CN112215507A - AI-combined RPA system flow complexity determination method and device - Google Patents
AI-combined RPA system flow complexity determination method and device Download PDFInfo
- Publication number
- CN112215507A CN112215507A CN202011128614.XA CN202011128614A CN112215507A CN 112215507 A CN112215507 A CN 112215507A CN 202011128614 A CN202011128614 A CN 202011128614A CN 112215507 A CN112215507 A CN 112215507A
- Authority
- CN
- China
- Prior art keywords
- complexity
- rpa system
- evaluation model
- preset evaluation
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 187
- 230000008569 process Effects 0.000 claims abstract description 137
- 238000013210 evaluation model Methods 0.000 claims abstract description 113
- 238000010586 diagram Methods 0.000 claims description 29
- 238000013473 artificial intelligence Methods 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 18
- 238000003058 natural language processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004801 process automation Methods 0.000 description 3
- 230000026676 system process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a method and a device for determining the complexity of an RPA system flow combined with an AI, relating to the field of RPA and AI, wherein the method comprises the following steps: the RPA system acquires a plurality of process associated feature information of a target service, the RPA system inputs the process associated feature information into a preset evaluation model, the RPA system determines the complexity of the target service process according to the process associated feature information and the preset evaluation model to acquire a complexity determination result, and the RPA system comprehensively considers a plurality of process associated feature information when determining the complexity of the target service converted into the RPA process, so that the accuracy of the determination result is improved. And the RPA system is automatically executed by the electronic equipment in the whole process of determining the complexity of the RPA process, so that the efficiency of determining the complexity of the RPA process is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of Robot Process Automation (RPA) and AI (Artificial Intelligence), in particular to a method, a device, equipment and a storage medium for determining the Process complexity of an RPA system combined with AI.
Background
Robot Process Automation (RPA) is a Process task that simulates human operations on a computer by specific "robot software" and executes automatically according to rules. Artificial Intelligence (AI) is a technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. At present, the RPA and AI technologies have the advantages of high automation degree, high accuracy and low cost, and are widely applied.
Before an enterprise prepares a manually completed service flow to be converted into an RPA flow, the complexity of the RPA flow corresponding to the service flow needs to be determined, and whether the RPA flow is converted into the RPA flow is determined according to a determined result. In the prior art, when the complexity of the RPA process is determined, only experts in related fields are used for simply determining the complexity, so that the degree of specialization required for determining the complexity is high, and factors considered in the determination process are not comprehensive, so that the accuracy of the determined result is low, and the determination efficiency is also low.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for determining the complexity of an RPA system flow combined with AI, which solves the technical problems that in the prior art, only experts in related fields are used for simple determination, the degree of specialization required by the determination is high, factors considered in the determination process are not comprehensive, the accuracy of the determination result is low, and the determination efficiency is low.
In a first aspect, an embodiment of the present invention provides a method for determining a complexity of an RPA system process in combination with an AI, including:
the RPA system acquires a plurality of process associated characteristic information of a target service;
the RPA system inputs the associated characteristic information of each process into a preset evaluation model;
and the RPA system determines the complexity of the target service process according to the process correlation characteristic information and a preset evaluation model so as to obtain a complexity determination result.
In a second aspect, an embodiment of the present invention provides an apparatus for determining a flow complexity of an RPA system in conjunction with an AI, including:
the information acquisition module is used for acquiring a plurality of process associated characteristic information of the target service;
the information input module is used for inputting the relevant characteristic information of each process into a preset evaluation model;
and the result determining module is used for determining the complexity of the target business process according to the process correlation characteristic information and a preset evaluation model so as to obtain a complexity determining result.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method according to the first aspect.
The embodiment of the invention provides a method, a device, equipment and a storage medium for determining the flow complexity of an RPA system combined with AI, wherein the RPA system obtains a plurality of flow associated characteristic information of a target service, inputs each flow associated characteristic information into a preset evaluation model, and determines the complexity of the flow of the target service according to the flow associated characteristic information and the preset evaluation model to obtain a complexity determination result. And the RPA system is automatically executed by the electronic equipment in the whole process of determining the complexity of the RPA process, so that the efficiency of determining the complexity of the RPA process is improved.
It should be understood that what is described in the summary above is not intended to limit key or critical features of embodiments of the invention, nor is it intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for determining a complexity of an RPA system flow in conjunction with an AI according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for determining complexity of an RPA system flow in conjunction with an AI according to a second embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a configuration interface determined in the method for determining the complexity of an RPA system process in combination with an AI according to the second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for determining a complexity of an RPA system flow in combination with an AI according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for determining a complexity of an RPA system flow in combination with an AI according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and the embodiments of the present invention are illustrative only and are not intended to limit the scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, and in the above-described drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to clearly understand the technical solution of the embodiment of the present invention, the following explains the key words related to the embodiment of the present invention:
RPA procedure complexity: the complexity of the RPA process during execution may be represented by data such as a complexity score or a complexity level.
And (3) flow correlation characteristic information: is characteristic information associated with the processing flow of the target business. Such as may include: the method comprises the following steps of switching the screen of target equipment when processing target services, service scene types, the number of standard input data, the deployment mode of the target equipment, the number of structured input data, the number of free text input and the like.
Presetting an evaluation model: and determining a model of the complexity of the RPA process corresponding to the target service. The preset evaluation model may be a model for setting a mapping relationship between the numerical value of each process associated feature information and the complexity score, or may be an evaluation model constructed by a deep learning algorithm and trained to converge, or the like.
Example one
Fig. 1 is a flowchart of an AI-integrated RPA system flow complexity determining method according to an embodiment of the present invention, and as shown in fig. 1, an execution subject of the embodiment is an RPA (Robotic Process Automation) system, which may be integrated in an electronic device.
Step 1-S1, the RPA system obtains a plurality of flow associated characteristic information of the target service.
In this embodiment, the target service is a service that needs to perform RPA process complexity determination, for example, a service that needs to be performed manually in an enterprise, for example, a financial reimbursement service, a mail sending and receiving service, and the like.
And the process associated characteristic information is characteristic information associated with the processing process of the target service. Such as may include: the method comprises the following steps of switching the screen of target equipment when processing target services, service scene types, the number of standard input data, the deployment mode of the target equipment, the number of structured input data, the number of free text input and the like.
Specifically, in this embodiment, the manner of acquiring the multiple pieces of flow related feature information of the target service by the RPA system may be that the RPA system receives the flow related feature information configured on the configuration interface by the user, or may also be that the RPA system monitors flow data processed by the user on the target device, and then extracts the multiple pieces of flow related feature information from the flow data based on Natural Language Processing (NLP). Or a flow diagram of the target service can be constructed in advance, and the flow diagram is analyzed based on natural language processing to obtain a plurality of flow associated characteristic information.
It can be understood that the manner in which the RPA system acquires the multiple pieces of flow associated feature information of the target service may also be other manners, which is not limited in this embodiment.
Step 1-S2, the RPA system inputs the relevant characteristic information of each process into a preset evaluation model.
Step 1-S3, the RPA system determines the complexity of the target service process according to the process correlation characteristic information and a preset evaluation model to obtain a complexity determination result.
Specifically, as an optional implementation manner, in this embodiment, a mapping relationship between a numerical value of each process associated feature information and a complexity score may be set in a preset evaluation model, and after the RPA system acquires the process associated feature information, the RPA system determines the numerical value of each process associated feature information, and inputs the numerical value into the preset evaluation model, so as to determine a corresponding complexity score according to the numerical value of each process associated feature information, and further determine a final total complexity score according to the complexity score corresponding to each process associated feature information, and obtain a complexity determination result according to the total complexity score.
As an optional implementation manner, in this embodiment, after the preset evaluation model may be a deep learning model and the RPA system acquires the associated feature information of each process, the associated feature information of each process may be input into the preset evaluation model, and the associated feature information of each process is analyzed by the preset evaluation model to output a complexity determination result. The complexity determination result may be level information of complexity.
It is to be understood that the RPA system may also determine the complexity determination result in other manners, which is not limited in this embodiment.
In the method for determining the complexity of the RPA system process in combination with the AI according to this embodiment, the multiple process-related feature information of the target service is acquired, each process-related feature information is input into the preset evaluation model, and the complexity of the target service process is determined according to the process-related feature information and the preset evaluation model, so as to obtain the complexity determination result. And the RPA system is automatically executed by the electronic equipment in the whole process of determining the complexity of the RPA process, so that the efficiency of determining the complexity of the RPA process is improved.
Example two
Fig. 2 is a flowchart of a method for determining complexity of a flow of an RPA system combined with an AI according to a second embodiment of the present invention, and as shown in fig. 2, the method for determining complexity of a flow of an RPA system combined with an AI according to the present embodiment is further detailed in steps 1 to S1 to steps 1 to S3 based on the method for determining complexity of a flow of an RPA system combined with an AI according to the first embodiment of the present invention, and the method for determining complexity of a flow of an RPA system combined with an AI according to the present embodiment includes the following steps.
And 2-S1, the RPA system acquires a plurality of flow associated characteristic information of the target service.
Wherein, the flow associated characteristic information comprises any of the following: the method comprises the following steps of screen switching times of target equipment, service scene types, the number of standard input data, the deployment mode of the target equipment, the number of structured input data and the number of free text input.
The target device is a device corresponding to the target service. If the complexity of the target service is high, the number of target devices may be multiple, and the number of screen switching times of the target devices is large. If the target equipment corresponding to one target service is provided with a local computer, a remote computer and a virtual machine, and when the target service is processed, the screen switching times of the target equipment are determined, wherein the screen switching times of the target equipment are required to be switched among several target equipment.
And the service scene type is the scene type to which the target service belongs. Such as financial reimbursement scenario, invoice audit scenario, payment for consumption scenario, etc.
In this embodiment, the RPA system may preset standard input data corresponding to a target service for a scene type of the target service, then obtain the input data of the target service, determine whether the input data conforms to the standard input data corresponding to the scene type, and further determine the number of the standard input data corresponding to the target service.
The deployment mode of the target device may be local deployment, remote deployment, virtual machine deployment, and the like.
The structured input data may be structured text input data, and the structured text is structured data composed of a title, a chapter, a paragraph, and the like. While free text is unstructured text. Such as invoices, attachments, etc. in the reimbursement service.
As an optional implementation manner, in this embodiment, steps 2 to S1 specifically include:
step 2-S11, the RPA system monitors the flow data of the user processing the target service on the target device.
And 2, step S12, the RPA system extracts a plurality of flow associated characteristic information from the flow data.
Specifically, in this optional implementation, when the user manually processes the target service on the target device, the RPA system may monitor each link in the target service processing flow, and further extract a plurality of flow associated feature information from the flow data based on natural language processing.
In this embodiment, when the RPA system acquires multiple pieces of flow associated feature information of a target service, the RPA system can acquire the flow associated feature information automatically without user involvement by monitoring flow data of a user processing the target service on a target device and extracting the multiple pieces of flow associated feature information from the flow data based on natural language processing.
As another optional implementation manner, in this embodiment, steps 2 to S1 specifically include:
and 2-S1 a, the RPA system presents a determined configuration interface to a user, and the determined configuration interface comprises a plurality of information configuration items.
Step 2-S1 b, the RPA system receives the flow associated characteristic information configured by the user through the corresponding information configuration item on the determined configuration interface.
Specifically, in this optional embodiment, as shown in fig. 3, the RPA system displays a configuration interface to a user through a screen of the electronic device, where the configuration interface includes a plurality of information configuration items, the user may input or select corresponding process-related feature information by clicking each information configuration item, and the RPA system receives the process-related feature information configured by the user through the corresponding information configuration item on the certain configuration interface.
In this embodiment, when acquiring multiple pieces of flow associated feature information of a target service, the RPA system displays a certain configuration interface to a user, determines that the configuration interface includes multiple information configuration items, receives flow associated feature information configured by the user on the certain configuration interface through corresponding information configuration items, and can quickly acquire the multiple pieces of flow associated feature information of the target service through interaction with the user, thereby improving efficiency of acquiring the multiple pieces of flow associated feature information of the target service.
As another optional implementation manner, in this embodiment, steps 2 to S1 specifically include:
and 2, S1A, and a flow chart of the RPA system for acquiring the target service.
And 2, step 1B, the RPA system analyzes the flow diagram based on natural language processing to obtain a plurality of flow associated characteristic information.
Specifically, in this optional implementation, the RPA system pre-constructs a flow diagram of the target service, and the flow diagram of the target service may be automatically generated after the electronic device monitors flow data processed by the user on the target device for the target service. The processing flow of the target business and the flow related data required by each link of the processing flow are written in detail in the flow block diagram of the target business. Therefore, after the RPA system analyzes the flow diagram of the target service, the RPA system can acquire flow related data, and then extract the flow related data based on natural language processing to acquire corresponding flow associated feature information.
After the flow diagram of the target service is generated, the RPA system may store the flow diagram of the target service in a preset area, and may acquire the flow diagram of the target service from the preset area when the flow diagram of the target service needs to be acquired. It should be noted that, the user may obtain the flow diagram of the target service from the preset area, and may visually display the flow diagram to determine whether the flow diagram of the target service is accurate, and if not, may adjust the flow diagram of the target service.
In this embodiment, when acquiring the multiple pieces of flow associated feature information of the target service, the RPA system first acquires the flow diagram of the target service, and then analyzes the flow diagram to acquire the multiple pieces of flow associated feature information.
Step 2-S20, the RPA system sets the mapping relation between the numerical value of each process correlation characteristic information and the complexity score; and storing the mapping relation into the corresponding preset evaluation model.
Specifically, in this embodiment, when the RPA system acquires the associated feature information of each process of the target service, each piece of the associated feature information of each process may correspond to a numerical value, and the higher the numerical value is, the more complicated the corresponding process link associated with the feature information is. Conversely, the lower the numerical value, the simpler the corresponding process link associated with the characteristic information is represented. The RPA system may preset a mapping relationship between the numerical value of each process associated feature information and the complexity score, and store the mapping relationship in the corresponding preset evaluation model.
It can be understood that, if the RPA system inputs each process related feature information into the first preset evaluation model, the mapping relationship is stored into the first preset evaluation model, and if the RPA system inputs each process related feature information into the second preset evaluation model, the mapping relationship is stored into the second preset evaluation model.
And 2-S2, inputting the relevant characteristic information of each process into a preset evaluation model by the RPA system.
And 2-S3, the RPA system determines the complexity of the target service process according to the process correlation characteristic information and a preset evaluation model to obtain a complexity determination result.
Optionally, steps 2 to S3 include:
and 2-S31, the RPA system selects a target preset evaluation model from at least one preset evaluation model.
It can be understood that, the RPA system may preset at least one preset evaluation model, and after the associated feature information of each process is input into the preset evaluation model, a target preset evaluation model may be selected from the at least one preset evaluation model to obtain the total complexity score.
And 2-S32, the RPA system determines the complexity score corresponding to each process associated characteristic information and a total complexity score calculation strategy through a target preset evaluation model, and calculates the complexity score corresponding to each process associated characteristic information according to the total complexity score calculation strategy so as to output the total complexity score.
It can be understood that the same process associated feature information may correspond to different complexity scores in different preset evaluation models, and different preset evaluation models may correspond to different total complexity score calculation strategies.
Therefore, the method can select a target preset evaluation model from at least one preset evaluation model, then determine the complexity value corresponding to each process associated characteristic information and a complexity total score calculation strategy through the target preset evaluation model, and calculate the complexity value corresponding to each process associated characteristic information according to the complexity total score calculation strategy so as to output the complexity total score.
As an optional implementation manner, in this embodiment, if the preset evaluation model is the first preset evaluation model, steps 2 to S2 include the following steps:
and 2-S21, inputting the relevant characteristic information of each process into a first preset evaluation model by the RPA system.
In this alternative embodiment, the target preset evaluation model is the first preset evaluation model, and steps 2 to S3 include:
and 2-S33, the RPA system selects a first preset evaluation model from at least one preset evaluation model as a target preset evaluation model.
And 2-S34, the RPA system determines complexity scores corresponding to the associated characteristic information of each process through a first preset evaluation model, and sums the complexity scores to output a total complexity score.
Specifically, in this optional implementation, the RPA system prestores a mapping relationship between the numerical value of each piece of process-related feature information and the complexity score in the first preset evaluation model, so that after obtaining each piece of process-related feature information of the target service, the RPA system can query the mapping relationship through the first preset evaluation model, obtain the complexity score corresponding to the numerical value of each piece of process-related feature information, and determine the complexity score as the complexity score corresponding to the piece of process-related feature information.
After the complexity score corresponding to each process association characteristic information of the target service is determined through the first preset evaluation model, the complexity scores can be summed, the summed result is used as a total complexity score, and the first preset evaluation model can output the total complexity score.
In this embodiment, the RPA system determines the complexity of the target service flow according to the flow associated feature information and the preset evaluation model, so that when the complexity determination result is obtained, the flow associated feature information can be input into the first preset evaluation model; selecting a first preset evaluation model from at least one preset evaluation model as a target preset evaluation model; complexity scores corresponding to the relevant characteristic information of each process are determined through the first preset evaluation model, and the complexity scores are summed to output a total complexity score, so that the total complexity score can be quickly determined.
As another alternative, in this embodiment, if the preset evaluation model is the second preset evaluation model, steps 2 to S2 include the following steps:
and 2, step S22, inputting the relevant characteristic information of each process into a second preset evaluation model by the RPA system.
In this alternative embodiment, the target preset evaluation model is the second preset evaluation model, and steps 2 to S3 include:
and 2-S35, the RPA system selects a second preset evaluation model from at least one preset evaluation model as a target preset evaluation model.
And 2-S36, determining complexity scores corresponding to the process associated characteristic information through a second preset evaluation model by the RPA system, determining weights corresponding to the process associated characteristic information, and performing weighted summation on the complexity scores to output a total complexity score.
Specifically, in this optional implementation manner, in the second preset evaluation model, the RPA system not only stores the mapping relationship between the numerical value of each piece of flow-related feature information and the complexity score in advance, but also stores the weight corresponding to each piece of flow-related feature information. The larger the influence of each process associated feature information on the target service processing complexity is, the larger the corresponding weight is, otherwise, the smaller the influence of each process associated feature information on the target service processing complexity is, the smaller the corresponding weight is, and the summation result of each weight is 1.
After acquiring the relevant characteristic information of each process of the target service, the RPA system may query the mapping relationship through a second preset evaluation model, acquire the complexity score corresponding to the numerical value of the relevant characteristic information of each process, and determine the complexity score as the complexity score corresponding to the relevant characteristic information of the process.
After the complexity score corresponding to each process associated feature information of the target service is determined through the second preset evaluation model, the weight corresponding to each process associated feature information can be obtained, the complexity scores are subjected to weighted summation, the result of the weighted summation is used as the total complexity score, and the second preset evaluation model can output the total complexity score.
In this embodiment, the RPA system determines the complexity of the target service flow according to the flow associated feature information and the preset evaluation model, so that when the complexity determination result is obtained, the flow associated feature information can be input into the second preset evaluation model; selecting a second preset evaluation model from at least one preset evaluation model as a target preset evaluation model; and determining complexity scores corresponding to the associated characteristic information of each process through a second preset evaluation model, determining weights corresponding to the associated characteristic information of each process, and performing weighted summation on the complexity scores to output a total complexity score.
Optionally, in this embodiment, steps 2 to S4 are further included.
And 2-S4, the RPA system determines the feasibility index of converting the target service into the RPA process according to the complexity determination result.
In this embodiment, as an optional implementation manner, if the complexity determination result is a complexity level, the feasibility index may be a feasibility level. The RPA system may preset a mapping relationship between the complexity level and the feasibility level of the RPA process, and after obtaining the complexity determination result of the target service, obtain the feasibility level mapped with the complexity determination result according to the mapping relationship, and determine the feasibility level mapped with the complexity determination result as a feasibility index corresponding to the target service and converted into the RPA process.
Or as another alternative, if the complexity determination result is a total complexity score, the feasibility index may be a feasibility score. The RPA system may preset a mapping relationship between the total complexity score and the feasibility score of the RPA process, and after obtaining the complexity determination result of the target service, obtain the feasibility score mapped with the complexity determination result according to the mapping relationship, and determine the feasibility score mapped with the complexity determination result as a feasibility index corresponding to the target service and converted into the RPA process.
It can be understood that the mode of determining the feasibility index converted into the RPA process by the RPA system according to the complexity determination result may also be other modes, which is not limited in this embodiment.
In the method for determining the complexity of the RPA system flow combined with the AI provided by this embodiment, when the RPA system obtains a plurality of flow associated feature information of a target service, and determines the complexity of the target service flow according to the flow associated feature information and a preset evaluation model to obtain a complexity determination result, the RPA system has a plurality of implementation manners, which not only can improve the accuracy and the determination efficiency of the determination result, but also makes the flow complexity determination method more versatile and is suitable for a plurality of types of services.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an AI-integrated RPA system flow complexity determining apparatus according to a third embodiment of the present invention, and as shown in fig. 4, an AI-integrated RPA system flow complexity determining apparatus 40 according to the present embodiment includes: an information acquisition module 41, a result determination module 42, and an index determination module 43.
The information obtaining module 41 is configured to obtain multiple pieces of process-related feature information of the target service. And the information input module 42 is used for inputting the relevant characteristic information of each process into a preset evaluation model. And a result determining module 43, configured to determine the complexity of the target business process according to the process-related feature information and a preset evaluation model, so as to obtain a complexity determining result.
The apparatus for determining complexity of a process of an RPA system in combination with an AI according to this embodiment may implement the technical solution of the method embodiment shown in fig. 1, and the implementation principle and the technical effect are similar, which are not described herein again.
Example four
Fig. 5 is a schematic structural diagram of an AI-combined RPA system flow complexity determining apparatus according to a fourth embodiment of the present invention, and as shown in fig. 5, the AI-combined RPA system flow complexity determining apparatus according to this embodiment further includes, on the basis of the AI-combined RPA system flow complexity determining apparatus according to a third embodiment of the present invention: and a mapping relation storage module 51.
Optionally, the information obtaining module 41 is specifically configured to: monitoring process data of a user processing a target service on target equipment; a plurality of flow associated feature information are extracted from the flow data based on Natural Language Processing (NLP).
Optionally, the information obtaining module 41 is specifically configured to: displaying a configuration determining interface to a user, wherein the configuration determining interface comprises a plurality of information configuration items; and receiving the process associated characteristic information configured by the user through the corresponding information configuration item on the determined configuration interface.
Optionally, the information obtaining module 41 is specifically configured to: acquiring a flow diagram of a target service; and analyzing the flow diagram based on the natural language processing NLP to acquire a plurality of flow associated characteristic information.
Wherein, the flow associated characteristic information comprises any of the following:
the method comprises the following steps of screen switching times of target equipment, service scene types, the number of standard input data, the deployment mode of the target equipment, the number of structured input data and the number of free text input.
Optionally, the result determining module 43 is specifically configured to: selecting a target preset evaluation model from at least one preset evaluation model; and determining a complexity score and a total complexity score calculation strategy corresponding to each process associated characteristic information through the target preset evaluation model, and calculating the complexity score corresponding to each process associated characteristic information according to the total complexity score calculation strategy to output a total complexity score.
Optionally, the result determining module 43 is specifically configured to: selecting a first preset evaluation model from at least one preset evaluation model as a target preset evaluation model; and determining complexity scores corresponding to the associated characteristic information of each process through the first preset evaluation model, and summing the complexity scores to output a total complexity score.
Optionally, the result determining module 43 is specifically configured to: selecting a second preset evaluation model from at least one preset evaluation model as a target preset evaluation model; and determining complexity scores corresponding to the associated characteristic information of each process through the second preset evaluation model, determining weights corresponding to the associated characteristic information of each process, and performing weighted summation on the complexity scores to output a total complexity score.
Optionally, the mapping relationship storage module 51 is configured to set a mapping relationship between a numerical value of each process associated feature information and a complexity score; and storing the mapping relation into the corresponding preset evaluation model.
The apparatus for determining complexity of a process of an RPA system in combination with an AI according to this embodiment may implement the technical solution of the method embodiment shown in fig. 2, and the implementation principle and the technical effect are similar, which are not described herein again.
EXAMPLE five
Fig. 6 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and as shown in fig. 6, an electronic device 600 according to the fifth embodiment of the present invention includes: memory 601, processor 602, and computer programs.
Wherein a computer program is stored in the memory 601 and configured to be executed by the processor 602 to implement the method for RPA system flow complexity determination in conjunction with AI provided in the first or second embodiment.
The relevant description may be understood by referring to the relevant description and effect corresponding to the steps in fig. 1-2, and will not be described herein too much.
The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for determining the complexity of the flow of the RPA system in combination with the AI according to any one of the first to second embodiments of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware form, and can also be realized in a form of hardware and a software functional module.
Program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (12)
1. A method for determining the complexity of an RPA system flow combined with an AI (Artificial Intelligence Association) is characterized by comprising the following steps:
the RPA system acquires a plurality of process associated characteristic information of a target service;
the RPA system inputs the associated characteristic information of each process into a preset evaluation model;
and the RPA system determines the complexity of the target service process according to the process correlation characteristic information and a preset evaluation model so as to obtain a complexity determination result.
2. The method according to claim 1, wherein the RPA system obtaining a plurality of process-associated feature information of a target service specifically includes:
the RPA system monitors the process data of the user on the target equipment for processing the target service;
the RPA system extracts a plurality of flow associated characteristic information from the flow data based on Natural Language Processing (NLP).
3. The method according to claim 1, wherein the RPA system monitors process data of the user processing the target service on the target device, and specifically includes:
the RPA system displays a determined configuration interface to a user, wherein the determined configuration interface comprises a plurality of information configuration items;
and the RPA system receives the process associated characteristic information configured by the user through the corresponding information configuration item on the determined configuration interface.
4. The method according to claim 1, wherein the RPA system monitors process data of the user processing the target service on the target device, and specifically includes:
the RPA system acquires a flow diagram of a target service;
and the RPA system analyzes the flow diagram based on Natural Language Processing (NLP) so as to acquire a plurality of flow associated characteristic information.
5. The method according to claim 1, wherein the RPA system determines the complexity of the target business process according to the process-related feature information and a preset evaluation model to obtain a complexity determination result, specifically comprising:
the RPA system selects a target preset evaluation model from at least one preset evaluation model;
and the RPA system determines a complexity score and a total complexity score calculation strategy corresponding to each process associated characteristic information through the target preset evaluation model, and calculates the complexity score corresponding to each process associated characteristic information according to the total complexity score calculation strategy so as to output a total complexity score.
6. The method according to claim 5, wherein the RPA system determines the complexity of the target business process according to the process-related feature information and a preset evaluation model to obtain a complexity determination result, specifically comprising:
the RPA system selects a first preset evaluation model from at least one preset evaluation model as a target preset evaluation model;
and the RPA system determines complexity scores corresponding to the associated characteristic information of each process through the first preset evaluation model, and sums the complexity scores to output a total complexity score.
7. The method according to claim 5, wherein the RPA system determines the complexity of the target business process according to the process-related feature information and a preset evaluation model to obtain a complexity determination result, specifically comprising:
the RPA system selects a second preset evaluation model from at least one preset evaluation model as a target preset evaluation model;
and the RPA system determines the complexity score corresponding to each process associated characteristic information through the second preset evaluation model, determines the weight corresponding to each process associated characteristic information, and performs weighted summation on each complexity score to output the total complexity score.
8. The method according to claim 5 or 6, wherein before the RPA system inputs the process-related feature information into the preset evaluation model, the method further comprises:
and the RPA system sets a mapping relation between the numerical value of the associated characteristic information of each process and the complexity score, and stores the mapping relation into a corresponding preset evaluation model.
9. The method of claim 1, wherein the process-related feature information comprises any of:
the method comprises the following steps of screen switching times of target equipment, service scene types, the number of standard input data, the deployment mode of the target equipment, the number of structured input data and the number of free text input.
10. An apparatus for determining flow complexity of an RPA system in conjunction with AI, comprising:
the information acquisition module is used for acquiring a plurality of process associated characteristic information of the target service;
the information input module is used for inputting the relevant characteristic information of each process into a preset evaluation model;
and the result determining module is used for determining the complexity of the target business process according to the process correlation characteristic information and a preset evaluation model so as to obtain a complexity determining result.
11. An electronic device, comprising:
a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-9.
12. A computer-readable storage medium, on which a computer program is stored, which computer program is executable by a processor to implement the method according to any one of claims 1-9.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020106143540 | 2020-06-30 | ||
| CN202010614354.0A CN111724081A (en) | 2020-06-30 | 2020-06-30 | RPA flow complexity determining method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112215507A true CN112215507A (en) | 2021-01-12 |
Family
ID=72570298
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010614354.0A Pending CN111724081A (en) | 2020-06-30 | 2020-06-30 | RPA flow complexity determining method, device, equipment and storage medium |
| CN202011128614.XA Pending CN112215507A (en) | 2020-06-30 | 2020-10-20 | AI-combined RPA system flow complexity determination method and device |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010614354.0A Pending CN111724081A (en) | 2020-06-30 | 2020-06-30 | RPA flow complexity determining method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111724081A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344355A (en) * | 2021-05-28 | 2021-09-03 | 中国农业银行股份有限公司 | Method and related device for evaluating automation requirements of robot process of business |
| CN113628758A (en) * | 2021-07-28 | 2021-11-09 | 北京来也网络科技有限公司 | Information processing method and device based on AI and RPA |
| CN115878081A (en) * | 2023-02-23 | 2023-03-31 | 安徽思高智能科技有限公司 | High-value RPA demand analysis system based on process discovery |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598366B (en) * | 2020-11-27 | 2023-02-28 | 北京理工大学 | Automatic planning method and device for asset management approval process |
| CN112488562A (en) * | 2020-12-11 | 2021-03-12 | 北京金山云网络技术有限公司 | Service implementation method and device |
| CN113011494B (en) * | 2021-03-18 | 2024-02-27 | 北京百度网讯科技有限公司 | Feature processing method, device, equipment and storage medium |
| CN113095776B (en) * | 2021-03-23 | 2024-03-01 | Tcl华星光电技术有限公司 | Business process management method, device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446309A (en) * | 2010-10-13 | 2012-05-09 | 清华大学 | Process pattern based dynamic workflow planning system and method |
| CN106775906A (en) * | 2016-11-22 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Business flow processing method and device |
| US20180150068A1 (en) * | 2016-11-30 | 2018-05-31 | Siemens Aktiengesellschaft | Model processing method and apparatus, and machine-readable medium |
| CN108551489A (en) * | 2018-05-07 | 2018-09-18 | 广东电网有限责任公司 | A kind of application server load balancing method, system, device and storage medium |
| CN110033123A (en) * | 2019-03-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for business assessment |
| CN110992169A (en) * | 2019-11-29 | 2020-04-10 | 深圳乐信软件技术有限公司 | Risk assessment method, device, server and storage medium |
-
2020
- 2020-06-30 CN CN202010614354.0A patent/CN111724081A/en active Pending
- 2020-10-20 CN CN202011128614.XA patent/CN112215507A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446309A (en) * | 2010-10-13 | 2012-05-09 | 清华大学 | Process pattern based dynamic workflow planning system and method |
| CN106775906A (en) * | 2016-11-22 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Business flow processing method and device |
| US20180150068A1 (en) * | 2016-11-30 | 2018-05-31 | Siemens Aktiengesellschaft | Model processing method and apparatus, and machine-readable medium |
| CN108551489A (en) * | 2018-05-07 | 2018-09-18 | 广东电网有限责任公司 | A kind of application server load balancing method, system, device and storage medium |
| CN110033123A (en) * | 2019-03-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for business assessment |
| CN110992169A (en) * | 2019-11-29 | 2020-04-10 | 深圳乐信软件技术有限公司 | Risk assessment method, device, server and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344355A (en) * | 2021-05-28 | 2021-09-03 | 中国农业银行股份有限公司 | Method and related device for evaluating automation requirements of robot process of business |
| CN113628758A (en) * | 2021-07-28 | 2021-11-09 | 北京来也网络科技有限公司 | Information processing method and device based on AI and RPA |
| CN115878081A (en) * | 2023-02-23 | 2023-03-31 | 安徽思高智能科技有限公司 | High-value RPA demand analysis system based on process discovery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111724081A (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215507A (en) | AI-combined RPA system flow complexity determination method and device | |
| CN110119903B (en) | Data comprehensive analysis system | |
| CN104050078B (en) | Test script generates system | |
| CN110443222B (en) | Method and device for training face key point detection model | |
| CN110334816B (en) | Industrial equipment detection method, device, equipment and readable storage medium | |
| CN111242318B (en) | Service model training method and device based on heterogeneous feature library | |
| CN114936301B (en) | Intelligent household building material data management method, device, equipment and storage medium | |
| CN111178537A (en) | Feature extraction model training method and device | |
| US20140019207A1 (en) | Interactive in-memory based sales forecasting | |
| WO2019123703A1 (en) | Data analysis assistance device, data analysis assistance method, and data analysis assistance program | |
| CN114004700A (en) | Service data processing method and device, electronic equipment and storage medium | |
| Hondo et al. | Data provenance management for bioinformatics workflows using NoSQL database systems in a cloud computing environment | |
| CN111679808A (en) | RPA robot application requirement evaluation method and device | |
| JP2006235692A (en) | Information processor and system for supporting security countermeasure | |
| CN107256254B (en) | Industry prosperity index acquisition method, storage device and terminal | |
| CN111476446A (en) | Service state monitoring processing method, device, equipment and storage medium | |
| CN107729424B (en) | Data visualization method and equipment | |
| US20040015387A1 (en) | Product sales support method and product sales support apparatus | |
| WO2019123704A1 (en) | Data analysis assistance device, data analysis assistance method, and data analysis assistance program | |
| WO2022267364A1 (en) | Information recommendation method and device, and storage medium | |
| CN114416583A (en) | Workload determination method, device, equipment and storage medium for automatic test | |
| CN114185987A (en) | Data development visualization method, device, equipment and storage medium | |
| CN113743791A (en) | Business evaluation method and device for business work order, electronic equipment and medium | |
| CN112686554A (en) | Material management system and method | |
| CN113469284A (en) | Data analysis method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |