A data approval system, method and terminal based on artificial intelligence

Abstract

The present invention relates to a data approval system, method and terminal based on artificial intelligence, and relates to the field of automated approval, including: receiving an approval request queue, obtaining an approval request cluster sequence; matching an approval node sequence queue according to a business number label; constructing a first node approval request tree, a second node approval request tree, and an Nth node approval request tree according to the approval node sequence queue and the approval request cluster sequence; performing task allocation optimization, obtaining a first node approval request task allocation list, a second node approval request task allocation list, and an Nth node approval request task allocation list for data approval management. The system solves the technical problem in the prior art that the occupancy time of each approval node is unstable due to the diversification of business, the uncertainty of approval time, and the huge amount of approval data.

Description

Technical Field

[0001] The present invention relates to the field of automated approval, and in particular to an artificial intelligence-based data approval system, method and terminal. Background Art

[0002] With the advancement of digitalization, many types of approval processes such as government affairs and industrial Internet have achieved paperless office. Since online digital approval saves costs and is not affected by time and space, it has gradually become the main channel for approval management.

[0003] The development of artificial intelligence has become a major boost to the automation of approval processes. Currently, the application of artificial intelligence in process approval is mostly focused on assisting approval nodes to conduct efficient automated approval. However, due to the diversity of business, uncertainty of approval time, and the huge amount of approval data, the disadvantage of unstable occupancy time of each approval node still exists, making it difficult to flexibly schedule each approval node. Summary of the invention

[0004] The present invention aims to solve the technical problem in the prior art that due to the diversification of business, the uncertainty of approval time, and the huge amount of approval data, the occupancy time of each approval node is unstable, and provides an artificial intelligence-based data approval system, method and terminal to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a data approval system based on artificial intelligence, comprising:

[0007] A user end is used to receive an approval request queue, wherein any approval request in the approval request queue has a service number tag and a request time tag;

[0008] Servers, including:

[0009] A cluster analysis module, configured to perform cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label;

[0010] An approval node sequence matching module, used to traverse the approval request queue and match the approval node sequence queue according to the business number tag;

[0011] An approval request tree building module, used to build a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree according to the approval node sequence queue and the approval request cluster sequence;

[0012] Task allocation optimization module, used for:

[0013] Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list;

[0014] According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list;

[0015] Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list;

[0016] The data approval execution module is used to perform data approval management according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

[0017] In a second aspect, the present invention provides a data approval method based on artificial intelligence, comprising:

[0018] receiving an approval request queue, wherein any approval request in the approval request queue has a business number tag and a request time tag;

[0019] Performing cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label;

[0020] According to the business number tag, traverse the approval request queue and match the approval node sequence queue;

[0021] According to the approval node sequence queue and the approval request cluster sequence, construct a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree;

[0022] Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list;

[0023] According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list;

[0024] Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list;

[0025] Data approval management is performed according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

[0026] In a third aspect, the present invention provides a computer terminal, comprising:

[0027] Memory for storing computer software programs;

[0028] The processor is used to read and execute the computer software program, thereby implementing an artificial intelligence-based data approval method of the second aspect.

[0029] The beneficial effects of the present invention are: providing a technical solution in which a user terminal receives an approval request queue input by a user and uploads it to a server, and then clusters it according to the user request time using a cluster analysis module to obtain an approval request cluster sequence; the approval node sequence can be quickly matched for the approval request according to the business number label; then, according to the approval node sequence queue and the approval request cluster sequence, a first node approval request tree, a second node approval request tree, and up to the Nth node approval request tree are constructed; further, tasks are assigned to the first node approval request tree, the second node approval request tree, and up to the Nth node approval request tree, to obtain a first node approval request task assignment list, a second node approval request task assignment list, and up to the Nth node approval request task assignment list. Since each task assignment result has an approval request processing time zone label, it can be processed in a time-limited manner, thereby achieving a technical effect of flexible scheduling of approval nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flowchart of a data approval method based on artificial intelligence provided by the present invention;

[0031] Figure 2 A schematic diagram of the structure of data approval based on artificial intelligence provided by the present invention;

[0032] Figure 3 The present invention is a schematic diagram of the structure of a computer terminal.

[0033] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0034] Computer terminal 500 , memory 510 , processor 520 , computer program 511 . DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0036] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0037] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0038] Embodiment 1:

[0039] like Figure 1 As shown, an embodiment of the present invention provides a data approval method based on artificial intelligence, comprising the steps of:

[0040] S10: receiving an approval request queue, wherein any approval request in the approval request queue has a service number tag and a request time tag;

[0041] In the embodiment of the present invention, preferably, when a user has an approval requirement, he can select a service type through a user terminal in the form of software or hardware to upload an approval request, and form an approval request queue on the server. The time when each approval request is uploaded is stored as a request time tag, and the number uniquely corresponding to the service type is stored as a service number tag. The service number tag facilitates the matching of the approval node sequence in the subsequent step, and the request time tag can be used to allocate the order of processing of the approval request.

[0042] S20: performing cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label;

[0043] Further, according to the request time tag, cluster analysis is performed on the approval request queue to obtain an approval request cluster sequence. Step S20 includes the following steps:

[0044] S21: Configure consistent time deviation;

[0045] S22: clustering the approval request queue according to the consistent time deviation to obtain multiple clusters of approval requests;

[0046] S23: traversing the multiple clusters of approval requests to extract the median request time, and obtaining multiple median request times;

[0047] S24: Sort the multiple clusters of approval requests from first to last according to the multiple median request times to obtain the approval request cluster sequence.

[0048] In the embodiment of the present invention, the consistent time deviation is the maximum time span that is considered to be uploaded at the same time through the self-configuration of the management personnel. When the request time tags of any two approval requests are less than or equal to the consistent time deviation, they are considered to be uploaded at the same time, that is, the processing priorities are the same, and therefore they are clustered into the same cluster. On the contrary, when the request time tags of any two approval requests are greater than the consistent time deviation, they are considered to be uploaded at different times, that is, the processing priorities are different, and therefore they are clustered into different clusters. Therefore, according to the consistent time deviation, the approval request queue is clustered to obtain multiple clusters of approval requests. The median request time tag of each cluster of the multiple clusters of approval requests is extracted as a representative request time tag and stored as multiple median request times. Then, the earlier the median request time is, the higher the corresponding approval request processing priority is, and the later the median request time is, the lower the corresponding approval request processing priority is. Therefore, according to the multiple median request times, the multiple clusters of approval requests are sorted from first to last to obtain the approval request cluster sequence, and the approval request cluster sequence is used to characterize the processing priority of each approval request.

[0049] S30: According to the business number tag, traverse the approval request queue and match the approval node sequence queue;

[0050] In the embodiment of the present invention, preferably, an approval node sequence matching database is deployed in the server, and the approval node sequence matching database is configured by an administrator, and multiple binary array data are stored internally, each array having a business number and an approval node sequence. When the business number label is input into the approval node sequence matching database, the approval node sequence is matched, and stored in a one-to-one correspondence with the approval request queue to generate an approval node sequence queue. The approval node that needs task assignment can be determined through the approval node sequence queue, which facilitates the scheduling process of executing the approval node.

[0051] S40: constructing a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree according to the approval node sequence queue and the approval request cluster sequence;

[0052] In the embodiment of the present invention, the approval node sequence of each approval request can be known according to the approval node sequence queue, and the approval priority of each approval request can be known according to the approval request cluster sequence. In order to facilitate the efficiency of task allocation in the later step and the visualization of data recording, the approval requests are grouped based on the approval nodes through the approval node sequence queue, and then the approval requests of each group are grouped twice according to the approval request cluster sequence, and the first node approval request tree, the second node approval request tree and the Nth node approval request tree are constructed using the results of the two groupings. Any approval request tree represents the approval request of the specified node and the processing priority of the approval request. Preferably, the processing priority of the leaf nodes at the same level in any approval request tree is the same, and the processing priority of the leaf nodes at the deep level is lower than the processing priority of the leaf nodes at the shallow level. N is the total number of approval nodes, which is an integer greater than or equal to 1. Through the first node approval request tree, the second node approval request tree and the Nth node approval request tree, it is convenient for the later step to quickly traverse the tree to perform task allocation, and through the strict division of the tree level, it is guaranteed that the approval request with high priority is preferentially allocated.

[0053] Further, according to the approval node sequence queue and the approval request cluster sequence, a first node approval request tree, a second node approval request tree and an Nth node approval request tree are constructed, and step S40 includes the following steps:

[0054] S41: performing a first-level aggregation on the approval request queue according to the approval node sequence queue to generate a first node approval request set, a second node approval request set, and finally an Nth node approval request set;

[0055] S42: According to the approval request cluster sequence, traverse the first node approval request set, the second node approval request set, and the Nth node approval request set to perform secondary aggregation, and obtain a first node approval request cluster sequence, a second node approval request cluster sequence, and the Nth node approval request cluster sequence;

[0056] S43: traverse the first node approval request cluster sequence, the second node approval request cluster sequence until the Nth node approval request cluster sequence, and construct the first node approval request tree, the second node approval request tree until the Nth node approval request tree.

[0057] Further, traversing the first node approval request cluster sequence, the second node approval request cluster sequence until the Nth node approval request cluster sequence, constructing the first node approval request tree, the second node approval request tree until the Nth node approval request tree, step S43 includes the steps of:

[0058] S431: extracting a first cluster approval request set, a second cluster approval request set, and up to an Mth cluster approval request set according to the first node approval request cluster sequence;

[0059] S432: Generate the first node approval request tree by taking the first node as the root node, the first cluster approval request set as the first-level leaf node, the second cluster approval request set as the second-level leaf node, and so on until the Mth cluster approval request set is the Mth-level leaf node.

[0060] In an embodiment of the present invention, the approval node sequence queue and the approval request queue have a corresponding relationship. Therefore, according to each approval node of the approval node sequence queue, the approval request of the corresponding node can be extracted from the approval request queue. The first node, the second node, and the Nth node are traversed to group the approval request queue to obtain the first node approval request set, the second node approval request set, and the Nth node approval request set. Further, according to the approval request cluster sequence, the first node approval request set, the second node approval request set, and the Nth node approval request set can be traversed to perform secondary grouping to obtain the first node approval request cluster sequence, the second node approval request cluster sequence, and the Nth node approval request cluster sequence; further, according to the first node approval request cluster sequence, the first cluster approval request set, the second cluster approval request set, and the Mth cluster approval request set are extracted, where M represents the number of clusters of the first node approval request cluster sequence. With the first node as the root node, the first cluster approval request set as the first-level leaf node, the second cluster approval request set as the second-level leaf node, until the Mth cluster approval request set is the M-level leaf node, the first node approval request tree is generated. Furthermore, in the same manner, the second node approval request cluster sequence is traversed until the Nth node approval request cluster sequence, and the second node approval request tree is generated until the Nth node approval request tree.

[0061] S50: performing task allocation optimization on the first node occupancy state based on the first node approval request tree to obtain a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list;

[0062] S60: performing task allocation optimization on the second node occupancy state according to the first node approval request processing time zone label list and in combination with the second node approval request tree, to obtain a second node approval request task allocation list, wherein the second node approval request task allocation list has a second node approval request processing time zone label list;

[0063] S70: until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list;

[0064] In an embodiment of the present invention, the occupancy state of the first node represents the occupancy state of each approval particle of the first node, and it can be determined which time zones are idle. The first node can be an organization responsible for the approval of the corresponding node, and the approval particle refers to the approval personnel. Since in the embodiment of the present invention, the approval management is implemented in accordance with the scheme of the embodiment of the present invention from the beginning, the idle state of each approval particle can be determined in real time, which is convenient for flexible scheduling. The order of allocation of approval requests can be determined according to the approval request tree of the first node, and according to the occupancy state of the first node, it can be determined which time zones of which approval particles are idle.

[0065] Furthermore, since the approval process executed by each node for a certain business type is the same, the mode value of the approval time executed by each node for a certain business type can be counted, thereby realizing the prediction of the approval time.

[0066] Furthermore, the approval requests are allocated to idle time zones that meet the corresponding approval durations in the order in which the approval requests are allocated, thus completing the task allocation of the first-node approval request tree and storing it as the first-node approval request task allocation list. At this time, when allocated to an idle time zone, the starting time of the idle time zone is used as the starting time of the approval request processing time zone label, and the approval duration is used as the timing length to obtain the end time of the approval request processing time zone label, which is stored as the first-node approval request processing time zone label list.

[0067] Furthermore, the time zone label list of the first node approval request processing can be used to predict the timestamps of each approval request arriving at the second node. At this time, the same process is performed by traversing the second node approval request tree to obtain the second node approval request task allocation list. Traverse and analyze until the Nth node approval request tree to obtain the Nth node approval request task allocation list.

[0068] S80: Perform data approval management according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

[0069] In an embodiment of the present invention, after determining the first node approval request task allocation list, the second node approval request task allocation list, and so on, management is performed based on this. Since the processing time label of each approval request is limited, flexible scheduling of subsequent approvals is facilitated.

[0070] Further, based on the first node approval request tree, the task allocation optimization is performed on the first node occupancy state to obtain the first node approval request task allocation list, and step S50 includes the following steps:

[0071] S51: Obtaining a first-level approval request set, a second-level approval request set, and up to an M-level approval request set of the first node approval request tree;

[0072] S52: Obtain a first node approval particle list, wherein the first node approval particle list has an idle time zone label list;

[0073] S53: traversing the first node approval request tree to predict the approval time and generate an approval time label set;

[0074] S54: traverse the first-level approval request set, the second-level approval request set until the M-level approval request set, combine the idle time zone label list and the approval duration label set, perform task allocation on the first node approval particle list, and obtain the first node approval request task allocation list.

[0075] In the embodiment of the present invention, the description of step S50 is a basic principle. In order for those skilled in the art to further understand the application scheme, a specific implementation method is provided:

[0076] Obtain the first-level approval request set, the second-level approval request set, and the M-level approval request set of the approval request tree of the first node. The first-level approval request set, the second-level approval request set, and the M-level approval request set correspond to the first-level leaf node, the second-level leaf node, and the third-level leaf node, respectively, and the processing priority decreases in sequence. The first node approval granule list refers to the smallest unit responsible for approval by the first node, such as, for example, approval personnel. The idle time zone label list represents the idle time zone information of each approval granule, and the idle time zone information of each approval granule may be one time zone or multiple time zones. Traversing the approval time label set refers to the predicted approval time obtained by statistically analyzing the historical approval time of each approval request in the first node approval request tree. After determining the approval time label set, the minimum span of time zones required to be distributed for each approval request can be determined.

[0077] Further, the first-level approval request set is allocated through the idle time zone label list and the approval duration label set: that is, the time zones with approval duration labels greater than or equal to the first-level approval request set are screened from the idle time zone label list from the first to the last, and then the approval requests are allocated. When all allocations are completed, the first-level approval request task allocation result is obtained. Further, the idle time zone label list is updated according to the first-level approval request task allocation result, and the second-level approval request set is allocated through the updated idle time zone label list and the approval duration label set to obtain the second-level approval request task allocation result. Traverse to the M-level approval request set to obtain the M-level approval request task allocation result. Finally, the first-level approval request task allocation result, the second-level approval request task allocation result, and the M-level approval request task allocation result are stored as the first node approval request task allocation list. Preferably, the list has a total of M elements, each of which is any one of the first-level approval request task allocation result, the second-level approval request task allocation result, and the M-level approval request task allocation result.

[0078] Further, the first node approval request tree is traversed to predict the approval time and generate an approval time tag set. Step S53 includes the following steps:

[0079] S531: extracting a first approval request of a first node according to the first node approval request tree;

[0080] S532: Counting a data set of historical approval duration records of the first approval request at the first node;

[0081] S533: Perform a central trend analysis on the historical approval time record data set to obtain a first approval time label, and add the label to the approval time label set.

[0082] In an embodiment of the present invention, the approval time is preferably determined in the following manner: extract the first approval request of the approval request tree of the first node, and count the business number of the first approval request in the historical approval time record data set of the first node. The example of central trend analysis is as follows: sort the historical approval time record data set from small to large to obtain the sorting result of the historical approval time record data; calculate the result of rounding down one quarter of the total number of the sequence numbers of the sorting result of the historical approval time record data, and store it as the first sequence number; calculate the result of rounding up three quarters of the total number of the sequence numbers of the sorting result of the historical approval time record data, and store it as the second sequence number; extract the first characteristic approval time from the sorting result of the historical approval time record data according to the first sequence number; extract the second characteristic approval time from the sorting result of the historical approval time record data according to the second sequence number; calculate 1.5 times the difference between the second characteristic approval time and the first characteristic approval time, and store it as the first range; calculate the first characteristic approval time minus the first range to obtain the first boundary time; calculate the second characteristic approval time plus the first range to obtain the second boundary time. The historical approval duration record data that is greater than or equal to the first boundary duration and less than or equal to the second boundary duration is stored as centralized data, the centralized data is averaged, the first approval duration label is stored, and added to the approval duration label set. Through centralized trend analysis, accidental values ​​can be deleted to improve the accuracy of processing results.

[0083] Further, the first-level approval request set, the second-level approval request set, and finally the M-level approval request set are traversed, and the idle time zone label list and the approval duration label set are combined to perform task allocation on the first node approval particle list to obtain the first node approval request task allocation list. Step S54 includes the following steps:

[0084] S541: Construct task allocation fitness evaluation function:

[0085] ,

[0086] in, Characterize the fitness of any task allocation scheme, Characterize any task allocation scheme, Represents the i-th approval request, Represents the approval time of the i-th approval request, represents the allocated idle time zone of the i-th approval request, c represents a small constant, Characterize the first weight, Characterize the second weight, Characterize the jth approval particle, represents the number of approval requests allocated to the j-th approval particle, H represents the total number of approval particles, and Q represents the total number of approval requests;

[0087] S542: configuring a task allocation condition, wherein the task allocation condition includes a first constraint condition and a second constraint condition, the first constraint condition being that the k-level approval request has a higher priority than the k+1 approval request, and the second constraint condition being that the approval duration is less than or equal to the allocated idle time zone step;

[0088] S543: Based on the first constraint condition and the second constraint condition, traverse the first-level approval request set, the second-level approval request set, and finally the M-level approval request set, and perform task allocation on the first node approval particle list in combination with the idle time zone label list and the approval duration label set to obtain a first node approval request task allocation solution set;

[0089] S544: According to the task allocation fitness evaluation function, the first node approval request task allocation scheme set is sorted by maximum value to obtain the first node approval request task allocation list.

[0090] In the embodiment of the present invention, in order to ensure the rationality of task allocation, for example, the difference between the task processing time and the total time of the deployment time zone is as small as possible, and the number of processing requests of each approval granule is as balanced as possible, in order to meet the above two requirements, a task allocation fitness evaluation function is constructed: ,in, Characterize the fitness of any task allocation scheme, Characterize any task allocation scheme, represents the i-th approval request, Represents the approval time of the i-th approval request, represents the allocated idle time zone of the i-th approval request, c represents a small constant, Characterize the first weight, Characterize the second weight, Characterize the jth approval particle, represents the number of approval requests allocated to the j-th approval particle, H represents the total number of approval particles, and Q represents the total number of approval requests.

[0091] Then configure the task allocation conditions, where the task allocation conditions include a first constraint and a second constraint. The first constraint is that the k-level approval request allocation priority is greater than the k+1 approval request, that is, it needs to be allocated in sequence according to the priority defined by the tree. The second constraint is that the approval time is less than or equal to the allocated idle time zone step, that is, the time zone span of the requested deployment must be greater than its predicted approval time.

[0092] Based on the first constraint and the second constraint, the first-level approval request set, the second-level approval request set, and finally the M-level approval request set are traversed, and the first node approval particle list is assigned tasks in combination with the idle time zone label list and the approval duration label set to obtain a first node approval request task allocation scheme set that meets the first constraint and the second constraint. Then, according to the task allocation fitness evaluation function, the first node approval request task allocation scheme set is sorted for the maximum value to obtain the first node approval request task allocation list. A more reasonable task allocation result can be selected through the optimization process.

[0093] The data approval method based on artificial intelligence provided by the embodiment of the present invention has at least the following technical effects:

[0094] Provided is a technical solution in which a user terminal receives an approval request queue input by a user and uploads it to a server, and then uses a cluster analysis module to perform clustering according to the user request time to obtain an approval request cluster sequence; the approval request can be quickly matched with an approval node sequence according to the business number label; then, according to the approval node sequence queue and the approval request cluster sequence, a first node approval request tree, a second node approval request tree, and up to the Nth node approval request tree are constructed; further, tasks are assigned to the first node approval request tree, the second node approval request tree, and up to the Nth node approval request tree, to obtain a first node approval request task assignment list, a second node approval request task assignment list, and up to the Nth node approval request task assignment list. Since each task assignment result has an approval request processing time zone label, it can be processed in a timely manner, thereby achieving a technical effect of flexible scheduling of approval nodes.

[0095] Embodiment 2:

[0096] like Figure 2 As shown, based on the same inventive concept as the data approval method based on artificial intelligence provided in Embodiment 1, the embodiment of the present invention further provides a data approval system based on artificial intelligence, including:

[0097] A user end is used to receive an approval request queue, wherein any approval request in the approval request queue has a service number tag and a request time tag;

[0098] Servers, including:

[0099] A cluster analysis module, configured to perform cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label;

[0100] An approval node sequence matching module, used to traverse the approval request queue and match the approval node sequence queue according to the business number tag;

[0101] An approval request tree building module, used to build a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree according to the approval node sequence queue and the approval request cluster sequence;

[0102] Task allocation optimization module, used for:

[0103] Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list;

[0104] According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list;

[0105] Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list;

[0106] The data approval execution module is used to perform data approval management according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

[0107] Furthermore, the cluster analysis module executes the steps including:

[0108] Configure consistent time deviation;

[0109] Clustering the approval request queue according to the consistent time deviation to obtain multiple clusters of approval requests;

[0110] Traversing the multiple clusters of approval requests to extract the median request time, and obtaining multiple median request times;

[0111] The plurality of clusters of approval requests are sorted from first to last according to the plurality of median request times to obtain the approval request cluster sequence.

[0112] Furthermore, the approval request tree building module execution steps include:

[0113] Performing a first-level aggregation on the approval request queue according to the approval node sequence queue to generate a first node approval request set, a second node approval request set, and finally an Nth node approval request set;

[0114] According to the approval request cluster sequence, traverse the first node approval request set, the second node approval request set, and the Nth node approval request set to perform secondary aggregation, and obtain the first node approval request cluster sequence, the second node approval request cluster sequence, and the Nth node approval request cluster sequence;

[0115] The first node approval request cluster sequence, the second node approval request cluster sequence, and the Nth node approval request cluster sequence are traversed to construct the first node approval request tree, the second node approval request tree, and the Nth node approval request tree.

[0116] Furthermore, the approval request tree building module execution steps include:

[0117] Extracting a first cluster approval request set, a second cluster approval request set, and finally an Mth cluster approval request set according to the first node approval request cluster sequence;

[0118] The first node approval request tree is generated by taking the first node as the root node, the first cluster approval request set as the first-level leaf node, the second cluster approval request set as the second-level leaf node, until the Mth cluster approval request set is the M-level leaf node.

[0119] Furthermore, the task allocation optimization module executes the steps including:

[0120] Obtaining a first-level approval request set, a second-level approval request set, and finally an M-level approval request set of the approval request tree of the first node;

[0121] Obtaining a first node approval particle list, wherein the first node approval particle list has an idle time zone label list;

[0122] Traversing the first node approval request tree to predict the approval time and generate an approval time label set;

[0123] The first-level approval request set, the second-level approval request set, and finally the M-level approval request set are traversed, and the idle time zone label list and the approval duration label set are combined to perform task allocation on the first node approval particle list to obtain the first node approval request task allocation list.

[0124] Furthermore, the task allocation optimization module executes the steps including:

[0125] Extracting the first approval request of the first node according to the first node approval request tree;

[0126] Counting a data set of historical approval duration records of the first approval request at the first node;

[0127] A central trend analysis is performed on the historical approval time record data set to obtain a first approval time label, which is added to the approval time label set.

[0128] Furthermore, the task allocation optimization module executes the steps including:

[0129] Construct task allocation fitness evaluation function:

[0130] ,

[0131] in, Characterize the fitness of any task allocation scheme, Characterize any task allocation scheme, Represents the i-th approval request, Represents the approval time of the i-th approval request, represents the allocated idle time zone of the i-th approval request, c represents a small constant, Characterize the first weight, Characterize the second weight, Characterize the jth approval particle, represents the number of approval requests allocated to the j-th approval particle, H represents the total number of approval particles, and Q represents the total number of approval requests;

[0132] Configure task allocation conditions, wherein the task allocation conditions include a first constraint condition and a second constraint condition, the first constraint condition is that the k-level approval request allocation priority is greater than the k+1 approval request, and the second constraint condition is that the approval duration is less than or equal to the allocation idle time zone step;

[0133] Based on the first constraint condition and the second constraint condition, traverse the first-level approval request set, the second-level approval request set, and finally the M-level approval request set, and perform task allocation on the first node approval particle list in combination with the idle time zone label list and the approval duration label set to obtain a first node approval request task allocation solution set;

[0134] According to the task allocation fitness evaluation function, the first node approval request task allocation scheme set is sorted for maximum value to obtain the first node approval request task allocation list.

[0135] Embodiment three:

[0136] See also Figure 3 , Figure 3 Schematic diagram of an embodiment of a computer terminal provided by an embodiment of the present invention. Figure 3 As shown, the embodiment of the present invention provides a computer terminal 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0137] receiving an approval request queue, wherein any approval request in the approval request queue has a business number tag and a request time tag;

[0138] Performing cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label;

[0139] According to the business number tag, traverse the approval request queue and match the approval node sequence queue;

[0140] According to the approval node sequence queue and the approval request cluster sequence, construct a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree;

[0141] Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list;

[0142] According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list;

[0143] Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list;

[0144] Data approval management is performed according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

[0145] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, 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.

[0146] 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.

[0147] 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.

[0148] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A data approval system based on artificial intelligence, characterized in that: include: A user end is used to receive an approval request queue, wherein any approval request in the approval request queue has a service number tag and a request time tag; Servers, including: A cluster analysis module, configured to perform cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label; An approval node sequence matching module, used to traverse the approval request queue and match the approval node sequence queue according to the business number tag; An approval request tree building module, used to build a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree according to the approval node sequence queue and the approval request cluster sequence; Task allocation optimization module, used for: Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list; According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list; Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list; The data approval execution module is used to perform data approval management according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

2. The system according to claim 1, characterized in that The cluster analysis module execution steps include: Configure consistent time deviation; Clustering the approval request queue according to the consistent time deviation to obtain multiple clusters of approval requests; Traversing the multiple clusters of approval requests to extract the median request time, and obtaining multiple median request times; The plurality of clusters of approval requests are sorted from first to last according to the plurality of median request times to obtain the approval request cluster sequence.

3. The system according to claim 1, characterized in that The steps of executing the approval request tree building module include: Performing a first-level aggregation on the approval request queue according to the approval node sequence queue to generate a first node approval request set, a second node approval request set, and finally an Nth node approval request set; According to the approval request cluster sequence, traverse the first node approval request set, the second node approval request set, and the Nth node approval request set to perform secondary aggregation, and obtain the first node approval request cluster sequence, the second node approval request cluster sequence, and the Nth node approval request cluster sequence; The first node approval request cluster sequence, the second node approval request cluster sequence, and the Nth node approval request cluster sequence are traversed to construct the first node approval request tree, the second node approval request tree, and the Nth node approval request tree.

4. The system according to claim 3, characterized in that The steps of executing the approval request tree building module include: Extracting a first cluster approval request set, a second cluster approval request set, and finally an Mth cluster approval request set according to the first node approval request cluster sequence; The first node approval request tree is generated by taking the first node as the root node, the first cluster approval request set as the first-level leaf node, the second cluster approval request set as the second-level leaf node, until the Mth cluster approval request set is the M-level leaf node.

5. The system according to claim 1, wherein: The task allocation optimization module execution steps include: Obtaining a first-level approval request set, a second-level approval request set, and finally an M-level approval request set of the approval request tree of the first node; Obtaining a first node approval particle list, wherein the first node approval particle list has an idle time zone label list; Traversing the first node approval request tree to predict the approval time and generate an approval time label set; The first-level approval request set, the second-level approval request set, and finally the M-level approval request set are traversed, and the idle time zone label list and the approval duration label set are combined to perform task allocation on the first node approval particle list to obtain the first node approval request task allocation list.

6. The system according to claim 5, characterized in that The task allocation optimization module execution steps include: Extracting the first approval request of the first node according to the first node approval request tree; Counting a data set of historical approval duration records of the first approval request at the first node; A central trend analysis is performed on the historical approval time record data set to obtain a first approval time label, which is added to the approval time label set.

7. A data approval method based on artificial intelligence, characterized in that: include: receiving an approval request queue, wherein any approval request in the approval request queue has a business number tag and a request time tag; Performing cluster analysis on the approval request queue according to the request time label to obtain an approval request cluster sequence, wherein the approval request cluster sequence is arranged from first to last according to the request time label; According to the business number tag, traverse the approval request queue and match the approval node sequence queue; According to the approval node sequence queue and the approval request cluster sequence, construct a first node approval request tree, a second node approval request tree, and finally an Nth node approval request tree; Based on the first node approval request tree, optimizing the task allocation for the first node occupancy state, obtaining a first node approval request task allocation list, wherein the first node approval request task allocation list has a first node approval request processing time zone label list; According to the first node approval request processing time zone label list, in combination with the second node approval request tree, the task allocation optimization is performed on the second node occupancy state to obtain the second node approval request task allocation list, wherein the second node approval request task allocation list has the second node approval request processing time zone label list; Until the time zone label list of the N-1th node approval request is processed, the task allocation optimization of the Nth node occupancy state is performed in combination with the Nth node approval request tree to obtain the Nth node approval request task allocation list; Data approval management is performed according to the first node approval request task allocation list, the second node approval request task allocation list, and up to the Nth node approval request task allocation list.

8. The method according to claim 7, characterized in that According to the request time tag, cluster analysis is performed on the approval request queue to obtain an approval request cluster sequence, including: Configure consistent time deviation; Clustering the approval request queue according to the consistent time deviation to obtain multiple clusters of approval requests; Traversing the multiple clusters of approval requests to extract the median request time, and obtaining multiple median request times; The plurality of clusters of approval requests are sorted from first to last according to the plurality of median request times to obtain the approval request cluster sequence.

9. A computer terminal, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the artificial intelligence-based data approval method described in any one of claims 7 to 8.

Images