WO2022160707A1 - Human-machine interaction method and apparatus combined with rpa and ai, and storage medium and electronic device - Google Patents

Abstract

A human-machine interaction method and apparatus combined with robotic process automation (RPA) and artificial intelligence (AI), and a storage medium and an electronic device, which are applied to natural language processing (NLP). The method comprises: acquiring service-related data and workflow data of an enterprise by using an RPA method (S101); processing the service-related data by using an AI platform, so as to obtain structured target service data corresponding to the service-related data (S102); according to the target service data and the workflow data and in combination with a pre-configured rule engine, generating a response processing logic corresponding to the enterprise (S103); and according to the response processing logic, controlling a digital employee execution apparatus to interact with a user (S104). By means of the method, the deployment and operation efficiency of a service platform combined with AI capability and RPA can be effectively improved, the application effect of the service platform can be effectively improved, the efficiency of interaction between a user and the service platform is improved, and the user experience is also improved.

Description

Human-computer interaction method, device, storage medium and electronic device combining RPA and AI

CROSS-REFERENCE TO RELATED APPLICATIONS

This disclosure requires Beijing Laiye Network Technology Co., Ltd. and Laiye Technology (Beijing) Co., Ltd. to submit to the Chinese Patent Office on January 29, 2021, the application number is 202110126884.5, and the name of the invention is "Human-computer interaction method combining RPA and AI, Apparatus, Storage Medium, and Electronic Equipment" of the Chinese Patent Application, the entire contents of which are incorporated by reference in this disclosure.

technical field

The present disclosure relates to the technical field of artificial intelligence, and in particular, to a human-computer interaction method, device, storage medium and electronic device combining RPA (Robotic Process Automation) and AI (Artificial Intelligence, artificial intelligence).

Background technique

Robotic Process Automation (RPA) for short is a specific "robot software" that simulates human operations on a computer and automatically performs process tasks according to rules.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

In related technologies, in the application of artificial intelligence AI capabilities and the realization of robotic process automation RPA, such as rule engines, big data processing, or process mining, the role points are small and scattered, and it is impossible to provide an integrated service platform for large-scale Therefore, it will affect the platform application effect of robotic process automation (RPA) using artificial intelligence (AI) capabilities, resulting in inefficient interaction between users and service platforms, and affecting user experience.

SUMMARY OF THE INVENTION

The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

Therefore, the purpose of the present disclosure is to propose a human-computer interaction method, device, storage medium and electronic device that combine RPA and AI, which can effectively improve the deployment and operation efficiency of a service platform combining artificial intelligence AI capabilities and robotic process automation RPA. , effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

In order to achieve the above-mentioned purpose, the human-computer interaction method combining RPA and AI proposed by the embodiment of the first aspect of the present disclosure is applied to natural language processing (Natural Language Processing, NLP), including: adopting the robotic process automation RPA method to obtain the business related information of the enterprise. data and workflow data; use the artificial intelligence AI platform to process the business-related data to obtain structured target business data corresponding to the business-related data; The configured rule engine generates response processing logic corresponding to the enterprise; and controls the digital employee execution device to interact with the user according to the response processing logic.

The human-computer interaction method combining RPA and AI proposed by the embodiment of the first aspect of the present disclosure obtains business-related data and workflow data of an enterprise by using the robotic process automation RPA method, and uses an artificial intelligence AI platform to process the business-related data to obtain The structured target business data corresponding to the business-related data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device and the user according to the response processing logic. Interaction, which can effectively improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA, effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the use of users. experience.

In order to achieve the above purpose, the human-computer interaction device combining RPA and AI proposed by the embodiment of the second aspect of the present disclosure is applied to natural language processing (Natural Language Processing, NLP), including: an acquisition module for adopting a robotic process automation RPA method Acquiring business-related data and workflow data of the enterprise; a processing module for processing the business-related data by using an artificial intelligence AI platform to obtain structured target business data corresponding to the business-related data; a generating module for According to the target business data and the workflow data, in combination with a preconfigured rule engine, a response processing logic corresponding to the enterprise is generated; and a control module is used to control the digital employee execution device to perform a communication with the user according to the response processing logic. interactive.

The human-computer interaction device combining RPA and AI proposed by the embodiment of the second aspect of the present disclosure obtains business-related data and workflow data of an enterprise by adopting the robotic process automation RPA method, and uses an artificial intelligence AI platform to process business-related data to obtain The structured target business data corresponding to the business-related data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device and the user according to the response processing logic. Interaction, which can effectively improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA, effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the use of users. experience.

In order to achieve the above purpose, the non-transitory computer-readable storage medium proposed by the embodiments of the third aspect of the present disclosure, when the instructions in the storage medium are executed by the processor of the electronic device, enables the electronic device to execute a combination of RPA A human-computer interaction method with AI, the method comprising: the human-computer interaction method combining RPA and AI proposed by the embodiments of the first aspect of the present disclosure.

The non-transitory computer-readable storage medium proposed by the embodiments of the third aspect of the present disclosure obtains business-related data and workflow data of an enterprise by adopting the robotic process automation (RPA) method, and uses an artificial intelligence AI platform to process the business-related data, so as to obtain business-related data and workflow data with an artificial intelligence (AI) platform. The structured target business data corresponding to the business-related data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device to interact with the user according to the response processing logic , which can effectively improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA, effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience. Spend.

A fourth aspect of the present disclosure further provides an electronic device, the electronic device includes a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is arranged inside a space enclosed by the housing, and the The processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to each circuit or device of the electronic device; the memory is used to store executable program codes; The executable program code stored in the memory is taken to run the program corresponding to the executable program code, so as to execute the human-computer interaction method combining RPA and AI proposed by the embodiment of the first aspect of the present disclosure.

The electronic device proposed by the embodiment of the fourth aspect of the present disclosure obtains the business-related data and workflow data of the enterprise by adopting the robotic process automation (RPA) method, and uses the artificial intelligence AI platform to process the business-related data, so as to obtain a structure corresponding to the business-related data According to the target business data and workflow data, combined with the pre-configured rule engine, the response processing logic corresponding to the enterprise is generated, and the digital employee execution device is controlled to interact with the user according to the response processing logic, so as to effectively improve Combining artificial intelligence AI capabilities and robotic process automation (RPA) service platform deployment and operation efficiency, it can effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

The computer program product provided by the embodiment of the fifth aspect of the present disclosure includes a computer program, and the computer program is executed by a processor to execute the human-computer interaction method combining RPA and AI provided by the embodiment of the first aspect of the present disclosure.

The computer program product proposed by the embodiment of the fifth aspect of the present disclosure obtains the business-related data and workflow data of the enterprise by adopting the Robotic Process Automation (RPA) method, and uses the artificial intelligence AI platform to process the business-related data, so as to obtain the business-related data corresponding to the business-related data. Structured target business data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device to interact with the user according to the response processing logic, so as to effectively Improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA, effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

Additional aspects and advantages of the present disclosure will be set forth, in part, from the following description, and in part will be apparent from the following description, or may be learned by practice of the present disclosure.

Description of drawings

The above and/or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

1 is a schematic flowchart of a human-computer interaction method combining RPA and AI proposed by an embodiment of the present disclosure;

FIG. 2 is a schematic structural diagram of a service platform in an embodiment of the present disclosure;

3 is a schematic flowchart of a human-computer interaction method combining RPA and AI proposed by another embodiment of the present disclosure;

4 is a schematic structural diagram of a human-computer interaction device combining RPA and AI proposed by an embodiment of the present disclosure;

5 is a schematic structural diagram of a human-computer interaction device combining RPA and AI proposed by another embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure and should not be construed as a limitation of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications and equivalents falling within the spirit and scope of the appended claims.

In order to solve related technologies, in the application of artificial intelligence AI capabilities and the realization of robotic process automation RPA, it is impossible to provide an integrated service platform for large-scale deployment and operation, thus affecting the use of artificial intelligence AI capabilities for robotic process automation RPA The application effect of the platform is not high, resulting in low interaction efficiency between users and the service platform, which affects the technical problem of user experience. Embodiments of the present disclosure provide a human-computer interaction method that combines RPA and AI. The RPA method obtains the business-related data and workflow data of the enterprise, and uses the artificial intelligence AI platform to process the business-related data to obtain structured target business data corresponding to the business-related data. The configured rule engine generates the response processing logic corresponding to the enterprise, and controls the digital employee execution device to interact with the user according to the response processing logic, which can effectively improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA. , effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

FIG. 1 is a schematic flowchart of a human-computer interaction method combining RPA and AI proposed by an embodiment of the present disclosure.

This embodiment is exemplified in that the human-computer interaction method combining RPA and AI is configured as a human-computer interaction device combining RPA and AI.

The human-computer interaction method combining RPA and AI in this embodiment can be configured in a human-computer interaction device combining RPA and AI, and the human-computer interaction device combining RPA and AI can be set in a server, or can also be set in an electronic device , the embodiments of the present disclosure do not limit this.

In this embodiment, the human-computer interaction method combining RPA and AI is configured in an electronic device as an example.

Among them, electronic devices such as smart phones, tablet computers, personal digital assistants, e-books and other hardware devices have various operating systems.

It should be noted that the executive body of the embodiments of the present disclosure may be, for example, a central processing unit (Central Processing Unit, CPU) in an electronic device in hardware, and may be, for example, natural language processing (natural language processing) in an electronic device in software processing, NLP) related services, which are not limited.

In addition, the "interaction" in the present disclosure refers to the interaction process combining RPA and artificial intelligence AI, that is to say, the interaction process is a full-process automation interaction process, and the interaction process is also related to artificial intelligence. The combination of AI realizes the automatic recognition of the user's interactive information (for example, the interactive semantics carried in the interactive text and/or interactive voice) using Natural Language Processing (NLP) methods, thereby assisting the improvement of AI combined with artificial intelligence. The capabilities and interactions between the RPA service platform and the user.

The present disclosure can be specifically applied to the natural language processing (NLP) scenario of artificial intelligence AI. ) domains of interaction between languages.

For example, in the present disclosure, based on the business-related data and workflow data of the enterprise to be deployed, it is possible to automatically generate the response processing logic corresponding to the enterprise according to the target business data and the workflow data in combination with the pre-configured rule engine. , and control the digital employee actuator to interact with the user according to the response processing logic.

As shown in Figure 1, the human-computer interaction method combining RPA and AI includes:

S101: Use the Robotic Process Automation (RPA) method to obtain business-related data and workflow data of the enterprise.

Among them, it can be an enterprise to which a service platform combining artificial intelligence AI capabilities and robotic process automation RPA is to be deployed and operated.

The business-related data may specifically be some unstructured data associated with the enterprise (for example, data such as pictures, voices, and videos generated during the business operation of the enterprise, which is not limited).

Among them, the workflow data may specifically refer to the data involved in the business workflow in the business operation process of the enterprise. For example, if the enterprise is a production and processing enterprise, the workflow may be, for example, the production process, product review process, product re-inspection process, etc. , the workflow data can be the data associated with the production process, the product review process, and the product re-inspection process, which are not limited.

In the specific implementation process of the embodiments of the present disclosure, in order to effectively ensure the comprehensiveness of the acquired data and improve the acquisition efficiency and accuracy of massive data, the robotic process automation RPA method can also be used to process the data from the big data associated with the enterprise. The business-related data is obtained from the platform, and the RPA method of robotic process automation is used to mine the enterprise's workflow data from the workflow processing platform associated with the enterprise.

That is to say, a communication link between the platform that realizes the RPA of robotic process automation and the big data platform can be established in advance. Then, when deploying the operation service platform, the robotic process automation (RPA) method can be used to obtain business-related data directly from the big data processing platform associated with the enterprise.

Optionally, when acquiring the workflow data of the enterprise, a communication link between the platform for realizing the robotic process automation RPA and the workflow processing platform may be established in advance, and the workflow processing platform may be specifically associated with the enterprise, and the work The stream processing platform can be used to store the massive workflow data associated with the enterprise, and then, when deploying the operation service platform, the robotic process automation (RPA) method can be used to directly mine the business from the workflow processing platform associated with the enterprise. related data.

As shown in FIG. 2, FIG. 2 is a schematic diagram of the architecture of the service platform in the embodiment of the disclosure, and FIG. 2 includes: a digital employee execution device 21, a big data platform 22, a workflow processing platform 23, a robot middle platform 24, the The robot middle station 24 can be regarded as a central processing unit that executes the RPA method of the robotic process automation and the artificial intelligence AI capability in the embodiment of the present disclosure. The various components and modules in FIG. 2 together constitute the combined artificial intelligence AI capability and the robotic process automation RPA. The service platform is the integrated service platform.

In the above-mentioned FIG. 2 , the robot middle station 24 can automatically collect business-related data of the enterprise from the big data platform 22 by using the robotic process automation RPA method, and perform multi-dimensional analysis and processing on the business-related data, and can also automatically The workflow data is mined from the workflow processing platform 23 by using the robotic process automation RPA method combined with the process mining technology.

For example, process mining technology, also known as workflow mining, is a technology that extracts useful information from workflow logs. Process mining technology can support service platforms to automatically discover business processes from enterprise process logs. Model, monitor and analyze changes in business processes.

The workflow processing platform 23 can be, for example, an enterprise resource planning (Enterprise Resource Planning, ERP) platform. For example, the robot middle platform 24 can mine the workflow log of the ERP system to obtain a workflow model, organize the model, and then analyze and locate the model. Business problems in workflow.

Optionally, in some embodiments, the business-related data is unstructured business data in a big data processing platform associated with the enterprise, and the workflow data includes at least: workflow model data and organizational structure data corresponding to the workflow , and the assignment data corresponding to the workflow.

That is to say, in the embodiment of the present disclosure, the business data obtained by the above-mentioned robot middle station 24 from the big data platform may be unstructured business data, and then the robot middle station 24 can also support corresponding processing of the obtained business data. It can effectively improve the format of business data and the adaptation performance of the integrated service platform, and effectively improve the access and use efficiency of business data in the service platform.

In this embodiment, because the above-mentioned workflow data includes at least: workflow model data, organizational structure data corresponding to the workflow, and allocation data corresponding to the workflow, the type dimension of the mined workflow data is expanded, and the data can be realized. The process mining technology and the robotic process automation RPA method are effectively combined to realize intelligent and automated process mining, thereby accelerating the deployment and operation of the robotic process automation RPA method, shortening the deployment and implementation time, and helping improve the overall business performance.

Among them, the above-mentioned workflow model data can be specifically, for example, the data related to some workflow models involved in the workflow of the enterprise, the workflow model, such as some standardized workflow business models, and the organizational structure data, such as the expansion of the enterprise. The data related to the departmental organization structure of the workflow, and the allocation data can be specific, for example, the allocation department corresponding to a process node in the workflow, the business data allocated to this department, and the work sub-process of this department, which corresponds to the department. personnel information and other data.

Therefore, in the embodiments of the present disclosure, the process mining technology and the big data processing platform are combined into the deployment, operation and maintenance of the integrated service platform, which can not only effectively help enterprises to improve operational efficiency and customer experience, but also effectively It can greatly reduce the task workload of the business personnel of the enterprise and the background operation and maintenance personnel of the service platform.

S102: Use an artificial intelligence AI platform to process business-related data to obtain structured target business data corresponding to the business-related data.

After using the robotic process automation (RPA) method to obtain the business-related data and workflow data of the enterprise mentioned above, the artificial intelligence AI platform can also be used to process the business-related data, so as to obtain structured target business data corresponding to the business-related data.

As shown in FIG. 2, FIG. 2 also includes an artificial intelligence AI platform 25. The artificial intelligence AI platform 25 can specifically integrate OCR (Optical Character Recognition, optical character recognition), ML (Machine Learning, machine learning), automatic speech recognition technology (Automatic Speech Recognition, ASR) module, natural language processing NLP module, text-to-speech (Text TSpeech, TTS) module, or any other possible functional modules can be integrated without limitation.

In the embodiment of the present disclosure, the AI processing capability of the artificial intelligence AI platform 25 can be automatically invoked by the robot middle platform 24, and the processing functions of the above-mentioned modules integrated with the AI processing capability can be used to process business-related data, so as to obtain business-related data. Corresponding structured target business data.

In the embodiment of the present disclosure, by integrating the artificial intelligence AI platform into the construction of the integrated service platform, the learning and use threshold of the artificial intelligence AI capability can be reduced to a large extent, and the application and promotion of the integrated service platform can be facilitated.

S103: Generate response processing logic corresponding to the enterprise in combination with the preconfigured rule engine according to the target business data and the workflow data.

After using the robotic process automation (RPA) method to obtain the business-related data and workflow data of the enterprise, and using the artificial intelligence AI platform to process the business-related data, to obtain the structured target business data corresponding to the business-related data, the target business data can be obtained according to the target business Data and workflow data, combined with a pre-configured rule engine, generate response processing logic corresponding to the enterprise.

The above-mentioned rule engine may be one or more of the following: a rule engine for recommending content to users; a rule engine for semantic analysis for users; and a rule engine for displaying content to users.

In the embodiment of the present disclosure, the above-mentioned response processing logic can be specifically written in the script file of the program code, and the response processing logic can be automatically read and called by the digital employee execution device, that is, the response processing logic can be assigned to Based on the search voice, matching content is recommended to the user.

S104: Control the digital employee execution device to interact with the user according to the response processing logic.

In combination with the above shown in FIG. 2 , one or more digital employee execution devices can be configured in the robot middle platform 24. The digital employee execution device can be a hardware component or a software virtual device. The digital employee executes the device. A device can be given the response processing logic described above to execute the response processing logic.

Different digital employee execution devices can be assigned different types of response processing logic, which can effectively assist the parallel execution of response processing logic and improve the response service efficiency of the integrated service platform.

It can be understood that the business requirements of an enterprise are usually constantly changing with the changing trend of the business environment. Therefore, in the embodiment of the present disclosure, the response processing logic of the digital employee execution device is automatically choreographed and implemented by a preconfigured rule engine. To serve enterprises and business personnel or system operation and maintenance personnel, it makes the design and implementation of response processing logic flexible to quickly adapt to changing business needs.

In other application scenarios, in order to effectively prevent the digital employee execution device from being unavailable to the user when it is in a maintenance state, an editing interface may be provided based on the above-mentioned rule engine, so as to assist in the implementation of the modification of rules other than the digital employee execution device to Adapt to business needs, and the rule method in the rule engine that generates the response processing logic is not actually compiled into the digital employee execution device, but is read and applied when the digital employee execution device is running. In this way, implementations can support modification of these rules without changing the code of the digital employee implement or stopping the digital employee implement in operation.

In other application scenarios, the robot middle platform of the embodiment of the present disclosure can support the business personnel of the enterprise to select the required type of rule engine to adapt to their own business requirements by integrating with multiple types of rule engines.

In this embodiment, the business-related data and workflow data of the enterprise are obtained by using the robotic process automation RPA method, and the business-related data is processed by the artificial intelligence AI platform, so as to obtain the structured target business data corresponding to the business-related data. Target business data and workflow data, combined with pre-configured rule engines, generate response processing logic corresponding to the enterprise, and control digital employee execution devices to interact with users according to the response processing logic, which can effectively improve the combination of artificial intelligence AI capabilities and robots The deployment and operation efficiency of the service platform of process automation RPA can effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

FIG. 3 is a schematic flowchart of a human-computer interaction method combining RPA and AI proposed by another embodiment of the present disclosure.

As shown in Figure 3, the human-computer interaction method combining RPA and AI includes:

S301: Use the Robotic Process Automation (RPA) method to obtain business-related data and workflow data of the enterprise.

S302: Use an artificial intelligence AI platform to process business-related data to obtain structured target business data corresponding to the business-related data.

For example descriptions of S301-S302, reference may be made to the foregoing embodiments, and details are not repeated here.

S303: Use the robotic process automation RPA method to process the target business data and workflow data to obtain corresponding business types, data formats, organizational structure information, allocation objects, and workflow processing procedures corresponding to the allocation objects.

Optionally, in some embodiments, the business-related data is unstructured business data in a big data processing platform associated with the enterprise, and the workflow data includes at least: workflow model data and organizational structure data corresponding to the workflow , and the assignment data corresponding to the workflow.

Among them, the above-mentioned workflow model data can be specifically, for example, the data related to some workflow models involved in the workflow of the enterprise, the workflow model, such as some standardized workflow business models, and the organizational structure data, such as the expansion of the enterprise. The data related to the departmental organization structure of the workflow, and the allocation data can be specific, for example, the allocation department corresponding to a process node in the workflow, the business data allocated to this department, and the work sub-process of this department, which corresponds to the department. personnel information and other data.

In this embodiment, the Robotic Process Automation (RPA) method can be used to process target business data and workflow data to obtain corresponding business types, data formats, organizational structure information, allocation objects, and workflow processing procedures corresponding to the allocation objects.

The business type can be used to indicate various businesses involved in the workflow data, such as production business, audit business, re-inspection business or other business, and the data format is the above-mentioned various business-related data and workflow The format corresponding to the data, the organizational structure information is the information related to the organizational structure of the above-mentioned middle department, the allocation objects such as the allocation department, allocation user, etc. corresponding to a process node in the workflow, and the workflow processing process corresponding to the allocation object, that is There is no restriction on the workflow processing sub-flow of the part corresponding to the assigned department or assigned user.

S304: Using the robotic process automation RPA method to parse out the business processing logic corresponding to the business type, data format, and organizational structure information from the preconfigured rule engine.

It should be noted that, the rule engine in the embodiment of the present disclosure may have some automated response processing logic generation methods pre-defined, so that the corresponding response processing logic generated based on the rule engine can be used to control the digital employee execution device Take the appropriate response action.

Based on the response processing logic generation method in the above rule engine, the business processing logic corresponding to the above-mentioned business type, data format, and organizational structure information can be automatically parsed.

For example, if the user inputs a search voice at one end, the business processing logic may be to recommend matching content to the user based on the search voice.

For example, if the user inputs a Chinese voice, the business processing logic may be to translate the Chinese voice into English.

The above are just examples. During the actual application of the integrated service platform, various types of business processing logic can be automatically split and analyzed according to the business process of the enterprise, such as the business processing logic of product manufacturing and the business processing of business operation. Logic, etc., there is no restriction on this.

In this embodiment, there may be various types of rule engines that can empower the middle platform of the robot. The rule engine provides a rule management function, and can modify, add, delete, and so on.

The rule engine in this embodiment can provide an editing and modification interface, so as to match with the defined rules according to the received feedback message of the terminal, and then judge whether adjustment is required, so that dynamic management of the rules can be achieved. Modify the decision-making strategy to make the strategy more flexible, and set the strategy more accurately according to the actual situation of the business; through flexible and practical strategy settings, the rules engine can be adjusted according to the current business situation for digital employees to perform automatic device arrangement and other adjustments Let users get a better business experience.

S305: Convert the workflow processing flow according to the business processing logic to obtain the target processing logic.

That is to say, according to the business process of the enterprise, the above can automatically split and analyze various types of business processing logic, which can be combined with the business processing logic to convert the workflow processing process of the enterprise into a digital employee that can be automatically invoked and executed. And output the processing logic of the response result, and use the processing logic as the target data logic.

S306: Mark the target processing logic with the identifier of the allocation object to obtain the response processing logic.

That is to say, according to the business process of the enterprise, the above can automatically split and analyze various types of business processing logic, which can be combined with the business processing logic to convert the workflow processing process of the enterprise into a digital employee that can be automatically invoked and executed. After outputting the processing logic of the response result, and using the processing logic as the target data logic, the target processing logic can also be marked with the identifier of the assigned object to obtain the response processing logic, so that the digital employee execution device executes the response processing logic. Avoid leakage of output response results and ensure the execution safety performance of digital employee execution devices.

For example, if the user inputs a search voice at one end, the business processing logic may be to recommend matching content to the user based on the search voice, then the above-mentioned generation method in the rule engine for content recommendation to the user may be used, and Based on the search voice, the business processing logic of searching, matching, displaying, and sorting the matching content recommended to the user is converted and integrated, so as to obtain the corresponding response processing logic, which may have the same or corresponding processing functions as the business processing logic. , that is, the response processing logic can be automatically executed to realize the above-mentioned business function of recommending matching content to the user based on the search voice.

For example, if the user inputs a Chinese voice at one end, the business processing logic may be to translate the Chinese voice into English, then the above-mentioned generation method in the rule engine for semantic analysis for the user can be used, and the The Chinese voice is translated and converted into English business processing logic such as semantic recognition, language matching, language translation, and result display, and then the business processing logic is converted and integrated to obtain the corresponding response processing logic. The response processing logic may be the same as or corresponding to the business processing logic. The processing function, that is, the response processing logic can be automatically executed to realize the above-mentioned business function of translating the Chinese speech into English.

In other application scenarios, if the response processing logic can be automatically executed to implement the above-mentioned business function of recommending matching content to users based on the search voice, the user's identity information can be pre-established on the integrated service platform On the basis of verification and matching, on the basis of indicating that the user has the authority to obtain the content matching function, the digital employee execution device is triggered to execute the response processing logic.

S307: Receive an interaction request input by the user, where the interaction request carries the user's identity identifier.

Wherein, the above interaction request may specifically be a user inputting a search voice at one end, or a user inputting a Chinese voice at one end, correspondingly, the interaction request may indicate that the user wishes to interact with the integrated service platform to obtain recommended content based on the search voice, or The interaction request may also indicate that the user wishes to interact with the integrated service platform to obtain English results obtained by translating the Chinese speech.

In the embodiment of the present disclosure, in order to ensure the security of the operation of the integrated service platform, the user's identity identifier carried in the interaction request can also be parsed, and the identity identifier can be used to uniquely identify the user's identity.

S308: Determine the allocation object identifier corresponding to the identity identifier.

For example, if the assignment object is such as the assignment department, assignment user, etc. corresponding to a certain process node in the workflow, if the identity identifier corresponds to the assignment object identifier, it can indicate that the user may belong to the assignment department in the business work. Or it indicates that the user may be the above-mentioned assigned user, so as to determine whether the user conforms to the business process of the enterprise based on the user's identity, and ensure the security performance of the business access of the integrated service platform.

That is to say, if there is a distribution object identifier corresponding to the identity identifier in the integrated service platform, it indicates that the user belongs to a corresponding distribution department in the business work, or is a distribution user.

S309: Determine a plurality of candidate digital employee execution devices according to the identity identifiers, and select a target digital employee execution device from the multiple candidate digital employee execution devices according to the assigned object identifier, and the response processing logic of the target digital employee execution device corresponds to The ID of the allocation object matches the allocation object ID.

After it is determined that the user belongs to a corresponding distribution department in the business work, or the user is assigned, that is, after the user's identity is verified and matched, a plurality of candidate digital employee execution devices can be determined according to the identity identification, and according to the distribution object. Identifying, selecting a target digital employee executive device from a plurality of candidate digital employee executive devices.

Optionally, in some embodiments, the digital employee execution device has a corresponding device label, determines a plurality of candidate digital employee execution devices according to the identity identifier, and also determines the authority information corresponding to the identity identifier; if the authority information is a public authority, Then multiple shared digital employee execution devices are called from the cloud server as multiple candidate digital employee execution devices, and the device label of the shared digital employee execution device is a label that matches the public authority; if the authority information is a private authority, Then, multiple private digital employee execution devices are invoked from the local terminal or local virtual machine of the service platform as multiple candidate digital employee execution devices, and the device tags of the private digital employee execution devices are tags matching the private authority.

For example, on the device label of the digital employee execution device of the robot center 24, deployment can be divided according to the characteristics of the business process involved in the response processing logic, such as the digital control logic corresponding to the common general business process. The employee execution device can be uniformly deployed on the cloud server and authorized to each user who needs it. After identity authentication, it can be supported to use the shared digital employee execution device. The private digital employee execution device is deployed in the local terminal of the service platform (for example, the user-side terminal of the integrated service platform can be used) or in the local virtual machine, and private authorization is performed to effectively prevent the digital employee execution device from being used by users who do not have authority. Use, or avoid unauthorized takeover by third-party platforms. Therefore, a corresponding device label is assigned to the digital employee execution device. The device label corresponds to matching private permissions or matching public permissions, which can effectively ensure the legal use of digital employees. and safety management.

S310: Use the target digital employee execution device to interact with the user based on the interaction request.

In the above solution, if the authority information is a public authority, multiple shared digital employee execution devices are called from the cloud server as multiple candidate digital employee execution devices. The terminal or the local virtual machine invokes a plurality of private digital employee execution devices, and serves as a plurality of candidate digital employee execution devices.

Then, the target digital employee execution device can be selected from the multiple candidate digital employee execution devices according to the assignment object identification (the assignment object identification, which corresponds to the user's identity identification), and the response processing logic of the target digital employee execution device The identification of the corresponding distribution object (the identification of the distribution object, which is marked when the response processing logic is generated above), is matched with the identification of the distribution object, so as to realize the rapid determination from multiple candidate digital employee execution devices A target digital employee execution device most suitable for the user's business usage needs is determined, so as to use the target digital employee execution device to interact with the user based on the interaction request.

In this embodiment, the business-related data and workflow data of the enterprise are obtained by using the robotic process automation RPA method, and the business-related data is processed by the artificial intelligence AI platform, so as to obtain the structured target business data corresponding to the business-related data. Target business data and workflow data, combined with pre-configured rule engines to generate response processing logic corresponding to the enterprise, and control digital employee execution devices to interact with users according to the response processing logic, which can effectively improve the combination of artificial intelligence AI capabilities and robots The deployment and operation efficiency of the service platform of process automation RPA can effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience. The above is to automatically split and analyze various types of business processing logic according to the business process of the enterprise. Combined with the business processing logic, the workflow processing process of the enterprise can be converted into a digital employee that can automatically call and execute, and output the response result. After the processing logic is used as the target data logic, the target processing logic can also be marked with the identifier of the assigned object to obtain the response processing logic, so that the digital employee execution device can avoid the leakage of the output response result when executing the response processing logic. , to ensure the execution safety performance of the digital employee execution device. A corresponding device label is assigned to the digital employee execution device, and the device label specifically corresponds to matching private permissions or matching public permissions, which can effectively ensure the legal use and security management of digital employees.

In this disclosure, the robot middle station can be deployed and operated on a large scale as an intermediate bridge connecting enterprise personnel and business, which can ensure the global circulation of business data in the business layer, and the digital employee execution device can store and restore the full amount of data in the robot middle station. It enables the data in the robot center to support the data business, accelerates the process of data businessization, and the feedback data generated by the data business can be returned to the robot center to continuously optimize the existing data services and make the data flow continuously in the business. Reduce the repeated download processing of data.

For example, both customer profiling and customer precision marketing require customer feature tags. The response processing logic created by the unified data service contains the data required by customer features, and then authorized to provide the two application departments, profiling and marketing, respectively. Created once, authorized multiple times and delivered to the front end. Compared with the previous chimney-type system requirements, repeated data download and processing can be avoided, and the timely and efficient data acquisition in the business can be ensured by combining small and large data. Through the unified digital employee execution device, different business departments can be provided to the middle platform of the robot. The middle-office management can carry out unified planning and allocation, ensure the coordination of resources and needs as a whole, and give full play to the short-term, smooth and fast creation of digital employees to implement device services to meet the data needs of all parties. The middle office, according to the special needs of the business or the planning direction of the enterprise development, continuously expands the third-party capabilities to provide more service value for enterprise business applications.

FIG. 4 is a schematic structural diagram of a human-computer interaction device combining RPA and AI proposed by an embodiment of the present disclosure.

As shown in FIG. 4 , the human-computer interaction device 40 combining RPA and AI includes:

The obtaining module 401 is configured to obtain business-related data and workflow data of the enterprise by adopting the Robotic Process Automation (RPA) method.

The processing module 402 is used for processing business-related data by using an artificial intelligence AI platform to obtain structured target business data corresponding to the business-related data.

The generating module 403 is configured to generate response processing logic corresponding to the enterprise in combination with the preconfigured rule engine according to the target business data and the workflow data.

The control module 404 is configured to control the digital employee execution device to interact with the user according to the response processing logic.

In some embodiments of the present disclosure, the obtaining module 401 is specifically used for:

Adopt the Robotic Process Automation (RPA) method to obtain business-related data from the big data processing platform associated with the enterprise;

Using the RPA method of robotic process automation, the workflow data of the enterprise is mined from the workflow processing platform associated with the enterprise.

In some embodiments of the present disclosure, the generating module 403 is specifically configured to:

Use the Robotic Process Automation (RPA) method to process the target business data and workflow data to obtain the corresponding business type, data format, organizational structure information, allocation objects, and workflow processing processes corresponding to the allocation objects;

Using the Robotic Process Automation (RPA) method, the business processing logic corresponding to the business type, data format, and organizational structure information is parsed from the pre-configured rule engine;

Transform the workflow processing flow according to the business processing logic to obtain the target processing logic;

The target processing logic is marked with the identifier of the assigned object to obtain the response processing logic.

In some embodiments of the present disclosure, as shown in FIG. 5 , which is a schematic structural diagram of a human-computer interaction device combining RPA and AI proposed by another embodiment of the present disclosure, the number of digital employee execution devices is one or more , the control module 404, including:

The receiving sub-module 4041 is used for receiving the interaction request input by the user, and the interaction request carries the identity of the user;

The first determination submodule 4042 is used to determine the assignment object identifier corresponding to the identity identifier;

The second determination sub-module 4043 is used to determine a plurality of candidate digital employee execution devices according to the identification, and select a target digital employee execution device from a plurality of candidate digital employee execution devices according to the assigned object identification, and the target digital employee execution device is selected. The identifier of the assignment object corresponding to the response processing logic of the execution device matches the assignment object identifier; and

The interaction sub-module 4044 is used for interacting with the user based on the interaction request using the target digital employee execution device.

In some embodiments of the present disclosure, the digital employee execution device has a corresponding device label, and the second determination sub-module 4043 is specifically used for:

Determine the permission information corresponding to the identity identifier;

If the permission information is a public permission, multiple shared digital employee execution devices are called from the cloud server as multiple candidate digital employee execution devices, and the device label of the shared digital employee execution device is a label that matches the public permission;

If the permission information is a private permission, multiple private digital employee execution devices are called from the local terminal or local virtual machine of the service platform, and used as multiple candidate digital employee execution devices, and the device label of the private digital employee execution device is Labels that match private permissions.

In some embodiments of the present disclosure, the business-related data is unstructured business data in a big data processing platform associated with the enterprise, and the workflow data includes at least: workflow model data and organizational structure data corresponding to the workflow , and the assignment data corresponding to the workflow.

In some embodiments of the present disclosure, the preconfigured rule engine includes at least one of the following:

A rules engine for recommending content to users;

A rules engine for semantic analysis to users;

A rules engine for displaying content to users.

It should be noted that the explanations of the embodiment of the human-computer interaction method combining RPA and AI in the above-mentioned embodiments of FIG. 1 to FIG. 3 are also applicable to the human-computer interaction device 40 combining RPA and AI of this embodiment, and its implementation principle similar, and will not be repeated here.

In this embodiment, the business-related data and workflow data of the enterprise are obtained by using the robotic process automation RPA method, and the business-related data is processed by the artificial intelligence AI platform, so as to obtain the structured target business data corresponding to the business-related data. Target business data and workflow data, combined with pre-configured rule engines, generate response processing logic corresponding to the enterprise, and control digital employee execution devices to interact with users according to the response processing logic, which can effectively improve the combination of artificial intelligence AI capabilities and robots The deployment and operation efficiency of the service platform of process automation RPA can effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

The electronic device may be a mobile phone, a tablet computer, or the like.

Referring to FIG. 6 , the electronic device 60 in this embodiment includes: a casing 601 , a processor 602 , a memory 603 , a circuit board 604 , and a power supply circuit 605 . The circuit board 604 is arranged inside the space enclosed by the casing 601 , the processor 602 , The memory 603 is provided on the circuit board 604; the power supply circuit 605 is used to supply power to each circuit or device of the electronic device 60; the memory 603 is used to store executable program codes; program code to run a program corresponding to the executable program code for executing:

Use the Robotic Process Automation (RPA) method to obtain business-related data and workflow data of the enterprise;

Use artificial intelligence AI platform to process business-related data to obtain structured target business data corresponding to business-related data;

According to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise; and

The digital employee actuator is controlled to interact with the user according to the response processing logic.

It should be noted that the explanations of the embodiment of the human-computer interaction method combining RPA and AI in the above-mentioned embodiments of FIG. 1 to FIG. 3 are also applicable to the electronic device 60 of this embodiment, and the implementation principle thereof is similar, which will not be repeated here. .

The electronic device in this embodiment obtains the business-related data and workflow data of the enterprise by adopting the RPA method of robotic process automation, and uses the artificial intelligence AI platform to process the business-related data, so as to obtain a structured target business corresponding to the business-related data Data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device to interact with the user according to the response processing logic, which can effectively improve the combination of artificial intelligence AI. The deployment and operation efficiency of the service platform of RPA can effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

In order to realize the above embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the terminal, the terminal can execute a human-computer interaction method combining RPA and AI , methods include:

Use the Robotic Process Automation (RPA) method to obtain business-related data and workflow data of the enterprise;

Use artificial intelligence AI platform to process business-related data to obtain structured target business data corresponding to business-related data;

According to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise; and

The digital employee actuator is controlled to interact with the user according to the response processing logic.

In the non-transitory computer-readable storage medium in this embodiment, the business-related data and workflow data of the enterprise are obtained by adopting the robotic process automation (RPA) method, and the business-related data is processed by the artificial intelligence AI platform, so as to obtain corresponding business-related data The structured target business data, according to the target business data and workflow data, combined with the pre-configured rule engine to generate the response processing logic corresponding to the enterprise, and control the digital employee execution device to interact with the user according to the response processing logic, so as to effectively It can effectively improve the deployment and operation efficiency of the service platform combining artificial intelligence AI capabilities and robotic process automation RPA, effectively improve the application effect of the service platform, improve the interaction efficiency between users and the service platform, and improve the user experience.

In order to realize the above-mentioned embodiments, the present disclosure also proposes a computer program product, when the instructions in the computer program product are executed by the processor, a human-computer interaction method combining RPA and AI is executed.

It should be noted that, in the description of the present disclosure, the terms "first", "second", etc. are only used for description purposes, and cannot be understood as indicating or implying relative importance. Also, in the description of the present disclosure, unless stated otherwise, "plurality" means two or more.

Any description of a process or method in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing a specified logical function or step of the process , and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present disclosure pertain.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those skilled in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

In some embodiments of the present disclosure, there is also provided a computer program product, including a computer program that, when executed by a processor, implements the aforementioned human-computer interaction method combining RPA and AI.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structures, materials, or features are included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present disclosure. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (17)

1. A human-computer interaction method combining RPA and AI, characterized in that, applied to natural language processing (Natural Language Processing, NLP), the method comprising:

   Use the Robotic Process Automation (RPA) method to obtain business-related data and workflow data of the enterprise;

   Use the artificial intelligence AI platform to process the business-related data to obtain structured target business data corresponding to the business-related data;

   Generate response processing logic corresponding to the enterprise according to the target business data and the workflow data in combination with a preconfigured rule engine; and

   The digital worker execution device is controlled to interact with the user according to the response processing logic.
2. The method according to claim 1, characterized in that, the acquisition of business-related data and workflow data of the enterprise by using a robotic process automation (RPA) method, comprising:

   Using the Robotic Process Automation (RPA) method, obtain the business-related data from the big data processing platform associated with the enterprise;

   Using the Robotic Process Automation (RPA) method, the workflow data of the enterprise is mined from the workflow processing platform associated with the enterprise.
3. The method according to any one of claims 1-2, wherein the response processing logic corresponding to the enterprise is generated according to the target business data and the workflow data in combination with a preconfigured rule engine, include:

   The target business data and the workflow data are processed by using the Robotic Process Automation (RPA) method to obtain corresponding business types, data formats, organizational structure information, allocation objects, and workflow processing procedures corresponding to the allocation objects;

   Using the Robotic Process Automation (RPA) method to parse out the business processing logic corresponding to the business type, data format, and organizational structure information from the preconfigured rule engine;

   Performing conversion processing on the workflow processing flow according to the business processing logic to obtain target processing logic;

   The target processing logic is marked with the identifier of the allocation object to obtain the response processing logic.
4. The method of claim 3, wherein the number of the digital employee execution devices is one or more, and the controlling the digital employee execution device to interact with the user according to the response processing logic comprises:

   receiving an interaction request input by the user, where the interaction request carries the identity of the user;

   Determine the allocation object identifier corresponding to the identity identifier;

   Determine a plurality of candidate digital employee execution devices according to the identification, and select a target digital employee execution device from the plurality of candidate digital employee execution devices according to the assignment object identification, and the target digital employee executes The identifier of the assignment object corresponding to the response processing logic of the device is matched with the assignment object identifier; and

   Interacting with the user based on the interaction request is performed using the target digital employee execution device.
5. The method of claim 4, wherein the digital employee execution device has a corresponding device label, and the determining a plurality of candidate digital employee execution devices according to the identity identifier further comprises:

   determine the authority information corresponding to the identity identifier;

   If the permission information is a public permission, multiple shared digital employee execution devices are called from the cloud server as the multiple candidate digital employee execution devices, and the device tags of the shared digital employee execution devices are the same as the label matched by the public authority;

   If the permission information is a private permission, call a plurality of private digital employee execution devices from the local terminal or local virtual machine of the service platform, and serve as the plurality of candidate digital employee execution devices, the private digital employee The device tag of the executing device is the tag that matches the private authority.
6. The method according to any one of claims 1-5, wherein the business-related data is unstructured business data in a big data processing platform associated with the enterprise, and the workflow data At least it includes: workflow model data, organizational structure data corresponding to the workflow, and allocation data corresponding to the workflow.
7. The method of claim 1 or 3, wherein the preconfigured rule engine includes at least one of the following:

   a rule engine for recommending content to the user;

   a rules engine for semantic analysis of the user;

   A rules engine for presenting content to the user.
8. A human-computer interaction device combining RPA and AI, characterized in that, applied to natural language processing (Natural Language Processing, NLP), the device comprising:

   The acquisition module is used to acquire the business-related data and workflow data of the enterprise by adopting the RPA method of robotic process automation;

   a processing module for processing the business-related data by using an artificial intelligence AI platform to obtain structured target business data corresponding to the business-related data;

   a generating module, configured to generate response processing logic corresponding to the enterprise according to the target business data and the workflow data in combination with a preconfigured rule engine; and

   The control module is used for controlling the digital employee execution device to interact with the user according to the response processing logic.
9. The device according to any one of claims 8-9, wherein the acquisition module is specifically used for:

   Using the Robotic Process Automation (RPA) method, obtain the business-related data from the big data processing platform associated with the enterprise;

   Using the Robotic Process Automation (RPA) method, the workflow data of the enterprise is mined from the workflow processing platform associated with the enterprise.
10. The apparatus according to claim 8, wherein the generating module is specifically used for:

    The target business data and the workflow data are processed by using the Robotic Process Automation (RPA) method to obtain corresponding business types, data formats, organizational structure information, allocation objects, and workflow processing procedures corresponding to the allocation objects;

    Using the Robotic Process Automation (RPA) method to parse out the business processing logic corresponding to the business type, data format, and organizational structure information from the preconfigured rule engine;

    Performing conversion processing on the workflow processing flow according to the business processing logic to obtain target processing logic;

    The target processing logic is marked with the identifier of the allocation object to obtain the response processing logic.
11. The device of claim 10, wherein the number of the digital employee execution devices is one or more, and the control module comprises:

    a receiving submodule, configured to receive an interaction request input by the user, where the interaction request carries the user's identity;

    a first determination submodule, used to determine the assignment object identifier corresponding to the identity identifier;

    The second determination sub-module is configured to determine a plurality of candidate digital employee execution devices according to the identity identifier, and select a target digital employee execution device from the plurality of candidate digital employee execution devices according to the assignment object identifier. a device, the identification of the distribution object corresponding to the response processing logic of the target digital employee execution device is matched with the identification of the distribution object; and

    An interaction sub-module for using the target digital employee execution device to interact with the user based on the interaction request.
12. The device according to claim 11, wherein the digital employee execution device has a corresponding device label, and the second determination submodule is specifically used for:

    determine the authority information corresponding to the identity identifier;

    If the permission information is a public permission, multiple shared digital employee execution devices are called from the cloud server as the multiple candidate digital employee execution devices, and the device tags of the shared digital employee execution devices are the same as the label matched by the public authority;

    If the permission information is a private permission, call a plurality of private digital employee execution devices from the local terminal or local virtual machine of the service platform, and serve as the plurality of candidate digital employee execution devices, the private digital employee The device tag of the executing device is the tag that matches the private authority.
13. The apparatus according to any one of claims 8-12, wherein the business-related data is unstructured business data in a big data processing platform associated with the enterprise, and the workflow data At least it includes: workflow model data, organizational structure data corresponding to the workflow, and allocation data corresponding to the workflow.
14. The apparatus according to claim 8 or 10, wherein the preconfigured rule engine includes at least one of the following:

    a rule engine for recommending content to the user;

    a rules engine for semantic analysis of the user;

    A rules engine for presenting content to the user.
15. A non-transitory computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the human-machine combining RPA and AI according to any one of claims 1-7 is realized interactive method.
16. An electronic device includes a casing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is arranged inside the space enclosed by the casing, and the processor and the memory are arranged in the circuit board; the power supply circuit is used to supply power to each circuit or device of the electronic device; the memory is used to store executable program codes; the processor reads the executable program stored in the memory by reading code to run a program corresponding to the executable program code, so as to execute the human-computer interaction method combining RPA and AI according to any one of claims 1-7.
17. A computer program product, comprising a computer program, characterized in that, when the computer program is executed by a processor, the human-computer interaction method combining RPA and AI according to any one of claims 1-7 is implemented.

Images