Conversational interaction method, device, equipment and storage medium combining RPA and AI

Abstract

The embodiments of the present application provide a conversation interaction method, device, equipment and storage medium combining RPA and AI. The method includes: receiving a conversation demand instruction input by a user; determining the corresponding user intent according to the conversation demand instruction; if it is determined that an RPA robot needs to be called according to the corresponding user intent, executing the call of the RPA robot and obtaining feedback data; outputting the conversation data based on the user intent and feedback data. Since the RPA robot corresponding to each user intent is predefined if relevant data needs to be obtained from the outside, and the RPA robot can be called to obtain feedback data corresponding to the user intent, it is possible to obtain matching feedback data through the corresponding RPA robot when facing complex business needs proposed by the user, and then push satisfactory answers to the user, thereby improving the user experience.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number "202010228225.8" filed by Beijing Benying Network Technology Co., Ltd. on March 27, 2020, with application name "Conversational Interaction Method, Device, Equipment and Storage Medium". Technical Field

[0003] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to a conversational interaction method, apparatus, device, and storage medium that combine RPA (Robotic Process Automation) and AI (Artificial Intelligence). Background Art

[0004] Robotic Process Automation (RPA) simulates human operations on computers through specific "robot software" and automatically executes 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 recent years, with the development of artificial intelligence, various conversational interactive robots have also developed rapidly. Users can meet their various work and life needs by interacting with conversational interactive robots.

[0005] Existing conversational interaction robots can only search for answers through the internal knowledge base to determine the questions and answers that meet the user's needs after the user sends a conversation request. Since the information stored in the internal knowledge base is limited, it can only meet the simple needs of users. When faced with complex business needs, it cannot push satisfactory answers to users, resulting in poor user experience. Summary of the invention

[0006] The embodiment of the present application provides a method, device, equipment and storage medium for dialogue interaction combining RPA and AI. The method solves the problem that the existing technology can only determine the questions and answers that meet the user's needs by searching the internal knowledge base for answers. Since the information stored in the internal knowledge base is limited, it can only meet the simple needs of the user. When facing complex business needs, satisfactory answers cannot be pushed to users, resulting in poor user experience.

[0007] In a first aspect, an embodiment of the present application provides a conversational interaction method combining RPA and AI, including:

[0008] Receiving a dialogue requirement instruction input by a user;

[0009] Determining a corresponding user intention according to the dialogue requirement instruction;

[0010] If it is determined that the RPA robot needs to be called according to the corresponding user intention, the RPA robot is called and feedback data is obtained;

[0011] Based on the user intention and the feedback data, dialogue data is output.

[0012] Furthermore, in the above method, the step of determining the corresponding user intention according to the dialogue requirement instruction includes:

[0013] Parsing the dialogue requirement instruction to obtain key words in the dialogue requirement instruction;

[0014] Matching the key words with at least one pre-stored user intention text;

[0015] The corresponding user intent is determined according to the user intent text that matches the key word.

[0016] Furthermore, in the above method, if it is determined that the RPA robot needs to be called according to the corresponding user intention, the calling of the RPA robot is executed to obtain feedback data, including:

[0017] According to the interaction strategy corresponding to the user intention, calling at least one processing node in the interaction strategy;

[0018] If the processing node includes an interface node, when the processing node runs to the interface node, the required parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The required parameters of the RPA robot are generated based on the interaction data of the node before the interface node.

[0019] Receive feedback data sent by the central control.

[0020] Furthermore, in the above method, the requirement parameters are generated in the following manner:

[0021] Running the processing nodes in the interaction strategy in sequence;

[0022] Fill the word slots based on the feedback information from each node user;

[0023] When running to the interface node, the requirement parameters of the RPA robot are generated based on the information in the preset word slot.

[0024] Furthermore, in the above method, outputting the dialogue data based on the user intention and the feedback data includes:

[0025] Receiving feedback data obtained after the central control executes the RPA call;

[0026] Generate text data based on the text generation rule corresponding to the user intention and in combination with the feedback data, and generate speech dialogue data by performing speech synthesis based on the text data;

[0027] The voice dialogue data is output.

[0028] Furthermore, in the above method, the text generation rule corresponding to the user intention is combined with the feedback data to generate text data, including:

[0029] Determine a plurality of text generation templates corresponding to the user intention;

[0030] Determine a feedback type of the feedback data, and determine a text generation template corresponding to the feedback type among the multiple text generation templates;

[0031] Generate text data based on a text generation template corresponding to the feedback type.

[0032] Furthermore, in the above method, the calling instruction of the RPA robot includes:

[0033] The calling authorization parameter of the current dialogue robot, wherein the calling authorization parameter is a unique identifier assigned to the dialogue robot by the central control.

[0034] In a second aspect, an embodiment of the present application provides a conversational interaction device combining RPA and AI, including:

[0035] An instruction receiving module, used for receiving a dialogue requirement instruction input by a user;

[0036] An intention determination module, used to determine the corresponding user intention according to the dialogue requirement instruction;

[0037] A data acquisition module, configured to execute the call of the RPA robot and obtain feedback data if it is determined that the RPA robot needs to be called according to the corresponding user intention;

[0038] A data output module is used to output dialogue data based on the user intention and the feedback data.

[0039] Further, in the above-mentioned device, the intention determination module is specifically used for:

[0040] The dialogue requirement instruction is parsed to obtain key words in the dialogue requirement instruction; the key words are matched with at least one pre-stored user intention text; and the corresponding user intention is determined according to the user intention text matching the key words.

[0041] Furthermore, in the above device, the data acquisition module is specifically used for:

[0042] According to the interaction strategy corresponding to the user intention, at least one processing node in the interaction strategy is called; if the processing node includes an interface node, when running to the interface node, the requirement parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface, and the requirement parameters of the RPA robot are generated based on the interaction data of the node before the interface node; and the feedback data sent by the central control is received.

[0043] Among them, the calling instruction of the RPA robot includes: the calling authorization parameter of the current dialogue robot, and the calling authorization parameter is the unique identifier assigned to the dialogue robot by the central control.

[0044] Furthermore, in the above-mentioned device, the demand parameters in the data acquisition module are generated in the following manner:

[0045] Run the processing nodes in the interaction strategy in sequence; fill the word slots according to the feedback information of the users of each node; when running to the interface node, generate the required parameters of the RPA robot based on the information in the preset word slots.

[0046] Furthermore, the data output module of the above device is specifically used for:

[0047] Receive feedback data obtained after the central control executes the RPA call; generate text data based on the text generation rule corresponding to the user intention and in combination with the feedback data, perform speech synthesis based on the text data to generate voice dialogue data; and output the voice dialogue data.

[0048] Furthermore, in the above-mentioned device, the data output module, when generating text data based on the text generation rule corresponding to the user intention in combination with the feedback data, is specifically used to:

[0049] Determine multiple text generation templates corresponding to the user intention; determine the feedback type of the feedback data, and determine a text generation template corresponding to the feedback type among the multiple text generation templates; and generate text data based on the text generation template corresponding to the feedback type.

[0050] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program;

[0051] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in any one of the first aspects.

[0052] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement a method as described in any one of the first aspects.

[0053] The embodiment of the present application provides a method, device, equipment and storage medium for dialogue interaction combining RPA and AI, by receiving dialogue requirement instructions input by the user; determining the corresponding user intention according to the dialogue requirement instructions; if it is determined that the RPA robot needs to be called according to the corresponding user intention, the call of the RPA robot is executed to obtain feedback data; based on the user intention and feedback data, the dialogue data is output. Since the RPA robot corresponding to each user intention is pre-defined if relevant data needs to be obtained from the outside, and the RPA robot can be called to obtain feedback data corresponding to the user intention, it is possible to obtain matching feedback data through the corresponding RPA robot when facing complex business requirements raised by the user, and then push satisfactory answers to the user, thereby improving the user experience.

[0054] It should be understood that the contents described in the above summary of the invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0056] Figure 1 An application scenario diagram of the conversational interaction method combining RPA and AI provided in an embodiment of the present application;

[0057] Figure 2 A flowchart of a conversational interaction method combining RPA and AI provided in Example 1 of the present application;

[0058] Figure 3 A flowchart of a conversational interaction method combining RPA and AI provided in Example 2 of the present application;

[0059] Figure 4 This is a flowchart of step 202 in the conversational interaction method combining RPA and AI provided in Embodiment 2 of the present application;

[0060] Figure 5 A flowchart of the step of generating demand parameters in the conversational interaction method combining RPA and AI provided in Example 2 of the present application;

[0061] Figure 6 This is a flowchart of step 206 in the conversational interaction method combining RPA and AI provided in Embodiment 2 of the present application;

[0062] Figure 7 This is a schematic diagram of the structure of a conversational interaction device combining RPA and AI provided in Example 3 of the present application;

[0063] Figure 8 It is a block diagram of an electronic device used to implement the conversational interaction method combining RPA and AI in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0065] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the implementation of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0066] First, the application scenario of the conversational interaction method combining RPA and AI provided in the embodiment of the present application is introduced. Figure 1As shown, the application scenarios provided in this embodiment include: a conversational robot and an RPA robot. Among them, the conversational robot is loaded on an electronic device, such as an electronic device with a voice interaction function with a user, such as a smart speaker, a smart phone, a tablet computer, or a hardware robot with a conversational function, etc. The conversational robot can be a conversational robot in a general field, or it can be a conversational robot in a specific application scenario, such as a train ticket inquiry robot, an air ticket inquiry robot, etc. After the conversational robot receives the conversational demand instruction input by the user, it determines the corresponding user intention according to the conversational demand instruction. If it is determined according to the corresponding user intention that the internal knowledge base does not store the corresponding feedback data, then the RPA robot to be called corresponding to the user intention is determined, the call of the RPA robot is executed, and the feedback data is obtained. After obtaining the feedback data, the conversational robot generates conversation data based on the user intention and the feedback data, and outputs the conversation data. As shown in Figure 1 In the example, the user's conversation demand instruction can be: "Please help me find the cheapest flight ticket from Beijing to Shanghai today". The conversation robot determines the RPA robot to be called corresponding to the user's intention, executes the call of the RPA robot, and then obtains the feedback data. The generated conversation data is "I found 20 flight information for you, and the cheapest one is 460 yuan." Since the RPA robot corresponding to each user intention is pre-defined when relevant data needs to be obtained from the outside, the RPA robot can be called to obtain the feedback data corresponding to the user's intention. Therefore, when facing complex business needs raised by users, matching feedback data can still be obtained through the corresponding RPA robot, and satisfactory answers can be pushed to users, improving user experience.

[0067] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0068] Embodiment 1

[0069] Figure 2 This is a flowchart of a conversational interaction method combining RPA and AI provided in Example 1 of the present application, such as Figure 2 As shown, the executor of this embodiment is a conversation interaction device combining RPA and AI, and the conversation interaction device combining RPA and AI can be located in an electronic device. The conversation interaction method combining RPA and AI provided in this embodiment includes the following steps.

[0070] Step 101: receiving a dialogue request instruction input by a user.

[0071] Specifically, in this embodiment, the electronic device has a sound receiving component, and the conversational robot can call the sound receiving component in the electronic device to obtain voice conversation demand instructions issued by the user, and can also receive text demand instructions input by the user from the interactive interface.

[0072] The conversation demand instruction is a conversation demand instruction in a specific field, such as the field of maternal and child care, the field of meal ordering, the field of ticket booking, etc., which is not limited in this embodiment. For example, the conversation demand instruction may be: "Please help me find the cheapest air ticket from Beijing to Shanghai today."

[0073] Step 102: determining the corresponding user intention according to the dialogue requirement instruction.

[0074] Among them, the user intention will vary according to the different dialogue demand instructions, which is related to the field and specific needs corresponding to the dialogue demand instructions.

[0075] As an optional implementation, in this embodiment, when the dialogue demand instruction is a voice instruction, the dialogue demand instruction can first be converted into a text demand instruction through voice recognition technology (abbreviated as: ASR technology), and then the text demand instruction is subjected to natural language processing to extract the corresponding user intention.

[0076] Or as another optional implementation, in this embodiment, after converting the dialogue demand instruction into a textual demand instruction, key words in the textual demand instruction are extracted, and the user intention is analyzed based on the key words.

[0077] It is understandable that, in this embodiment, the method of determining the corresponding user intention according to the dialogue requirement instruction may also be other methods, which are not limited in this embodiment.

[0078] Step 103: If it is determined that the RPA robot needs to be called according to the corresponding user intention, the RPA robot is called and feedback data is obtained.

[0079] Among them, the RPA robot is an automated process robot. Each RPA robot can execute automated processes in specific application fields, such as maternal and child care, meal ordering, ticket booking, etc. The RPA robot can be a hardware robot, an electronic device loaded with an RPA execution terminal, or other RPA robots that can execute RPA processes, and this application is not limited to this.

[0080] Among them, the RPA robot can be integrated into an electronic device, and the electronic device and the RPA robot can communicate through a bus. Or the RPA robot is set outside the electronic device, and the communication connection method between the electronic device and the RPA robot can be Global System of Mobile communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division-Synchronous Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE) system and future 5G, etc. It can be understood that the communication method between the electronic device and the visual sensor can also be a wireless communication method, and the wireless communication method can be Zigbee communication, Bluetooth BLE communication or mobile hotspot wifi communication, etc.

[0081] In this embodiment, the corresponding relationship between each user intention and the interaction strategy may be pre-stored, and the interaction strategy may include at least one processing node and an interaction flow. Depending on the user intention, the type of processing node and the interaction flow will also change accordingly.

[0082] In this embodiment, the correspondence between each pre-stored user intention and interaction strategy is used to implement the interaction between the electronic device and the user. For example, if the user intention is to pay attention to pregnancy, the processing nodes may include: an inquiry node, a branch word slot node, a meter reading node, and a message sending node. After determining the user intention, the interaction process may be: first, the inquiry node collects multiple key words, such as the collected key words include: "pregnancy" and "three weeks", and then the branch word slot node performs a logical branch judgment to determine that the demand is "precautions for three weeks of pregnancy", and then accesses the meter reading node, the meter reading node queries "precautions for three weeks of pregnancy" from the pre-stored knowledge base, and then sends the query result to the message sending node, and the message sending node sends "precautions for three weeks of pregnancy" to the user.

[0083] In the above exemplary description, feedback data is obtained by accessing information in the internal knowledge base. When facing complex business needs, it is necessary to access external data to obtain feedback data. In order to achieve access to external data, communication between the electronic device and the corresponding RPA robot is required.

[0084] As an optional implementation, in this embodiment, when pre-storing the correspondence between each user intent and the interaction strategy, it is possible to mark whether the RPA robot needs to be called and the identifier of the RPA robot to be called. After obtaining the user intent, if the interaction strategy corresponding to the user intent is marked with the need to call the RPA robot, the RPA robot to be called is determined according to the identifier of the RPA robot to be called, and then the RPA robot is called. Relevant data can be obtained through the RPA robot, and feedback data can be obtained.

[0085] As another optional implementation, in this embodiment, it is also possible to determine whether the RPA robot needs to be called by judging whether the processing node of the corresponding interaction strategy includes an interface node according to the user's intention. If the RPA robot needs to be called, the configuration information of the interface node is used to determine which RPA robot needs to be called. After determining the RPA robot to be called, the RPA robot is called. Relevant data can be obtained through the RPA robot, and feedback data can be obtained.

[0086] It is understandable that the method of determining whether to call the RPA robot according to the corresponding user intention may also be other methods, which are not limited in this embodiment.

[0087] Step 104: outputting the dialogue data based on the user's intention and the feedback data.

[0088] Specifically, in this embodiment, based on user intention and feedback data, conversation data in text form required by the user can be generated, and the conversation data can be converted from text form to voice form, and the conversation data can be played through a voice playback component to achieve the purpose of meeting user needs.

[0089] The conversation interaction method combining RPA and AI provided in this embodiment receives the conversation demand instruction input by the user; determines the corresponding user intent according to the conversation demand instruction; if it is determined that the RPA robot needs to be called according to the corresponding user intent, executes the call of the RPA robot and obtains feedback data; outputs the conversation data based on the user intent and feedback data. Since the RPA robot corresponding to each user intent is pre-defined when relevant data needs to be obtained from the outside, and the RPA robot can be called to obtain feedback data corresponding to the user intent, it is possible to obtain matching feedback data through the corresponding RPA robot when facing complex business needs raised by the user, and then push satisfactory answers to the user, thereby improving the user experience.

[0090] Embodiment 2

[0091] Figure 3 This is a flowchart of a conversational interaction method combining RPA and AI provided in Example 2 of the present application, such as Figure 3As shown, the conversation interaction method combining RPA and AI provided in this embodiment is a further refinement of steps 102 to 104 based on the first embodiment of the conversation interaction method combining RPA and AI in this application. The conversation interaction method combining RPA and AI provided in this embodiment includes the following steps.

[0092] Step 201: receiving a dialogue request instruction input by a user.

[0093] In this embodiment, the implementation method of step 201 is similar to the implementation method of step 101 in the first embodiment of the present application, and will not be repeated here.

[0094] Step 202: Determine the corresponding user intention according to the dialogue requirement instruction.

[0095] In one implementation, semantic understanding technology may be used to parse the dialogue demand instructions and determine the user's intention.

[0096] In another embodiment, if Figure 4 As shown, in this embodiment, step 202 includes the following steps:

[0097] Step 221, parsing the dialogue requirement instruction to obtain key words in the dialogue requirement instruction.

[0098] Specifically, in this embodiment, after first converting the dialogue demand instruction in voice form into demand instruction in text form, a keyword recognition algorithm may be used to recognize keywords in the demand instruction in text form to obtain key words.

[0099] The keyword recognition algorithm is not limited in this embodiment, and may be, for example, a frequent vocabulary dictionary for a specific field or a frequent vocabulary dictionary for a general field.

[0100] Step 2022, matching the key words with at least one pre-stored user intention text.

[0101] Specifically, the user intention text of each application field may be stored in the form of a list, and a preset matching algorithm may be used to match the key words with each user intention text in the user intention list to determine the user intention text matching the key words.

[0102] The type of the preset matching algorithm is not limited, and may be a complete matching algorithm, a fuzzy matching algorithm, etc.

[0103] Step 2023: Determine the corresponding user intent based on the user intent text that matches the key word.

[0104] Specifically, in this embodiment, the user intention text corresponding to the key words matched by the preset matching algorithm is determined as the user intention that matches the dialogue requirement instruction.

[0105] Step 203: Call at least one processing node in the interaction strategy according to the interaction strategy corresponding to the user intention.

[0106] In this embodiment, the correspondence between each user intention and the interaction strategy is pre-stored, and the interaction strategy may include at least one processing node and an interaction process. The communication relationship between each processing node is specified in the interaction process. Depending on the user intention, the category of processing nodes and the interaction process included in the interaction strategy are also different. If the RPA robot needs to be called, the processing node corresponding to the interaction strategy will include an interface node, and the configuration of the interface node can determine which RPA robot needs to be called.

[0107] Specifically, in this embodiment, a corresponding interaction strategy is first determined according to the user intention, and at least one processing node is called in sequence according to the interaction flow in the interaction strategy.

[0108] In this embodiment, an example is given of calling at least one processing node in the interaction strategy according to the interaction strategy corresponding to the user's intention: if the user's intention is to order the cheapest air ticket, the processing nodes included in the interaction strategy facing the intention of ordering the cheapest air ticket may include: an inquiry node, an interface node, and a message sending node. Among them, the inquiry node is to inquire about the key information of booking an air ticket and receive the key information of user feedback. The interface node is to connect the RPA robot to be called, and then execute the call of the RPA robot. The message sending node is used to send the conversation data after obtaining the final conversation data.

[0109] Step 204, if the processing node includes an interface node, when running to the interface node, the required parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The required parameters of the RPA robot are generated based on the interaction data of the node before the interface node.

[0110] Among them, the calling instruction of the RPA robot includes: the calling authorization parameter of the current dialogue robot, and the calling authorization parameter is the unique identifier assigned to the dialogue robot by the central control.

[0111] Specifically, in this embodiment, when the conversational robot calls the RPA robot, it needs to obtain the authorization of the RPA robot, so the calling instruction of the RPA robot includes the calling authorization parameters of the current conversational robot, so that the RPA robot can be called by the conversational robot according to the calling authorization parameters of the current conversational robot.

[0112] In this embodiment, if the processing node includes an interface node, it means that the RPA robot needs to be called. When calling the RPA robot, the required parameters of the RPA robot need to be determined, where the required parameters of the RPA robot are generated based on the interaction data of the node before the interface node.

[0113] As an optional implementation, Figure 5 As shown, the requirement parameters are generated in the following way:

[0114] Step 2041, running the processing nodes in the interaction strategy in sequence.

[0115] Step 2042, filling the word slots according to the feedback information of each node user.

[0116] The processing node in the running interactive strategy is the processing node before the interface node in the processing flow.

[0117] Specifically, in this embodiment, when the processing node before the interface node is run, if user feedback information is needed, key words are extracted according to the user feedback information, and the key words are used to fill the word slots.

[0118] Step 2043, when running to the interface node, the required parameters of the RPA robot are generated based on the information in the preset word slot.

[0119] Specifically, in this embodiment, after the processing node preceding the interface node is executed, when the interface node is executed, there are sufficient key words in the preset word slot, and the requirement parameters of the RPA robot are generated according to these key words. In one embodiment, the interface node stores the preset word slot information for generating the requirement parameters of the RPA robot. When the interface node is executed, the preset word slot information is determined, the data filled in the preset word slot is obtained, and the requirement parameters of the RPA robot are generated.

[0120] Based on the example in step 203, the exemplary description is continued: the node running before the interface node includes an inquiry node, which asks the user for the specific time of taking the flight, the departure airport, the departure place, and the destination. After receiving the user's feedback information, the key words in the word slot filled according to the user's feedback information obtained by the inquiry node may include: the name of the departure place, the name of the destination, the departure airport, the flight time, etc. Then, when the interface node is run, the generated demand parameter may be, for example, "depart from xx airport on x month x day from Beijing to Shanghai".

[0121] In this embodiment, after determining the requirement parameters of the RPA robot, the requirement parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The central control here can be the RPA robot control center. The central control can perform corresponding processing according to the requirement parameters of the RPA robot. The specific processing method may vary according to the type of the requirement parameters of the RPA robot. For example, if the requirement parameters of the RPA robot include time and place, the legitimacy of the time and place is verified. After the verification is passed, the requirement parameters of the RPA robot and the calling instructions of the RPA robot are sent to the RPA robot, and data related to the requirement parameters are obtained from the RPA robot.

[0122] Step 205, receiving feedback data sent by the central control.

[0123] Specifically, in this embodiment, after the central control obtains the data related to the demand parameters sent by the RPA robot, it parses and processes the related data to obtain feedback data. The electronic device receives the feedback data sent by the central control.

[0124] Step 206: outputting the dialogue data based on the user intention and the feedback data.

[0125] As an optional implementation, in this embodiment, if Figure 6 As shown, step 206 includes the following steps:

[0126] Step 2061, receiving feedback data obtained after the central control executes the RPA call.

[0127] Step 2062, based on the text generation rules corresponding to the user's intention, generate text data in combination with the feedback data, and perform speech synthesis based on the text data to generate speech dialogue data.

[0128] Optionally, the text generation rule may be a text generation template.

[0129] As an optional implementation, in this embodiment, generating text data based on the text generation rule corresponding to the user intention in step 2062 in combination with the feedback data includes the following steps:

[0130] Step 2062a, determining multiple text generation templates corresponding to the user's intention.

[0131] In this embodiment, the corresponding text generation template is pre-set according to the user's intention. For example, if the user's intention is to book a ticket, the text generation template corresponding to the ticket booking intention may be "Hello, I have booked a ticket for you ()", or "Hello, the ticket you ordered is out of stock".

[0132] It is understandable that the preset text generation template may be different for different user intentions.

[0133] Step 2062b, determining the feedback type of the feedback data, and determining a text generation template corresponding to the feedback type among multiple text generation templates.

[0134] In this embodiment, the feedback type of the feedback data can be different. For example, in the example of step 2062b, the feedback data of ticket booking can be a specific ticket type, or can also be a type for which no ticket is available. Then, according to the feedback type of the feedback data, a corresponding text generation template is determined.

[0135] For example, let's continue with the above exemplary description. If the feedback data is a specific ticket type, the corresponding text generation template is a template of "Hello, I have booked a ticket for you (). If the feedback data is a type for which there is no ticket, the corresponding text generation template is "Hello, the ticket you ordered is out of stock."

[0136] Step 2062c, generating text data based on a text generation template corresponding to the feedback type.

[0137] Specifically, in this embodiment, key information in the feedback data can be extracted, and if there is a word slot that needs to be filled in the text generation template, the key information is added to the word slot corresponding to the corresponding text generation template to generate text data. Alternatively, if there is no word slot that needs to be filled in the text generation template, the text generation template can be directly used as text data.

[0138] In this embodiment, after generating text data based on the text generation rule corresponding to the user's intention in combination with the feedback data, speech synthesis is performed based on the text data to generate speech dialogue data.

[0139] Specifically, as an optional implementation, in step 2062, performing speech synthesis based on text data to generate speech dialogue data includes the following steps:

[0140] Step 2062d, sending the text data to the speech synthesis tool through the asynchronous dialogue interface.

[0141] Step 2062e, converting the text data into speech dialogue data after speech synthesis through a speech synthesis tool.

[0142] Specifically, in this embodiment, the text data is sent to the speech synthesis tool through the asynchronous dialogue interface. The speech synthesis tool converts the text data into speech form through speech synthesis technology to form speech dialogue data, and the speech dialogue data is output from the speech synthesis tool.

[0143] Step 2063, output the voice conversation data.

[0144] In this embodiment, the electronic device plays the conversation data through the voice playing component to achieve the purpose of meeting the user's needs.

[0145] The conversational interaction method combining RPA and AI provided in this embodiment, if it is determined that the RPA robot needs to be called according to the corresponding user intention, the call of the RPA robot is executed, and when the feedback data is obtained, at least one processing node in the interaction strategy is called according to the interaction strategy corresponding to the user intention; if the processing node includes an interface node, then when it runs to the interface node, the demand parameters of the RPA robot and the call instructions of the RPA robot are sent to the central control through the interface, and the demand parameters of the RPA robot are generated based on the interaction data of the node before the interface node; receive the feedback data sent by the central control. Based on the text generation rules corresponding to the user intention, text data is generated in combination with the feedback data, and speech synthesis is performed based on the text data to generate speech conversation data; output the speech conversation data, so when facing the complex business needs proposed by the user, it is still possible to obtain the feedback data through the corresponding RPA robot, and obtain the feedback data that meets the user's needs through further processing, and then push a satisfactory answer to the user, which improves the user experience.

[0146] Embodiment 3

[0147] Figure 7 This is a structural diagram of a conversational interaction device combining RPA and AI provided in Example 3 of the present application, such as Figure 7 As shown, the conversation interaction device 70 combining RPA and AI provided in this embodiment includes: an instruction receiving module 71, an intention determination module 72, a data acquisition module 73 and a data output module 74.

[0148] The instruction receiving module 71 is used to receive the dialogue requirement instruction input by the user. The intention determination module 72 is used to determine the corresponding user intention according to the dialogue requirement instruction. The data acquisition module 73 is used to execute the call of the RPA robot and obtain feedback data if it is determined that the RPA robot needs to be called according to the corresponding user intention. The data output module 74 is used to output the dialogue data based on the user intention and the feedback data.

[0149] The conversational interaction device combining RPA and AI provided in this embodiment can perform Figure 2 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0150] Furthermore, the conversational interaction device 70 combining RPA and AI provided in this embodiment also includes the following technical solutions.

[0151] Optionally, the intention determination module 72 is specifically configured to:

[0152] The dialogue requirement instruction is parsed to obtain key words in the dialogue requirement instruction; the key words are matched with at least one pre-stored user intention text; and the corresponding user intention is determined according to the user intention text matched with the key words.

[0153] Optionally, the data acquisition module 73 is specifically used to:

[0154] According to the interaction strategy corresponding to the user's intention, at least one processing node in the interaction strategy is called; if the processing node includes an interface node, when it runs to the interface node, the requirement parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The requirement parameters of the RPA robot are generated based on the interaction data of the node before the interface node; and the feedback data sent by the central control is received.

[0155] Among them, the calling instruction of the RPA robot includes: the calling authorization parameter of the current dialogue robot, and the calling authorization parameter is the unique identifier assigned to the dialogue robot by the central control.

[0156] Optionally, the demand parameters in the data acquisition module 73 are generated in the following manner:

[0157] Run the processing nodes in the interaction strategy in sequence; fill the word slots according to the feedback information of the users at each node; when running to the interface node, generate the required parameters of the RPA robot based on the information in the preset word slots.

[0158] Optionally, the data output module 74 is specifically used to:

[0159] Receive feedback data obtained after the central control executes the RPA call; generate text data based on the text generation rules corresponding to the user's intention and the feedback data, perform speech synthesis based on the text data to generate voice dialogue data; and output the voice dialogue data.

[0160] Optionally, the data output module 74, when generating text data based on the text generation rule corresponding to the user intention and in combination with the feedback data, is specifically configured to:

[0161] Determine multiple text generation templates corresponding to user intentions; determine a feedback type of feedback data, and determine a text generation template corresponding to the feedback type among multiple text generation templates; and generate text data based on the text generation template corresponding to the feedback type.

[0162] The conversational interaction device combining RPA and AI provided in this embodiment can perform Figure 3-Figure 6 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0163] Embodiment 4

[0164] Figure 8 is a block diagram of an electronic device used to implement the conversational interaction method combining RPA and AI in an embodiment of the present application, such as Figure 8 As shown, the electronic device 800 provided in the fourth embodiment of the present application includes: a memory 801, a processor 802 and a computer program.

[0165] The computer program is stored in the memory 801 and is configured to be executed by the processor 802 to implement the conversational interaction method combining RPA and AI provided in the first or second embodiment.

[0166] For related instructions, please refer to Figures 1 to 6 The relevant descriptions and effects corresponding to the steps are understood, and no further elaboration is given here.

[0167] Electronic devices are intended to be various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0168] In this embodiment, the memory 801 and the processor 802 are connected via a bus.

[0169] Embodiment 5

[0170] Embodiment 5 of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the conversational interaction method combining RPA and AI provided in Embodiment 1 or Embodiment 2.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0172] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0174] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0175] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0177] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A conversational interaction method combining RPA and AI, characterized in that: include: Receiving a dialogue requirement instruction input by a user; Determining a corresponding user intention according to the dialogue requirement instruction; If it is determined that the RPA robot needs to be called according to the corresponding user intention, the RPA robot is called and feedback data is obtained; Outputting conversation data based on the user intention and the feedback data; If it is determined that the RPA robot needs to be called according to the corresponding user intention, the calling of the RPA robot is executed to obtain feedback data, including: According to the interaction strategy corresponding to the user intention, at least one processing node in the interaction strategy is called, wherein a correspondence between the user intention and the interaction strategy is pre-stored, the interaction strategy includes at least one processing node and an interaction process, and the communication relationship between each processing node is specified in the interaction process. Then, according to different user intentions, the categories of processing nodes and interaction processes included in the interaction strategy are also different. If the RPA robot needs to be called, the RPA robot to be called is determined in the configuration of the interface node in the processing node corresponding to the interaction strategy; If the processing node includes an interface node, when the processing node runs to the interface node, the required parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The required parameters of the RPA robot are generated based on the interaction data of the node before the interface node. Receive feedback data sent by the central control; The outputting the dialogue data based on the user intention and the feedback data includes: Receiving feedback data obtained after the central control executes the RPA call; Determine a plurality of text generation templates corresponding to the user intention; Determine a feedback type of the feedback data, and determine a text generation template corresponding to the feedback type among the multiple text generation templates; Generate text data based on a text generation template corresponding to the feedback type, wherein if there is a word slot to be filled in the text generation template, add key information to the word slot corresponding to the corresponding text template to generate the text data, and if there is no word slot to be filled in the text generation template, directly use the text template as the text data; Performing speech synthesis based on the text data to generate speech dialogue data; The voice dialogue data is output.

2. The method according to claim 1, characterized in that The determining the corresponding user intention according to the dialogue requirement instruction includes: Parsing the dialogue requirement instruction to obtain key words in the dialogue requirement instruction; Matching the key words with at least one pre-stored user intention text; The corresponding user intent is determined according to the user intent text that matches the key word.

3. The method according to claim 1, characterized in that The requirement parameters are generated in the following way: Running the processing nodes in the interaction strategy in sequence; Fill the word slots based on the feedback information from each node user; When running to the interface node, the requirement parameters of the RPA robot are generated based on the information in the preset word slot.

4. The method according to claim 1, characterized in that: The calling instruction of the RPA robot includes: The calling authorization parameter of the current dialogue robot, wherein the calling authorization parameter is a unique identifier assigned to the dialogue robot by the central control.

5. A conversational interaction device combining RPA and AI, characterized in that: include: An instruction receiving module, used for receiving a dialogue requirement instruction input by a user; An intention determination module, used to determine the corresponding user intention according to the dialogue requirement instruction; A data acquisition module, configured to execute the call of the RPA robot and obtain feedback data if it is determined that the RPA robot needs to be called according to the corresponding user intention; A data output module, configured to output conversation data based on the user intention and the feedback data; If it is determined that the RPA robot needs to be called according to the corresponding user intention, the calling of the RPA robot is executed to obtain feedback data, including: According to the interaction strategy corresponding to the user intention, at least one processing node in the interaction strategy is called, wherein a correspondence between the user intention and the interaction strategy is pre-stored, the interaction strategy includes at least one processing node and an interaction process, and the communication relationship between each processing node is specified in the interaction process. Then, according to different user intentions, the categories of processing nodes and interaction processes included in the interaction strategy are also different. If the RPA robot needs to be called, the RPA robot to be called is determined in the configuration of the interface node in the processing node corresponding to the interaction strategy; If the processing node includes an interface node, when the processing node runs to the interface node, the required parameters of the RPA robot and the calling instructions of the RPA robot are sent to the central control through the interface. The required parameters of the RPA robot are generated based on the interaction data of the node before the interface node. Receive feedback data sent by the central control; The outputting the dialogue data based on the user intention and the feedback data includes: Receiving feedback data obtained after the central control executes the RPA call; Determine a plurality of text generation templates corresponding to the user intention; Determine a feedback type of the feedback data, and determine a text generation template corresponding to the feedback type among the multiple text generation templates; Generate text data based on a text generation template corresponding to the feedback type, wherein if there is a word slot to be filled in the text generation template, add key information to the word slot corresponding to the corresponding text template to generate the text data, and if there is no word slot to be filled in the text generation template, directly use the text template as the text data; Performing speech synthesis based on the text data to generate speech dialogue data; The voice dialogue data is output.

6. An electronic device, characterized in that: include: Memory, processor and computer program; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

Images