouped to obtain a plurality of instruction data sets; Calculating the average of the urgency levels corresponding to all the pending instruction data in each instruction data set to obtain a set urgency parameter corresponding to each instruction data set; At least one urgent instruction data set is selected from the plurality of instruction data sets according to the set urgent parameter.

4. The instruction approval data processing method based on multiple neural networks according to claim 3 is characterized in that: Determining the urgency level of each of the pending instruction data based on the prediction algorithm includes: Inputting the instruction text and instruction attachment of each of the pending instruction data into a trained instruction urgency prediction neural network to obtain the urgency level corresponding to each of the pending instruction data; the instruction urgency prediction neural network is trained by a training data set including a plurality of training instruction texts, training instruction attachments and corresponding urgency level annotations; 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 a plurality of emergency-related texts; Determine the text urgency corresponding to each of the emergency-related texts based on a semantic fan algorithm; The average value of the text urgency levels corresponding to all the emergency-related texts is calculated to obtain the urgency level of the instruction data to be approved.

5. The instruction approval data processing method based on multiple neural networks according to claim 3 is characterized in that: The similarity-based clustering algorithm is used to group the plurality of instruction data to be approved to obtain a plurality of instruction data sets, including: For any two of the pending approval instruction data, calculating the data similarity between the instruction texts and instruction attachments corresponding to the two pending approval data; Calculating the type similarity between the instruction types corresponding to the two pieces of data to be approved; Calculating the time similarity between the time when the instructions corresponding to the two pieces of data to be approved are issued; Calculating a weighted average of the data similarity, the type similarity and the time similarity to obtain the correlation similarity between the two pieces of data to be approved; Based on the association similarity, the multiple instruction data to be approved are grouped based on a clustering grouping algorithm to obtain multiple instruction data sets; wherein the association similarity between any two instruction data to be approved in each instruction data set is greater than a first similarity threshold, and the association similarity between any two instruction data to be approved belonging to different instruction data sets is less than a second similarity threshold; and the second similarity threshold is less than the first similarity threshold.

6. The instruction approval data processing method based on multiple neural networks according to claim 3 is characterized in that: The step of selecting at least one emergency instruction data set from the plurality of instruction data sets according to the set emergency parameter comprises: Sorting all the instruction data sets from large to small according to the set emergency parameter to obtain a set sequence; The first preset number of instruction data sets in the set sequence and the set emergency parameters of which are greater than the parameter threshold are screened out to obtain at least one emergency instruction data set.

7. The instruction approval data processing method based on multiple neural networks according to claim 6 is characterized in that: The predicting of the emergency event type corresponding to each of the emergency instruction data sets based on the neural network algorithm includes: For each of the emergency data sets, each of the pending instruction data in the emergency instruction data set is input into a trained event prediction neural network to obtain a data event type corresponding to each of the pending instruction data; the event prediction neural network is trained by a training data set including a plurality of training instruction data and corresponding event type annotations; The majority items of the data event types corresponding to all the pending instruction data in the emergency instruction data set are counted to obtain the emergency event type corresponding to the emergency instruction data set.

8. The instruction approval data processing method based on multiple neural networks according to claim 1 is characterized in that: The step of determining the approval priority of each of the instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user includes: For each of the 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, the emergency event type corresponding to the pending instruction data is a null mark; Determine the user level parameter corresponding to the instruction data to be approved according to the preset correspondence between the user type and the level and the user type corresponding to the instruction data to be approved; Determine the event level parameter corresponding to the instruction data to be approved according to the preset correspondence between the event type and the level, and the emergency event type corresponding to the instruction data to be approved; Calculate the weighted average of the user level parameter and the event level parameter to obtain the priority parameter corresponding to the instruction data to be approved; The approval priority of each of the instruction data to be approved is determined according to the priority parameters corresponding to all the instruction data to be approved; the degree of the approval priority is proportional to the size of the priority parameter.

9. An instruction approval data processing system based on multiple neural networks, characterized in that: The system comprises: The acquisition module is used to acquire data of multiple pending approval instructions issued by multiple approval users within the same time period; A grouping module, configured to determine at least one urgent instruction data set based on an association clustering grouping algorithm and the plurality of instruction data to be approved; A prediction module, used for predicting the type of emergency event corresponding to each of the emergency instruction data sets based on a neural network algorithm; The determination module is used to determine the approval priority of each of the instruction data to be approved according to the emergency event type corresponding to the emergency instruction data set and the user type of the approving user.

10. An instruction approval data processing system based on multiple neural networks, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the instruction approval data processing method based on multiple neural networks as described in any one of claims 1-8.

Images