CN115935089B

CN115935089B - Get-on point recommendation optimization method and system based on RPA technology

Info

Publication number: CN115935089B
Application number: CN202310066805.5A
Authority: CN
Inventors: 肖培宁; 马春荃; 孙滨; 俞德明
Original assignee: Hangzhou Hesmore Information Technology Co ltd; Nanchang Hesi Information Technology Co ltd; Beijing Hesi Information Technology Co Ltd
Current assignee: Hangzhou Hesmore Information Technology Co ltd; Nanchang Hesi Information Technology Co ltd; Beijing Hesi Information Technology Co Ltd
Priority date: 2023-02-06
Filing date: 2023-02-06
Publication date: 2023-05-12
Anticipated expiration: 2043-02-06
Also published as: CN115935089A

Abstract

The application provides a get-on point recommendation optimization method and system based on an RPA technology, comprising the following steps: identifying the current state of the process automation robot; recommending at least one boarding recommendation point to a user of the process automation robot based on the current state using a predictive learning model, wherein the predictive learning model is trained based on actual selections of boarding recommendation points by the user; receiving a reply to the get-on recommendation point from the user; when the reply is to accept the at least one get-on recommendation point, adding the at least one get-on recommendation point to the process automation robot; based on the number of replied users, distributing confidence coefficient to each get-on recommendation point; and generating a suggested next batch of get-on recommendation points for selection according to the get-on recommendation points and the confidence level. The RPA technology is innovatively used in the test process of the taxi taking software, and the recommended test flow of the taxi taking point is optimized.

Description

Get-on point recommendation optimization method and system based on RPA technology

Technical Field

The application relates to the technical field of software testing, in particular to a get-on point recommendation optimization method and system based on an RPA technology.

Background

The RPA robot process automation technology, english is (Robotic Process Automation), is to simulate the operations such as mouse clicking, keyboard input and the like of a user through the integrated screen capturing and service process automation management technology, such as opening an application program, processing an Excel form, logging in a management system and the like, and changes a section of service with a certain rule and needing to be repeatedly executed into a section of process file capable of being automatically executed. And then the data is delivered to the designated RPA robot for 7 x 24 hours to be executed on demand.

In the existing taxi taking software testing process, such as taxiing, windward running and the like, a large amount of manual testing is needed, operations such as clicking, keyboard input and the like are simulated by a user, recommendation of a taxi taking point of the user is optimized again according to an optimization algorithm in the background after a test result is analyzed, and then manual operation is needed again to repeat the above processes. This process often requires significant human labor time costs.

The existing RPA technology is often used in the industries of electronic commerce, finance, securities and the like, and the RPA technology is not used in the test process of the taxi taking software.

Disclosure of Invention

In view of this, the present application aims to provide a get-on point recommendation optimization method and system based on RPA technology, which can solve the existing problems in a targeted manner.

Based on the above purpose, the application provides a get-on point recommendation optimization method based on an RPA technology, which comprises the following steps:

identifying the current state of the process automation robot;

recommending at least one boarding recommendation point to a user of the process automation robot based on the current state using a predictive learning model, wherein the predictive learning model is trained based on actual selections of boarding recommendation points by the user;

receiving a reply to the get-on recommendation point from the user;

when the reply is to accept the at least one get-on recommendation point, adding the at least one get-on recommendation point to the process automation robot;

based on the number of replied users, distributing confidence coefficient to each get-on recommendation point;

and generating a suggested next batch of get-on recommendation points for selection according to the get-on recommendation points and the confidence level.

Further, the identifying the current state of the process automation robot includes:

responding to an operation picture screenshot which is sent by any virtual network console server and corresponds to the associated RPA robot at present, and determining that the associated RPA robot is in an operation state at present; responding to a natural language processing result corresponding to the connection state of the RPA robot associated with any virtual network console server side and the console to indicate disconnection, and determining that the RPA robot associated with any virtual network console server side is in an offline state; or,

And responding to the triggering of a preset control in the RPA monitoring interface, and determining the current running state of the RPA robot corresponding to each virtual network console server according to the data information currently acquired from each virtual network console server and the connection state of the RPA robot associated with each virtual network console server and the console.

Further, the recommending at least one boarding recommendation point to the user of the process automation robot using the predictive learning model includes:

modeling preset real track data for displaying the geographic position of the passenger to obtain a predictive learning model;

calculating track similarity of preset real track data, selecting passenger geographic positions corresponding to the preset real track data with the similarity higher than a preset value, and extracting semantic information of all the passenger geographic positions;

calculating semantic similarity according to the semantic information of the geographic position of the passenger;

and selecting a plurality of geographic positions according to the calculation result of the semantic similarity, and displaying the geographic positions on a map as get-on recommendation points for the user of the process automation robot to select.

Further, the predictive learning model is trained by:

Storing a list of commonly used boarding points associated with the RPA workflow;

storing a past get-on point selection list corresponding to the user;

the predictive learning model is updated based on the list of common drive-in points, the list of past drive-in point selections, and the one or more drive-in points that are monitored.

Further, the adding the at least one get-on recommendation point to the process automation robot when the reply is to accept the at least one get-on recommendation point includes:

receiving at least one get-on recommendation point accepted by a user from a user interface of the RPA;

adding a resource/process pair corresponding to the get-on recommendation point to a command table of the RPA, wherein the resource/process pair represents the get-on recommendation point selected from the user interface;

determining that a redundant resource/process pair is included in the command table, the redundant resource/process pair being a repetition of the resource/process pair, and in response, deleting the redundant resource/process pair;

transmitting at least one command in the command table to an adapter of the process automation robot, the at least one command comprising a command to execute a process using a resource within an RPA platform;

or,

a wizard component that initiates a Customer Resource Management (CRM) component in the RPA;

Generating, using the wizard component, a result of a match between the predictive learning model and a plurality of fields of the customer resource management component;

and generating an RPA workflow based on a matching result of the guide component, wherein the RPA workflow adds the at least one boarding recommendation point to a combined box or a list box generated by the RPA workflow based on at least one field in a plurality of fields of the client resource management component.

Further, the assigning a confidence level to each get-on recommendation point based on the number of the replied users includes:

identifying a number of users selecting each pick-up recommendation point;

determining a recommendation event corresponding to each get-on recommendation point based on the number of users selecting each get-on recommendation point, wherein the recommendation event includes one or more event attributes determined based on one or more items;

determining event confidence of a recommended event corresponding to each on-board recommended point based on the event attribute;

or,

identifying a message of the user, wherein the message comprises a situation that whether the user replies to accept each get-on recommendation point;

determining a recommended event and initial event confidence of the recommended event according to the message;

the initial event confidence is presented via a graphical interface, and a new event confidence is determined for the recommended event based on one or more additional computer-based actions of the user associated with the recommended event.

Further, the generating a suggested next batch of get-on recommendation points according to the get-on recommendation points and the confidence level for selection comprises:

acquiring a selection standard of RPA, and deleting the get-on recommended points with the event confidence level lower than the selection standard;

displaying an interface for adding a get-on recommendation point by a user;

acquiring a get-on recommendation point added by a user;

and merging the deleted get-on recommendation points with the get-on recommendation points added by the user, taking the merged get-on recommendation points as the next get-on recommendation points and displaying a selection interface.

Based on the above purpose, the application further provides a get-on point recommendation optimization system based on the RPA technology, which comprises:

the state identification module is used for identifying the current state of the flow automatic robot;

a first recommendation module that recommends at least one get-on recommendation point to a user of the process automation robot based on the current state using a predictive learning model, wherein the predictive learning model is trained based on actual selection of the get-on recommendation point by the user;

the reply receiving module is used for receiving replies from the users to the get-on recommendation points;

the adding recommendation point module is used for adding the at least one get-on recommendation point to the flow automation robot when the reply is that the at least one get-on recommendation point is accepted;

The confidence coefficient module is used for distributing confidence coefficient to each get-on recommendation point based on the number of replied users;

and the second recommendation module generates a recommended next batch of get-on recommendation points for selection according to the get-on recommendation points and the confidence level.

Overall, the advantages of the present application and the experience brought to the user are:

the application innovatively uses the RPA technology in the test process of the taxi taking software, optimizes the recommended test flow of the taxi taking point, and has the following advantages:

1. high running speed

The RPA performs repetitive operations based on explicit business rules, which can be performed faster than humans, resulting in shorter response times and a greater number of tasks.

2. Low execution cost

The RPA robot can work for a long time without interruption for 7 x 24 hours, human errors can be avoided, and labor cost and time cost are saved.

3. Not replacing the existing system

The PRA robot is mainly based on a screen grabbing technology, simulates the operation of a user on a front end interface, can rapidly realize new business requirements without reconstructing an existing system, and reduces the complexity and risk of IT deployment.

4. High scalability

The RPA robot can be deployed based on a physical machine and a virtual machine, can also support the deployment and operation of different systems in different environments such as windows system, mac system, linux system, home-made system, mobile terminal and the like, and can expand service scenes and the number of robots at any time when enterprises have demands.

5. Safety compliance

The RPA executes tasks based on definite business rules, so that the accuracy and compliance of business processing are greatly improved, and errors possibly caused by manual processing are avoided. The user may perform the recording based on a log, screenshot, video omnibearing audit trail RPA.

Drawings

In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the disclosure and are not therefore to be considered limiting of its scope.

Fig. 1 shows a schematic diagram of the system architecture principle of the present application.

Fig. 2 shows a flowchart of a get-on point recommendation optimization method based on RPA technology according to an embodiment of the present application.

FIG. 3 shows an interface diagram of a first recommended get-on point.

FIG. 4 illustrates a selected interface schematic after a user first selects a recommended get-on point.

FIG. 5 illustrates an interface diagram for assigning confidence levels to different recommended pick-up points.

FIG. 6 illustrates an interface diagram for assigning confidence levels to different recommended pick-up points.

Fig. 7 shows a configuration diagram of an on-coming point recommendation optimizing system based on RPA technology according to an embodiment of the present application.

FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;

fig. 9 shows a schematic diagram of a storage medium according to an embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 shows a schematic diagram of the system architecture principle of the present application. In the embodiment of the application, a process automation robot is provided first, the current state of the process automation robot is identified, and then at least one boarding recommendation point is recommended to a user of the process automation robot; after receiving a reply to the get-on recommendation point from the user, judging whether the get-on recommendation point is accepted and approved by the user, and if so, adding the at least one get-on recommendation point into the flow automation robot; the robot continues to allocate confidence coefficient to each get-on recommendation point according to the number of the replied users, and then generates a recommended next get-on recommendation point according to the get-on recommendation points and the confidence coefficient level for the users to select.

Fig. 2 shows a flowchart of a get-on point recommendation optimization method based on RPA technology according to an embodiment of the present application. As shown in fig. 2, the method for optimizing the get-on point recommendation based on the RPA technology includes:

s1, identifying the current state of the process automation robot;

s2, recommending at least one boarding recommendation point to a user of the process automation robot by using a predictive learning model based on the current state, wherein the predictive learning model is trained based on actual selection of the boarding recommendation point by the user;

s3, receiving a reply to the get-on recommendation point from the user;

s4, when the reply is to accept the at least one get-on recommended point, adding the at least one get-on recommended point into the flow automation robot;

s5, distributing confidence coefficient for each get-on recommendation point based on the number of replied users;

s6, generating a recommended next batch of get-on recommendation points for selection according to the get-on recommendation points and the confidence level.

VNC (Virtual Network Console) is an abbreviation for virtual network console. The VNC is free open source software based on UNIX and Linux operating systems, and has strong remote control capability, high efficiency and practicability. In Linux, the VNC includes the following four commands: vncserver, vncnviewer, vnvcpasswd, and vncnconnect. In most cases the user only needs two of these commands: vncserver and vncnview.

VNC consists essentially of two parts: part is the client's application (vncovierer); the other part is a server-side application (vncserver). The server-side application program of the VNC has strong adaptability in UNIX and Linux operating systems, and the graphical user interface is very friendly. The computer of the Linux platform with the application program (vncnserver) installed on the client can be connected with the computer with the application program (vncnserver) installed on the server very conveniently. In addition, a Java Web interface is built in the server (vncserver), so that the operation of a user on other computers through the server can be displayed through Netscape, and the operation process and the display mode are visual and convenient. The present application employs VNC technology.

Specifically, in step S1, the specific implementation scheme for identifying the current state of the process automation robot includes:

responding to a running picture screenshot which is sent by any virtual network control platform (VNC) server and corresponds to the associated RPA robot at present, and determining that the associated RPA robot is in a running state at present; responding to a Natural Language Processing (NLP) result corresponding to the connection state of any RPA robot associated with a virtual network console server side to indicate disconnection, and determining that the RPA robot associated with any virtual network console server side is in an offline state; or,

In step S2, at least one boarding recommendation point is recommended to a user of the process automation robot using a predictive learning model based on the current state. Wherein the predictive learning model is an artificial intelligence model consisting of a filtering model, a deep learning model and a ranking model.

Recommending at least one get-on recommendation point to a user of the process automation robot using a predictive learning model, comprising:

As shown in fig. 3, the recommended boarding point A, B, C, D may also be further displayed to the user in the form of a GUI interface. Of course, a blank bar can be designed for the user to further input a new boarding point.

The predictive learning model is trained by:

storing a past get-on point selection list corresponding to the user;

According to various embodiments described herein, the present application utilizes predictive learning models (e.g., based on artificial intelligence implementations) to customize and personalize workflow design processes for users. While the user is developing the RPA workflow, the user-selected entry points are monitored in real-time (or substantially real-time) and one or more recommended entry points are identified as candidate entry points for consideration by the user as entry points in the next workflow entry point sequence. The identification and generation of recommended pick-up points is also performed in real-time (or substantially real-time) using predictive learning models.

The process is further personalized for the user as the predictive learning model is trained and retrained based on actual selections made by the user (e.g., based on whether the user selects from recommended pick-up points). The identification of recommended pick-up points may be based on a variety of considerations. For example, personalization may take into account user-specific patterns (e.g., user preferences, user style, etc.) from past pick-up point selections by the user. Customization may be achieved by intelligent-based filtering of the boarding points that are most relevant (e.g., most popular, most commonly used) to the workflow being designed, etc.

In accordance with one or more embodiments, the system may include a design environment with a user interface that allows a user to easily drag and drop recommended boarding points to facilitate building a workflow in an efficient and effective manner. For example, after a get-on point is placed into the workflow design window of the user interface, the get-on point suggestion tab on the user interface will automatically update to the next set of suggestions identified by the predictive learning model. Initially, the system may recommend pick-up points, such as the most common pick-up points, based on popularity filtering. Over time, predictive learning models utilize artificial intelligence functionality to train and adjust models to generate relevant suggestions that are more tailored to the user's style and preferences.

As will be apparent to those skilled in the art, the RPA user may use any type of design environment, including but not limited to a GUI-based environment or a text-based environment. Furthermore, in some implementations, users may record that they themselves or others are performing a process to be automated. In such implementations, the design of the RPA flow does not occur in any particular environment. Thus, the present application may be configured to present its recommendations in any form suitable for a given environment.

For example, in a GUI-based design environment, recommended flow operations may appear in a drop-down menu or displayed as drag-and-drop icons. On the other hand, in a text-based design environment, recommended flow operations may be displayed as "shadow text" that "completes" the semi-typing. (of course, text-based environments may also use drop-down menus, and vice versa, also depending on implementation.) As another example, recommended flow operations may be displayed as a "pop-up window" or notification on the designer's display device.

Furthermore, the present application may include a plurality of neural networks according to the implementation and the designed process.

For example, one neural network may be responsible for encoding the context information into a single digital representation, while another machine learning sub-module may use the representation to recommend operations according to the encoded context.

One example of a related neural network application is the use of well-known natural language processing techniques to identify language-based (communication-related) actions. Once trained, the present application will receive as input the encoding of the current state.

In step S3, receiving a reply to the get-on recommendation point from the user, as shown in fig. 4, to obtain a selected interface schematic diagram; the selected get on recommendation point A, C, D may be highlighted by highlighting in a different color. Of course, a blank bar can be designed for the user to further input a new boarding point.

According to another aspect, the present application tracks certain metrics associated with boarding points used by a user in building an RPA workflow. Such information may be useful in comparing the efficiency of the user's selection of recommended pick-up points, rather than predicting pick-up points not recommended by the learning model.

The user's index of replies to the get-on recommended points may include data or other information that may quantify or track parameters such as the number of mouse clicks, the amount of text the user enters to select a get-on point, the amount of time to complete the task of adding the corresponding get-on point, the completion of the workflow design containing all get-on points, and so forth. The index can also help the user to find the performance of the predictive learning model according to the data and the information. These examples are illustrative only and are not limiting in any way.

In step S4, when the reply is to accept the at least one get-on recommended point, adding the at least one get-on recommended point to the process automation robot; the method comprises the following two embodiments, wherein one of the two embodiments is realized.

The first embodiment is as follows:

at least one command in the command table is transmitted to an adapter of the process automation robot, the at least one command comprising a command to execute a process using a resource within an RPA platform.

For example, if the distance between two get-on recommended points is too close among the multiple get-on recommended points selected by the user, one of the get-on recommended points that is not already existing in the background is deleted, or the corresponding one of the historical data with a smaller number of users is deleted, so as to further optimize the get-on recommended points.

The second embodiment is as follows:

In step S5, a confidence is assigned to each get-on recommendation point based on the number of replied users.

The pick-up recommendation points may be different for different users, and thus, when the number of times that each pick-up recommendation point is selected by the user is counted last, the result is often different. How to measure the credibility of each get-on recommendation point is one of the technical problems to be solved by the application.

Specifically, step S5 may be implemented in one of the following two manners:

the first way is:

identifying a number of users selecting each pick-up recommendation point;

And determining the event confidence of the recommended event corresponding to each on-board recommended point based on the event attribute.

In the first way, according to the number of users clicked on each get-on recommendation point, the relation can be in direct proportion to the confidence level of the users, so that the confidence level of the users can be determined. For example, if one hundred users reply to each recommendation point, recommendation point a may set its confidence level to 90% if there are 90 user choices; if 80 users select the recommendation point C, the confidence level of the recommendation point C can be set to be 80%; if 70 users select the recommendation point D, the confidence level of the recommendation point D can be set to be 70%; and so on. This way is better understood.

For example, as shown in fig. 5, in one or more embodiments, the predictive learning model selected as in fig. 4 predicts 3 pick-up recommendation points A, C, D as candidate pick-up recommendation points, and may further add one (or more) other pick-up recommendation points E (not yet in the collection, predicted by the predictive learning model), each pick-up recommendation point being assigned a confidence level based on the number of replied users, the four pick-up recommendation points A, C, D, E having confidence levels of 90%, 80%, 70% and 85%, respectively.

The second way is:

In a second mode, after the confidence level of each recommended point is preliminarily determined by the number of replies from the user on the basis of the first mode, the user is notified of the initially calculated confidence level. The user may challenge or question the initial confidence level, such as clicking, entering, etc. Thereby giving the opportunity to revise the initial confidence level, and further ensuring the accuracy of the confidence level.

In step S6, a recommended next batch of boarding recommendation points is generated for selection according to the boarding recommendation points and the confidence level.

Assuming that the RPA has a selection criteria, the on-coming recommendation points with a confidence level below 85% will be eliminated. Thus, in evaluating the four get on recommendation points in FIG. 5, the RPA will remove/delete the get on recommendation point D, C with 70%, 80% confidence level from the collection, plus the user manually added get on point E.

For example, the predictive learning model may generate a suggested next batch of pick-up recommendation points for selection by the user, including four pick-up recommendation points from the collection with a confidence level of 70% or more, and an additional pick-up recommendation point, selected by the RPA based on the particular user's consideration being serviced.

This simplified example is illustrative only and is not limiting in any way.

The application embodiment provides an on-coming point recommendation optimization system based on the RPA technology, which is configured to execute the on-coming point recommendation optimization method based on the RPA technology described in the above embodiment, as shown in fig. 7, and the system includes:

a state identifying module 501, configured to identify a current state of the process automation robot;

a first recommendation module 502 that recommends at least one get on recommendation point to a user of the process automation robot based on the current state using a predictive learning model, wherein the predictive learning model is trained based on actual selection of get on recommendation points by the user;

a reply receiving module 503, configured to receive a reply to the get-on recommendation point from the user;

an add recommendation point module 504 that adds the at least one get-on recommendation point to the process automation robot when the reply is to accept the at least one get-on recommendation point;

The confidence module 505 allocates a confidence to each get-on recommendation point based on the number of replied users;

the second recommendation module 506 generates a recommended next batch of pick-up recommendation points for selection according to the pick-up recommendation points and the confidence level.

The get-on point recommendation optimization system based on the RPA technology provided by the above embodiment of the present application and the get-on point recommendation optimization method based on the RPA technology provided by the embodiment of the present application are the same inventive concept, and have the same beneficial effects as the method adopted, operated or implemented by the application program stored therein.

The embodiment of the application also provides the electronic equipment corresponding to the get-on point recommendation optimization method based on the RPA technology provided by the previous embodiment, so as to execute the get-on point recommendation optimization method based on the RPA technology. The embodiments of the present application are not limited.

Referring to fig. 8, a schematic diagram of an electronic device according to some embodiments of the present application is shown. As shown in fig. 8, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, the processor 200, the communication interface 203 and the memory 201 being connected by the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, the method for optimizing the get-on point recommendation based on the RPA technology provided in any of the foregoing embodiments of the present application is executed.

The memory 201 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 203 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.

Bus 202 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. The memory 201 is configured to store a program, and the processor 200 executes the program after receiving an execution instruction, and the method for optimizing the get-on point recommendation based on the RPA technology disclosed in any embodiment of the present application may be applied to the processor 200 or implemented by the processor 200.

The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 200 or by instructions in the form of software. The processor 200 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201, and in combination with its hardware, performs the steps of the above method.

The electronic equipment provided by the embodiment of the application and the loading point recommendation optimization method based on the RPA technology provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the electronic equipment based on the same inventive concept.

The present embodiment further provides a computer readable storage medium corresponding to the method for optimizing the get-on point recommendation based on the RPA technology provided in the foregoing embodiment, referring to fig. 9, the computer readable storage medium is shown as an optical disc 30, and a computer program (i.e. a program product) is stored thereon, where the computer program, when executed by a processor, performs the method for optimizing the get-on point recommendation based on the RPA technology provided in any of the foregoing embodiments.

It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.

The computer readable storage medium provided by the above embodiment of the present application and the method for optimizing the get-on point recommendation based on the RPA technology provided by the embodiment of the present application are the same inventive concept, and have the same beneficial effects as the method adopted, operated or implemented by the application program stored therein.

It should be noted that:

the algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and the above description of specific languages is provided for disclosure of preferred embodiments of the present application.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the application and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the present application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a virtual machine creation system according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application may also be embodied as a device or system program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of various changes or substitutions within the technical scope of the present application, and these should be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. The method for recommending and optimizing the get-on point based on the RPA technology is characterized by comprising the following steps of:

identifying the current state of the process automation robot;

receiving a reply to the get-on recommendation point from the user;

when the reply is to accept the at least one get-on recommendation point, adding the at least one get-on recommendation point to the process automation robot, comprising:

or,

generating an RPA workflow based on a matching result of a wizard component, wherein the RPA workflow adds the at least one boarding recommendation point to a combined frame or a list frame generated by the RPA workflow based on at least one field of a plurality of fields of the client resource management component;

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The current state of the automatic robot of the identification flow comprises:

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

the recommending at least one boarding recommendation point to a user of the process automation robot using a predictive learning model comprises:

4. The method of claim 3, wherein the step of,

the predictive learning model is trained by:

storing a past get-on point selection list corresponding to the user;

5. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the assigning a confidence level to each get-on recommendation point based on the number of the replied users comprises:

identifying a number of users selecting each pick-up recommendation point;

or,

6. The method of claim 5, wherein the step of determining the position of the probe is performed,

the generating a suggested next batch of get-on recommendation points for selection according to the get-on recommendation points and the confidence level comprises the following steps:

displaying an interface for adding a get-on recommendation point by a user;

acquiring a get-on recommendation point added by a user;

7. The utility model provides a get-on point recommendation optimizing system based on RPA technique which characterized in that includes:

the adding recommendation point module is used for adding the at least one get-on recommendation point to the flow automation robot when the reply is that the at least one get-on recommendation point is accepted, and comprises the following steps:

Or,

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor runs the computer program to implement the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of claims 1-6.