Service processing method and device based on intelligent agent

Abstract

The embodiment of the invention provides an agent-based service processing method and device, and the method comprises the steps: receiving interaction information which is submitted by a user terminal after an agent interface configured by a travel service is triggered in the operation process of the travel service, intelligent agent calling of the travel service is carried out based on the interaction information, and a target sub-intelligent agent corresponding to the interaction information is determined in a plurality of configured sub-intelligent agents through the intelligent agent; the question and answer sub-agents and the sub-agents matched with the interaction information are used for service cooperative processing to obtain a service result, service response data are generated according to the service result and issued to the user terminal, and therefore the service response data are generated in the process that the user uses the travel service in an agent cooperative processing mode so that the user can check the service response data.

Description

Technical Field

[0001] This document relates to the field of data processing technologies, and in particular, to an agent-based service processing method and apparatus. Background Art

[0002] With the continuous development and popularization of the Internet, more and more services are provided online. Users can conveniently use a variety of services online. As the number of users increases, more and more online services are emerging. Artificial intelligence technology has gradually been introduced into online services. As users continue to use these services, their requirements for various aspects of online services are also constantly increasing. Users' requirements for the response speed, intelligence, and convenience of online services are all increasing. How to provide better online services has become the main concern of all parties. Summary of the Invention

[0003] One or more embodiments of this specification provide an agent-based service processing method, including: receiving interaction information submitted by a user terminal after an agent interface configured for a cultural and tourism service is triggered. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Invoking an agent for the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information from among a plurality of configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Service response data is generated based on the service result and sent to the user terminal.

[0004] One or more embodiments of this specification provide another agent-based service processing method, including: obtaining interaction information submitted by a user after triggering an agent interface configured for a cultural and tourism service. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Sending the interaction information to a server so that the server invokes an agent for the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information from among a plurality of configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Receiving service response data generated and sent by the server according to the service result and displaying it on a cultural and tourism service page.

[0005] One or more embodiments of this specification provide an agent-based service processing device, including: an interaction information receiving module, configured to receive interaction information submitted by a user terminal after an agent interface configured for a cultural and tourism service is triggered. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. An agent invocation module, configured to perform agent invocation of the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among a plurality of configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. A service response data sending module, configured to generate service response data according to the service result and send it to the user terminal.

[0006] One or more embodiments of this specification provide another agent-based service processing device, including: an interaction information obtaining module, configured to obtain interaction information submitted after a user triggers an agent interface configured for a cultural and tourism service. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. An interaction information sending module, configured to send the interaction information to a server so that the server performs agent invocation of the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among a plurality of configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. A service response data display module, configured to receive service response data generated and sent by the server according to the service result and display it on a cultural and tourism service page.

[0007] One or more embodiments of this specification provide an agent-based service processing device, including: a processor; and a memory configured to store computer-executable instructions, the computer-executable instructions, when executed, cause the processor to: receive interaction information submitted by a user terminal after an agent interface configured for a cultural and tourism service is triggered. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Perform agent invocation of the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among a plurality of configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Generate service response data according to the service result and send it to the user terminal.

[0008] One or more embodiments of this specification provide another agent-based service processing device, including: a processor; and a memory configured to store computer-executable instructions, which when executed cause the processor to: obtain interaction information submitted after a user triggers an agent interface for cultural and tourism service configuration. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Send the interaction information to a server so that the server performs agent invocation for the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, perform service collaborative processing with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Receive service response data generated and sent by the server according to the service result, and display it on the cultural and tourism service page.

[0009] One or more embodiments of this specification provide a computer-readable storage medium for storing computer-executable instructions, which when executed implement the following process: receive interaction information submitted by a user terminal after an agent interface for cultural and tourism service configuration is triggered. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Perform agent invocation for the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, perform service collaborative processing with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Generate service response data according to the service result and send it to the user terminal.

[0010] One or more embodiments of this specification provide another computer-readable storage medium for storing computer-executable instructions, which when executed implement the following process: obtain interaction information submitted after a user triggers an agent interface for cultural and tourism service configuration. The cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. Send the interaction information to a server so that the server performs agent invocation for the cultural and tourism service based on the interaction information. The agent determines a target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, perform service collaborative processing with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. Receive service response data generated and sent by the server according to the service result, and display it on the cultural and tourism service page. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings; Figure 1 Schematic diagram of an implementation environment of an agent-based service processing method provided for one or more embodiments of this specification; Figure 2 Processing flowchart of an agent-based service processing method provided for one or more embodiments of this specification; Figure 3 Processing flowchart of an agent-based service processing method applied to a first interaction scenario provided for one or more embodiments of this specification; Figure 4 Processing flowchart of an agent-based service processing method applied to a second interaction scenario provided for one or more embodiments of this specification; Figure 5 Another processing flowchart of an agent-based service processing method provided for one or more embodiments of this specification; Figure 6 Schematic diagram of an embodiment of an agent-based service processing device provided for one or more embodiments of this specification; Figure 7 Another schematic diagram of an embodiment of an agent-based service processing device provided for one or more embodiments of this specification; Figure 8 Schematic diagram of the structure of an agent-based service processing device provided for one or more embodiments of this specification; Figure 9 Another schematic diagram of the structure of an agent-based service processing device provided for one or more embodiments of this specification. Detailed implementation

[0012] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only some embodiments of this specification, rather than all embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0013] The agent-based service processing method provided by one or more embodiments of this specification is applicable to the implementation environment of cultural and tourism service operation. Refer to Figure 1 , this implementation environment at least includes: The user's user terminal 101, the server 102 of the cultural and tourism service, and the agent 103 of the cultural and tourism service; Among them, the user's user terminal 101 is used to access the cultural and tourism service, send interaction information to the server 102, and receive the service response data sent by the server 102. It can also display the service response data. Further, a client of the cultural and tourism service can be installed in the user terminal 101. The client can be an application program, or a subroutine of an application program, or a service module of an application program. The user's user terminal 101 can specifically be a mobile phone, a personal computer, a tablet computer, an e-book reader, a device for information interaction based on VR (Virtual Reality), a vehicle-mounted terminal, an IoT device, a wearable intelligent device, a laptop computer, a desktop computer, and so on; The server 102 of the cultural and tourism service is used to receive the interaction information sent by the user terminal 101, call the agent 103 based on the interaction information, generate service response data according to the service result generated by the agent 103, and send it to the user terminal 101. Specifically, the payment server 102 can be a single server, or a server cluster composed of several servers, or one or more cloud servers in a cloud computing platform.

[0014] The agent 103 of the cultural and tourism service is used to determine the target sub-agent corresponding to the interaction information among multiple configured sub-agents according to the interaction information. If it is determined to be a question-and-answer sub-agent, the service result is obtained through service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information; the agent 103 can be independently deployed, and the server 102 interacts with the agent 103 in the way of agent call. The agent 103 can be deployed in a single server, or in a server cluster composed of several servers, or in one or more cloud servers in a cloud computing platform. In addition, the agent 103 can also be deployed inside the server 102.

[0015] In this implementation environment, after the user terminal 101 submits interaction information by triggering the intelligent agent interface for cultural and tourism service configuration, it sends the interaction information to the server 102. The server 102 invokes the intelligent agent 103 of the cultural and tourism service based on the received interaction information. The intelligent agent 103 determines the target sub-intelligent agent corresponding to the interaction information among the configured multiple sub-intelligent agents in response to the invocation. If it is a question-and-answer sub-intelligent agent, it performs service collaborative processing with the sub-intelligent agent adapted to the interaction information through the question-and-answer sub-intelligent agent to obtain a service result. The server 102 generates service response data based on the service result generated by the intelligent agent 103 and sends it to the user terminal 101. The user terminal 101 displays the received service response data, so as to obtain service response data and display it to the user in the process of the user using the cultural and tourism service through the multi-intelligent agent collaboration method.

[0016] One or more embodiments of a service processing method based on an intelligent agent provided in this specification are as follows: Refer to Figure 2 , the service processing method based on an intelligent agent provided in this embodiment, the method specifically includes steps S202 to S206.

[0017] Step S202, receive the interaction information submitted by the user terminal after the intelligent agent interface for cultural and tourism service configuration is triggered.

[0018] The cultural and tourism service described in this embodiment can be a service related to cultural and tourism, such as a cultural and tourism service related to a target area (city). The cultural and tourism service can be provided through an application program and / or a subroutine of the application program. The cultural and tourism service can also be a cultural and tourism application, or a cultural and tourism subroutine of the application program. Among them, the cultural and tourism service can provide multiple different functions, and the user can use these functions in the cultural and tourism service.

[0019] For example, the user can ask questions about cultural and tourism reference information within the cultural and tourism service, and the user can also ask questions about travel suggestions within the cultural and tourism service; or, the user can also purchase tickets, query tickets, and make ticket reservations within the cultural and tourism service; or, the user can also query regional information, regional passenger flow information, and travel information within the cultural and tourism service; in addition, the user can also make travel reservations and purchase cultural and tourism products within the cultural and tourism service.

[0020] Specifically, the cultural and tourism service can be configured with intelligent agents, and the cultural and tourism service can perform service processing through the intelligent agents. The cultural and tourism service can generate and configure corresponding trigger controls and / or interfaces for each function. The user can use the corresponding functions in the cultural and tourism service through the trigger controls and / or interfaces. This interface can be an intelligent agent interface for invoking the intelligent agent of the cultural and tourism service, and can invoke the intelligent agent of the cultural and tourism service after detecting that the intelligent agent interface is triggered. The intelligent agent interface can be configured on the cultural and tourism service page, and the user can trigger the intelligent agent interface to use the corresponding functions in the cultural and tourism service.

[0021] Among them, the intelligent agent refers to an intelligent agent accessing the cultural and tourism service or configured in the cultural and tourism service. The intelligent agent can cooperate with the cultural and tourism service to execute functions for realizing the cultural and tourism service. The intelligent agent can be independently deployed outside the program providing the cultural and tourism service or deployed in the program providing the cultural and tourism service. The intelligent agent can be configured with multiple sub-intelligent agents, and each sub-intelligent agent can correspond one-to-one to each function of the cultural and tourism service to independently realize the functions of the cultural and tourism service through the sub-intelligent agents, or each sub-intelligent agent can also cooperate to realize each function of the cultural and tourism service to realize each function of the cultural and tourism service through the cooperative processing of multiple sub-intelligent agents. Optionally, the sub-intelligent agents include: a question-and-answer sub-intelligent agent, a query sub-intelligent agent, a ticketing sub-intelligent agent, a guided tour sub-intelligent agent, and / or a cultural and tourism product sub-intelligent agent.

[0022] For example, the question-and-answer sub-intelligent agent can be used to realize the question function of cultural and tourism reference information and the question function of appearance suggestions of the cultural and tourism service, and the ticketing sub-intelligent agent can be used to realize the ticketing query function, ticketing purchase function, and ticketing refund function of the cultural and tourism service; or, the query sub-intelligent agent can also be used to realize the regional information query function, regional passenger flow query function, and appearance information query function of the cultural and tourism service, and the guided tour sub-intelligent agent can be used to realize the guided tour function of the cultural and tourism service; in addition, the cultural and tourism product sub-intelligent agent can be used to realize the travel reservation function and cultural and tourism product purchase function of the cultural and tourism service.

[0023] In specific implementation, during the process of a user accessing the cultural and tourism service, to improve the access efficiency and convenience, a near-field communication tag can be configured for the cultural and tourism service. The user can enter the cultural and tourism service by establishing a near-field communication connection between the user terminal and the near-field communication tag by bringing the user terminal close to the near-field communication tag. In this regard, the user terminal can establish a near-field communication connection with the near-field communication tag of the cultural and tourism service to enter the cultural and tourism service; optionally, the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag.

[0024] Specifically, fixed data can be configured in the near-field communication tag of the cultural and tourism service, such as: the access address of the cultural and tourism service. The user terminal can enter the cultural and tourism service according to the access address of the cultural and tourism service obtained through near-field communication interaction. In an optional implementation manner provided in this embodiment, the following method is adopted to enter the cultural and tourism service: parse the access data transmitted by the near-field communication tag to obtain the access address of the cultural and tourism service, and enter the cultural and tourism service based on the access address.

[0025] During the specific execution process, there is also a situation where a user immediately uses the cultural and tourism service after entering it. After the near-field communication interaction, the user terminal enters the cultural and tourism service and sends the interaction information to the server after submitting the interaction information through the intelligent agent interface configured for the cultural and tourism service. In another alternative implementation provided in this embodiment, before the user terminal obtains the interaction information, it further includes: parsing the access data transmitted by the near-field communication tag to obtain the access address of the cultural and tourism service, and entering the cultural and tourism service based on the access address.

[0026] In practical applications, to enhance the security of the cultural and tourism service, encrypted data can be configured in the near-field communication tag of the cultural and tourism service. For example, the access instruction of the cultural and tourism service is encrypted and written into the near-field communication tag. The user terminal parses the encrypted data obtained from the near-field communication interaction to obtain the data transmission interface of the cultural and tourism service, and calls the data transmission interface to send the encrypted data to the server. Correspondingly, before receiving the interaction information sent by the user terminal, it can receive the encrypted access data and decrypt it to obtain the access instruction for the cultural and tourism service page, and then send the cultural and tourism service page to the user terminal so that the user terminal can enter the cultural and tourism service. In an alternative implementation provided in this embodiment, before receiving the interaction information, it further includes: Obtaining the encrypted access data submitted by the user terminal by calling the data transmission interface of the cultural and tourism service; Decrypting the encrypted access data to obtain the access instruction for the cultural and tourism service page, and in response to the access instruction, sending the cultural and tourism service page to the user terminal. Optionally, the data transmission interface is obtained by parsing the encrypted access data transmitted by the near-field communication tag.

[0027] During the specific execution process, there is also a situation where a user has not used the cultural and tourism service after entering it, and the user has not performed any operations after entering the cultural and tourism service. In response to this, in an alternative implementation provided in this embodiment, the following method is used to enter the cultural and tourism service: receiving the cultural and tourism service page sent by the server after decrypting the encrypted access data, and displaying the cultural and tourism service page. Optionally, the encrypted access data is obtained after the user terminal performs near-field communication with the near-field communication tag and is sent to the server through the data transmission interface. Correspondingly, here, the encrypted access data submitted by the user terminal is obtained and decrypted, and the cultural and tourism service page is generated according to the decrypted data and sent to the user terminal. The cultural and tourism service page is generated in the following way: obtaining the encrypted access data submitted by the user terminal by calling the data transmission interface of the cultural and tourism service; decrypting the encrypted access data to obtain the access instruction for the cultural and tourism service page, and in response to the access instruction, sending the cultural and tourism service page to the user terminal.

[0028] In addition, in practical applications, users can also enter the cultural and tourism services in the application according to the access keywords of the cultural and tourism services. Specifically, the user terminal can obtain the access address of the cultural and tourism services by inputting the access keywords of the cultural and tourism services in the application in response to the user's operation instruction, and enter the cultural and tourism services based on the access address of the cultural and tourism services. In an optional implementation manner provided in this embodiment, the cultural and tourism services are entered in the following way: obtain the access address of the cultural and tourism services by inputting the access keywords of the cultural and tourism services in the application in response to the user's operation instruction, and enter the cultural and tourism services based on the access address of the cultural and tourism services.

[0029] In an actual scenario, the user terminal can enter the cultural and tourism services when the screen is unlocked. Specifically, the user can first unlock the user terminal and then perform near-field communication interaction with the near-field communication tag, or enter the cultural and tourism services by searching in the application. In addition, the user terminal can also perform near-field communication interaction with the near-field communication tag when the screen is locked, and the user terminal can enter the cultural and tourism services after unlocking. For the above two cases, the cultural and tourism services can be displayed on the user terminal in the form of a floating window and interact through the floating window.

[0030] During specific implementation, the user terminal obtains the interaction information submitted after triggering the intelligent agent interface for configuring the cultural and tourism services. After obtaining the interaction information, the user terminal sends the interaction information. Correspondingly, here, the interaction information submitted after triggering the intelligent agent interface for configuring the cultural and tourism service page by the user terminal is received.

[0031] Among them, the interaction information refers to the information used to describe the user's operation generated after the user triggers the intelligent agent interface for configuring the cultural and tourism services. The interaction information may include the configuration information of the intelligent agent interface triggered by the user and / or the interaction data entered by the user. Optionally, the interaction information includes the configuration information of the intelligent agent interface and / or the interaction data. Among them, the interaction data includes interaction text and / or interaction voice.

[0032] As described above, the intelligent agent interface refers to the interface for calling the intelligent agent of the cultural and tourism services configured in the cultural and tourism services and / or the cultural and tourism service page. After the intelligent agent interface is triggered, the intelligent agent of the cultural and tourism services can be called based on the interaction information. The interaction information can be submitted to the server by the user terminal after the user triggers the intelligent agent interface of the cultural and tourism services. Specifically, the interaction information can be sent to the server by the user terminal after triggering the intelligent agent interface of the question-and-answer sub-intelligent agent. Based on this, the interaction information contains the configuration information of the intelligent agent interface of the question-and-answer sub-intelligent agent and the interaction data entered by the user. Or, the interaction information can also be sent to the server by the user terminal after triggering the intelligent agent interface of the remaining candidate sub-intelligent agents. Based on this, the interaction information contains the configuration information of the intelligent agent interface of the candidate sub-intelligent agents.

[0033] In practical applications, after receiving the interaction information sent by the user terminal, it is possible to query in the knowledge base whether there is a preset reply text that matches the interaction data in the interaction information. If there is, the preset reply text can be sent to the user terminal to improve the response efficiency of the cultural and tourism service. In an optional implementation manner provided in this embodiment, after receiving the interaction information, it further includes: querying in the knowledge base whether there is a preset reply text that matches the interaction data in the interaction information; if there is, sending the preset reply text to the user terminal; if not, no processing is required; in addition, if no preset reply text that matches the interaction data is found in the knowledge base, step S204 can also be executed to perform an intelligent agent call for the cultural and tourism service based on the interaction information.

[0034] Step S204, perform an intelligent agent call for the cultural and tourism service based on the interaction information.

[0035] Specifically, when implementing, an intelligent agent call for the cultural and tourism service is performed based on the interaction information sent by the user terminal. Correspondingly, the intelligent agent of the cultural and tourism service determines the target sub-intelligent agent corresponding to the interaction information among the configured multiple sub-intelligent agents in response to the intelligent agent call, and obtains a service result through service collaboration processing between the target sub-intelligent agent and the sub-intelligent agent adapted to the interaction information. Optionally, the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among the configured multiple sub-intelligent agents. If the target sub-intelligent agent is a question-and-answer sub-intelligent agent, a service result is obtained through service collaboration processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information.

[0036] Specifically, during the process of performing the intelligent agent call, the interaction information can be used as the call input for the intelligent agent call of the cultural and tourism service to perform the intelligent agent call of the cultural and tourism service. Specifically, the application programming interface (API) of the intelligent agent of the cultural and tourism service can be called based on the interaction information to send the interaction information to the intelligent agent.

[0037] After the above-mentioned call for the cultural and tourism service is performed based on the interaction information sent by the user terminal, correspondingly, the intelligent agent of the cultural and tourism service performs processing in response to the intelligent agent call. During the specific execution process, a service result can be obtained by means of service collaboration processing through the sub-intelligent agent adapted to the interaction information; specifically, the intelligent agent can determine the target sub-intelligent agent according to the interaction information, and obtain a service result through service collaboration processing between the target sub-intelligent agent and the sub-intelligent agent adapted to the interaction information; during the service collaboration process, the target sub-intelligent agent can be used as the main intelligent agent in the service collaboration process for service collaboration processing; in addition, the intelligent agent can also be used as the main intelligent agent for service collaboration processing between the target sub-intelligent agent and the other sub-intelligent agents, or the target sub-intelligent agent and the other sub-intelligent agents can also perform service collaboration processing by mutually calling each other.

[0038] Among them, the service result can be the service collaboration result obtained after the sub - agents perform service collaboration processing. The service result may include the processing results of each sub - agent, may also include the target processing result generated by the target sub - agent, and may further include the aggregation result of the processing results of each sub - agent and the target sub - agent. Optionally, the service result includes: the processing result of the target sub - agent, the respective processing results corresponding to each sub - agent, and / or the aggregation result of the processing results of each sub - agent. Corresponding to the multiple sub - agents provided above, the service result may include the output data corresponding to each sub - agent. For example: the service result may include the service text generated by the Q&A sub - agent, and may also include the area information queried by the query sub - agent.

[0039] Optionally, the service result includes service text, the access address of an external program, the access address of a sub - service of a cultural and tourism service, service elements, and / or the configuration information of an agent interface; the service elements may include renderable elements submitted by an external program and / or renderable elements generated by a sub - agent.

[0040] Specifically, during the determination process of the target sub - agent, after receiving the interaction information, the target sub - agent corresponding to the interaction information can be determined among the multiple sub - agents configured in the agent according to the data included in the interaction information, so as to perform service processing through the target sub - agent. In an optional implementation manner provided in this embodiment, determining the target sub - agent corresponding to the interaction information among the configured multiple sub - agents includes: detecting whether the interaction information contains interaction data entered by the user; if so, determining the Q&A sub - agent as the target sub - agent among the sub - agents; if not, no processing is required. Alternatively, the target sub - agent can also be directly determined according to the configuration information of the agent interface included in the interaction information. In an optional implementation manner provided in this embodiment, determining the target sub - agent corresponding to the interaction information among the configured multiple sub - agents includes: extracting the configuration information of the agent interface included in the interaction information, and taking the sub - agent corresponding to the configuration information as the target sub - agent.

[0041] After the determination of the above - mentioned target sub - agent is completed, if the target sub - agent is the Q&A sub - agent, the Q&A sub - agent can query the preset reply text matching the interaction information in the knowledge base, and use the preset reply text as service data, or write the preset reply text into the service data. In an optional implementation manner provided in this embodiment, after determining the target sub - agent, it further includes: querying in the knowledge base whether there is a preset reply text matching the interaction data in the interaction information; if not, no processing is required; if so, obtaining the preset reply text to write the preset reply text into the service result.

[0042] Specifically, in the process of service collaborative processing, based on the multiple sub-agents provided above, the ways in which the target sub-agent collaborates with different agents in service processing may vary. The following specifically describes the service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information, as well as the service collaborative processing between the remaining candidate sub-agents and the sub-agent adapted to the interaction information.

[0043] (1) Service collaborative processing between the question-and-answer sub-agent and the sub-agent corresponding to the interaction information If the target sub-agent is the question-and-answer sub-agent, the service result is obtained through the service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information. Specifically, the agent determines the sub-agent corresponding to the interaction information as the question-and-answer sub-agent among the configured multiple sub-agents, and obtains the service result through the service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information.

[0044] Specifically, in the process of service collaborative processing, the agent and / or the question-and-answer sub-agent can select the candidate sub-agent adapted to the interaction data according to the interaction data in the interaction information, and perform service collaborative processing according to the service collaboration method between the question-and-answer sub-agent and the candidate sub-agent. In an optional implementation provided in this embodiment, obtaining the service result through the service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information includes: Selecting the candidate sub-agent adapted to the interaction data according to the interaction data included in the interaction information, and determining the service collaboration method between the question-and-answer sub-agent and the candidate sub-agent; performing service collaborative processing according to the service collaboration method to obtain the service result.

[0045] Optionally, the service collaboration method includes: using the question-and-answer sub-agent as the main agent to call the candidate sub-agent for service collaborative processing, mutually calling the question-and-answer sub-agent and the candidate sub-agent at the same level for service collaborative processing, and / or using the agent as the main agent to call the question-and-answer sub-agent and the candidate sub-agent for service collaborative processing.

[0046] Specifically, in the process of selecting the sub-agent adapted to the interaction information, the agent and / or the question-and-answer sub-agent can determine the candidate sub-agent according to the intention of the interaction information. In an optional implementation provided in this embodiment, the sub-agent adapted to the interaction information is determined in the following way: performing intention recognition on the interaction data in the interaction information to obtain the intention category, and determining the sub-agent corresponding to the intention category as the candidate sub-agent.

[0047] Specifically, during the process of intention recognition, the large language model can be used for intention recognition. During the process of intention recognition by the large language model, it can first perform intention recognition on the interaction data to obtain the user intention, match the user intention with the preset intention categories of each sub-agent, and select the preset intention category corresponding to the matching result as the intention recognition result. Specifically, during the process of determining the candidate sub-agent, the candidate sub-agent adapted to the interaction information can be selected according to the intention category; in an optional implementation manner provided in this embodiment, the candidate sub-agent is determined in the following manner: if the intention category includes the intention category corresponding to generating cultural and tourism reference texts, the question-and-answer sub-agent is selected as the candidate sub-agent among each sub-agent; if the intention category includes the intention category corresponding to querying regional information, the query sub-agent is selected as the candidate sub-agent among each sub-agent; if the intention category includes the intention category corresponding to purchasing tickets, the ticket sub-agent is selected as the candidate sub-agent among each sub-agent.

[0048] In addition, the association relationship between each sub-agent can be preset, and the service result can be obtained through the service collaboration processing between the question-and-answer sub-agent and the sub-agent associated with the question-and-answer sub-agent. For example: establish the association relationship between the question-and-answer sub-agent and the query sub-agent; the service result obtained through the service collaboration processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information can be replaced by: the service result obtained through the service collaboration processing between the question-and-answer sub-agent and the sub-agent associated with the question-and-answer sub-agent, and combined with the remaining steps and / or optional implementation manners provided in this embodiment to form a new implementation manner.

[0049] Based on the above three service collaboration processing methods, during the specific execution process, the collaboration processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information can be carried out according to the service collaboration method. The following separately describes the service collaboration processing process corresponding to the three service collaboration methods.

[0050] (a) Use the question-and-answer sub-agent as the main agent to call the candidate sub-agent for service collaboration processing During the specific execution process, the candidate sub-agent can be called for service processing based on the service data generated by the question-and-answer sub-agent to obtain the processing result, and the service data and the processing result are used as the service result; in the first optional implementation manner provided in this embodiment, obtaining the service result through the service collaboration processing according to the service collaboration method includes: The question-and-answer sub-agent inputs the interaction data in the interaction information into the large language model for data processing to generate service data, and extracts the regional keywords included in the service data; based on the regional keywords, the candidate sub-agent is called for service processing to obtain regional information, and the service data, the regional information, and / or the configuration information of the intelligent agent interface of the candidate sub-agent are used as the service result.

[0051] (b)Mutually call the Q&A sub-agent and the candidate sub-agent at the same level for service collaboration processing During the specific execution process, there is also a situation where the interaction data matches the preset call text of the candidate sub-agent. In response to this, after the candidate sub-agent generates a processing result, the Q&A sub-agent can generate service data based on the processing result, and use the processing result and the service data as the service result. In the second optional implementation provided in this embodiment, obtaining the service result through service collaboration processing according to the service collaboration method includes: The candidate sub-agent performs service processing based on the interaction information to obtain the access address of the sub-service corresponding to the candidate sub-agent; the Q&A sub-agent generates service data based on the access address and uses the access address and / or the service data as the service result.

[0052] Specifically, the agent can be used as the main agent to input the interaction information into the candidate sub-agent, then input the access address into the Q&A sub-agent, and use the access address and the service data as the service result.

[0053] (c)Use the agent as the main agent to call the Q&A sub-agent and the candidate sub-agent for service collaboration processing During the specific execution process, the agent can also be used as the main agent to call the Q&A sub-agent and the candidate sub-agent for service collaboration processing. In the third optional implementation provided in this embodiment, obtaining the service result through service collaboration processing according to the service collaboration method includes: The agent performs intent recognition and keyword extraction on the interaction data in the interaction information to obtain multiple keywords corresponding to each intent category; input each keyword into the candidate sub-agent corresponding to the intent category for service processing to obtain the processing result and the service data generated by the Q&A sub-agent; perform aggregation processing on the service data, the processing result, and / or the configuration information of the agent interface of the candidate sub-agent to obtain the service result.

[0054] In practical applications, during the service collaboration processing between the Q&A sub-agent and the other sub-agents, the sub-agent can also interact with the sub-program and / or the sub-service to obtain external data for service processing. The sub-agent for service collaboration processing can be determined through the keywords in the interaction data. Here, a specific description is given based on the ticket sub-agent and the tour guide sub-agent provided above.

[0055] (i)The Q&A sub-agent and the ticket sub-agent perform service collaboration processing During the specific execution process, the Q&A sub-agent can extract ticket keywords contained in the interaction data, call the ticket subroutine through the ticket sub-agent to query for ticket information, and the Q&A sub-agent generates service text based on the ticket information. In an optional implementation provided in this embodiment, obtaining a service result through service collaboration processing includes: The Q&A sub-agent extracts ticket keywords from the interaction information, inputs the ticket keywords into the ticket sub-agent to query for ticket information, and obtains ticket information. The ticket information and the interaction information are input into the Q&A sub-agent for text generation to obtain service text, and the ticket information, the service text, and the access address of the ticket subroutine are used as the service result. Optionally, the ticket information is obtained by querying the data query interface of the ticket subroutine with the ticket keywords as input data.

[0056] (ii)The Q&A sub-agent and the tour guide sub-agent perform service collaboration processing During the specific execution process, the Q&A sub-agent can extract tour guide keywords contained in the interaction data, call the tour guide sub-service of the cultural and tourism service through the tour guide sub-agent to obtain tour guide data, and the Q&A sub-agent generates service text based on the tour guide data. In another optional implementation provided in this embodiment, obtaining a service result through service collaboration processing includes: The Q&A sub-agent extracts tour guide keywords of the target area from the interaction information, inputs the area information of the target area into the tour guide sub-agent for service processing to obtain tour guide data of the target area. The tour guide data is input into the Q&A sub-agent for text generation to obtain service text, and the tour guide data, the service text, and the access address of the tour guide sub-service in the cultural and tourism service are used as the service result.

[0057] In addition to the above two ways of service collaboration processing between the Q&A sub-agent and the sub-agent, the appropriate sub-agent can also be called for service processing according to the extracted keywords. The specific execution method refers to the execution methods of the ticket sub-agent and the tour guide sub-agent provided above. For example, the passenger flow keywords of the target area are extracted from the interaction information, the area information of the target area is input into the query sub-agent to query the passenger flow of the target area to obtain passenger flow information; the passenger flow information is input into the Q&A sub-agent for text generation to obtain service text, and the passenger flow information, the service text, and the access address of the passenger flow subroutine are used as the service result.

[0058] In addition, during the service collaboration processing, the service collaboration processing between the Q&A sub-agent and the sub-agent adapted to the interaction information can also be performed when the service collaboration method is not determined. Specifically, the service collaboration processing can be performed by the main agent collaborating with the sub-agent. The following respectively explains the three service collaboration processes.

[0059] (A)The Q&A sub-agent serves as the main agent for service collaboration processing In the specific execution process, the Q&A sub-agent first generates service data based on the interaction data, and then calls the sub-agent adapted to the interaction information according to the service data generated by the Q&A sub-agent to obtain the service result; in the first optional implementation manner provided in this embodiment, obtaining the service result through service collaboration processing includes: The Q&A sub-agent inputs the interaction data in the interaction information into the large language model for data processing to generate service data, and extracts the regional keywords included in the service data; based on the regional keywords, the candidate sub-agent is called for service processing to obtain the regional information, and the service data, the regional information, and / or the configuration information of the intelligent agent interface of the candidate sub-agent are used as the service result. Optionally, the target region includes a cultural and tourism scenic area.

[0060] Furthermore, the regional information can be obtained after service processing by multiple candidate sub-agents. Multiple candidate sub-agents can be called based on the regional keywords for service processing to obtain multiple processing results, and the multiple results are used as the regional information and / or the multiple results are aggregated to obtain the regional information; for example, the query sub-agent is called to query the passenger flow in the target region to obtain the passenger flow volume of the target region, the ticketing sub-agent is called to query the ticketing information in the target region to obtain the ticketing information of the target region and / or the travel sub-agent is called to query the travel information in the target region to obtain the travel recommendation text of the target region, and the passenger flow volume, the ticketing information, and / or the travel recommendation text of the target region are used as the regional information. Among them, the travel recommendation text can be the recommendation text of public transportation and / or the recommendation text of travel restrictions.

[0061] Specifically, in the process of generating service data through the large language model, the Q&A sub-agent can select the target large language model adapted to the interaction data according to the intent category and / or keywords of the interaction data for service data generation; in the first optional implementation manner provided in this embodiment, the service data is obtained in the following way: the intent of the user is obtained by performing intent recognition on the interaction data, and the matching result is obtained by matching the user intent with the preset intents of each large language model; the target large language model is selected according to the matching result, and the interaction data is input into the target large language model for data processing to obtain the service data; Alternatively, the target prompt word can also be generated according to the keywords of the interaction data for data processing through the large language model; in the second optional implementation manner provided in this embodiment, the service data is obtained in the following way: the keywords of the interaction data are extracted and the target prompt word is generated according to the extracted keywords, and the target prompt word is input into the large language model for data processing to obtain the service data; Alternatively, an expert model adapted to the intent category can be selected according to the intent type of the interaction data for data processing to obtain service data. In the third alternative implementation provided in this embodiment, the service data is obtained in the following manner: perform intent recognition on the interaction data to obtain the user intent, and match the user intent with the preset intents of each model in the model library to obtain a matching result; select a target model according to the matching result, and input the interaction data into the target model for data processing to obtain service data.

[0062] (B) The Q&A sub-agent, as the main agent, first calls the candidate sub-agent for service collaborative processing During the specific execution process, there is also a situation where the interaction data corresponds to the preset call data of the candidate sub-agent. The candidate sub-agent can be called first for service processing to obtain service data, and the Q&A sub-agent generates a service text based on the service data to obtain a service result. In the second alternative implementation provided in this embodiment, obtaining the service result through service collaborative processing includes: The Q&A sub-agent inputs the interaction data in the interaction information into the candidate sub-agent for service processing to obtain a processing result; generates a preset interaction text according to the processing result, and generates a service result according to the processing result, the service text, and the configuration information of the intelligent agent interface of the Q&A sub-agent corresponding to the preset interaction text.

[0063] (C) The intelligent agent, as the main agent, performs service collaborative processing During the specific execution process, the intelligent agent can be used as the main agent to call the Q&A sub-agent and the sub-agent adapted to the interaction data in the interaction information for service collaborative processing, and aggregate the service processing results of the sub-agents. In the third alternative implementation provided in this embodiment, obtaining the service result through service collaborative processing includes: The intelligent agent performs intent recognition and keyword extraction on the interaction data in the interaction information to obtain multiple keywords corresponding to each intent category; inputs each keyword into the candidate sub-agent corresponding to the intent category for service processing to obtain a processing result and the service data generated by the Q&A sub-agent; performs aggregation processing on the service data, the processing result, and / or the configuration information of the intelligent agent interface of the candidate sub-agent to obtain a service result.

[0064] (2) Service collaborative processing of the remaining candidate sub-agents and the sub-agents corresponding to the interaction information If the target sub-agent is a candidate sub-agent, the service result is obtained through the collaborative processing of the candidate sub-agent and the sub-agent adapted to the interaction information, that is: the agent determines the sub-agent corresponding to the interaction information among the configured multiple sub-agents as the candidate sub-agent, and the service result is obtained through the collaborative processing of the candidate sub-agent and the sub-agent adapted to the interaction information. The following specifically describes the cases of the collaborative processing of the service for two types of candidate sub-agents and the sub-agent adapted to the interaction information.

[0065] (A) Obtaining the service result through the collaborative processing of the candidate sub-agent and the question-and-answer sub-agent In the specific execution process, the service result can be obtained through the collaborative processing of the candidate sub-agent and the question-and-answer sub-agent; in the first alternative implementation provided in this embodiment, if the target sub-agent is a candidate sub-agent, obtaining the service result through the collaborative processing includes: obtaining the service result through the collaborative processing of the candidate sub-agent and the question-and-answer sub-agent.

[0066] (B) Using the agent as the main agent for service collaborative processing In the specific execution process, the agent can be used as the main agent to collaboratively call the candidate sub-agent and the question-and-answer sub-agent for service processing to obtain the service result; in the second alternative implementation provided in this embodiment, if the target sub-agent is a candidate sub-agent, obtaining the service result through the collaborative processing includes: The agent calls the candidate sub-agent for service processing to obtain the access address of the sub-program and / or sub-service corresponding to the candidate sub-agent, and queries the candidate interaction text preset by the candidate sub-agent in the knowledge base; generates the agent interface of the question-and-answer sub-agent corresponding to the candidate interaction text, inputs the agent information of the candidate sub-agent into the question-and-answer sub-agent to generate the service text, and generates the service result according to the configuration information of the agent interface corresponding to the candidate interaction text and the service text.

[0067] Specifically, the agent inputs the interaction information into the candidate sub-agent for service processing to obtain the access address of the sub-program and / or sub-service corresponding to the candidate sub-agent, queries the candidate interaction text preset by the candidate sub-agent in the knowledge base, generates the agent interface of the question-and-answer sub-agent corresponding to the candidate interaction text, inputs the agent information of the candidate sub-agent into the question-and-answer sub-agent to generate the service text, and takes the configuration information of the agent interface corresponding to the candidate interaction text and the service text as the service result.

[0068] It should be noted that for the above-mentioned service collaborative processing methods of the remaining candidate sub-intelligent agents and the sub-intelligent agents corresponding to the interaction information, the service collaborative processing can also be carried out according to actual needs by using the service collaborative processing method of the question-and-answer sub-intelligent agent and the sub-intelligent agent corresponding to the interaction information provided above; for example: the candidate sub-intelligent agent performs service processing based on the interaction information to obtain a processing result; based on the processing result, the question-and-answer sub-intelligent agent is called to perform service processing to obtain service data, and the processing result and the service data are used as the service result.

[0069] It should also be noted that the question-and-answer sub-intelligent agent can be used as the target sub-intelligent agent or as the sub-intelligent agent adapted to the interaction information for service collaborative processing; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among the multiple configured sub-intelligent agents. If the target sub-intelligent agent is the question-and-answer sub-intelligent agent, the step of obtaining the service result through the service collaborative processing of the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information can be replaced by: the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among the multiple configured sub-intelligent agents. If the target sub-intelligent agent is the candidate sub-intelligent agent, the service result is obtained through the service collaborative processing of the candidate sub-intelligent agent and the sub-intelligent agent adapted to the interaction information, and is combined with the remaining steps and / or optional implementation manners provided in this embodiment to form a new embodiment.

[0070] In addition, the target sub-intelligent agent can also independently perform service processing to obtain a service result, and the target sub-intelligent agent performs service processing according to the interaction information to obtain a service result; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among the multiple configured sub-intelligent agents. If the target sub-intelligent agent is the question-and-answer sub-intelligent agent, the step of obtaining the service result through the service collaborative processing of the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information can be replaced by: the intelligent agent determines the sub-intelligent agent corresponding to the interaction information among the multiple configured sub-intelligent agents as the target sub-intelligent agent, and inputs the interaction information into the target sub-intelligent agent for service processing to obtain a service result; further, the target sub-intelligent agent can also call the remaining candidate sub-intelligent agents for service processing to obtain a service result during the service processing.

[0071] Step S206, generate service response data according to the service result and send it to the user terminal.

[0072] During specific implementation, extract the processing result of the sub-intelligent agent included in the service result, generate service response data according to the processing result and send it to the user terminal. Correspondingly, the user terminal receives the service response data and renders and displays the service response data on the cultural and tourism service page.

[0073] Among them, the service response data refers to the response data in response to the interaction information sent by the user terminal. The user terminal can display the service response data in the cultural and tourism service, and the service response data can be displayed in the form of messages, rich texts, and / or waistcoats. Optionally, the service response data includes: text data, access addresses, rich texts, and / or configuration information of the agent interface.

[0074] Specifically, during the generation process of the service response data, the processing results included in the service result can be classified according to the data type, and the service result can be written into a preset data template according to the data type; in an optional implementation manner provided in this embodiment, generating the service response data according to the service result includes: Classify and process the data included in the service result according to the data type to obtain the service data corresponding to each data type; Write the classified service data into the data template to obtain the service response data.

[0075] In practical applications, the server can pre-store some service elements to generate service response messages according to the service elements. The service result can also include the configuration information of the agent interface of the sub-agent to configure the agent interface in the service response data; in view of this, the service response data can be generated according to the service elements and the service result, and the agent interface can be configured in the service response data according to the configuration information of the agent interface in the service result; in an optional implementation manner provided in this embodiment, generating the service response data according to the service result includes: Extract the configuration information of the agent interface of the Q&A sub-agent corresponding to the reply text and the candidate interaction text included in the service result, and generate a service response message based on the reply text and / or the preset service elements; Configure the agent interface corresponding to the candidate interaction text in the service response message according to the configuration information, and use the configured service response message as the service response data.

[0076] In addition, the service result can also include the access addresses of the sub-services and / or external programs corresponding to the sub-agents. The access addresses can be configured in the text generated by the Q&A sub-agent to generate a rich text as the service response data; in another optional implementation manner provided in this embodiment, generating the service response data according to the service result includes: Extract the access addresses of the sub-programs and / or sub-services corresponding to the candidate sub-agents included in the service result and the reply text generated by the Q&A sub-agent; Generate a rich text according to the access address and / or the reply text and use it as the service response data.

[0077] It should be noted that for the two implementation methods of generating service response data based on service results provided above, any one of the implementation methods can be selected for implementation according to actual needs during the specific implementation process. It should be noted that the above two implementation methods can also be integrally combined according to actual needs, and corresponding technical means can also be selected from the two implementation methods for combination to form a new implementation method. For example, extract the access addresses of the subroutines and / or sub-services corresponding to the candidate sub-agents included in the service result, the reply text generated by the question-and-answer sub-agent, and the configuration information of the agent interface of the question-and-answer sub-agent corresponding to the candidate interaction text; according to the access address, generate rich text based on the agent interface and / or the reply text corresponding to the candidate interaction text and use it as service response data.

[0078] In summary, the agent-based service processing method provided in this embodiment can be applied to a server. During the process of a user accessing a cultural and tourism service, the server receives the interaction information submitted by the user terminal, invokes the agents of the cultural and tourism service based on the interaction information. The agent determines the target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, the server obtains a service result through service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information, performs service processing through the multi-agent service collaboration method, generates service response data based on the service result obtained by the agent, and sends it to the user terminal. By means of agent invocation, the service response efficiency is improved, the efficiency and reliability of data processing are improved through the multi-agent collaboration method, and the user's interaction perception is enhanced through the service response data.

[0079] The above steps S202 to S206 provided in this embodiment can be executed by the server of the cultural and tourism service. It should be noted that the above steps S202 to S206 executed by the server and the steps S502 to S506 executed by the user terminal in the following embodiments can cooperate with each other during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of steps S502 to S506 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of steps S202 to S206 provided in this embodiment.

[0080] The following takes the application of an agent-based service processing method provided in this embodiment in the first interaction scenario as an example, combined with Figure 3 , to further illustrate the agent-based service processing method provided in this embodiment. See Figure 3 , the agent-based service processing method applied to the first interaction scenario specifically includes the following steps.

[0081] Step S306, receive the interaction information sent by the user terminal.

[0082] Optionally, the interaction information includes the configuration information of the agent interface of the Q&A sub-agent and / or the interaction data entered by the user.

[0083] Step S308, perform agent call for cultural and tourism services based on the interaction information.

[0084] Here, the agent can determine the Q&A sub-agent among multiple configured sub-agents according to the configuration information in the interaction information, and through the Q&A sub-agent, the ticketing sub-agent and the travel sub-agent, perform service collaborative processing to obtain a service result.

[0085] Step S310, extract the cultural and tourism reference text, ticketing purchase link and travel recommendation text included in the service result obtained from the agent call.

[0086] Step S312, obtain a message template, write the cultural and tourism reference text and the travel recommendation text into the message target to obtain a service response message, and configure the ticketing purchase link in the service response message.

[0087] Step S314, send the configured service response message to the user terminal.

[0088] Among them, performing service collaborative processing to obtain a service result includes: the Q&A sub-agent inputs the interaction data in the interaction information into a large language model to obtain a cultural and tourism reference text; extracts the regional keyword in the cultural and tourism reference text, and inputs the regional keyword into the ticketing sub-agent to obtain a ticketing purchase link for the target region; extracts the time keyword in the cultural and tourism reference text, and inputs the time keyword into the travel sub-agent to obtain a travel recommendation text for the target region; aggregates the cultural and tourism reference text, the ticketing purchase link and the travel recommendation text to obtain a service result.

[0089] It should be noted that any one step or any combination of steps from step S306 to step S314 can be combined with any one step or any combination of steps from the above step S202 to step S206 to form a new implementation manner according to the needs of implementation and deployment; in addition, according to the actual deployment needs, any one or any combination of technical features in step S306 to step S314 can be combined with any one or more technical features provided by the above step S202 to step S206 to form a new implementation manner; or, any one or any combination of technical features in step S306 to step S314 can also be replaced by any one or more technical feature combinations provided by the above step S202 to step S206 according to the actual deployment needs to form a new implementation manner, which will not be elaborated here one by one.

[0090] In addition, it should be noted that the above steps S306 to S314 provided in this embodiment can be executed by the server. It should be noted that the above steps S306 to S314 executed by the server and the steps S302 to S304 and steps S316 to S318 executed by the user terminal in the following embodiment can cooperate with each other during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of steps S302 to S304 and steps S316 to S318 provided in the following method embodiment. When reading the following method embodiment, please refer to the corresponding content of steps S306 to S314 provided in this embodiment.

[0091] The following takes the application of an agent-based service processing method provided in this embodiment in the second interaction scenario as an example, and in combination with Figure 4 , the agent-based service processing method provided in this embodiment will be further described. Refer to Figure 4 , the agent-based service processing method applied to the second interaction scenario specifically includes the following steps.

[0092] Step S408, receive the interaction information sent by the user terminal.

[0093] Optionally, the interaction information includes: the configuration information of the agent interface of the passenger flow sub-agent.

[0094] Step S410, perform agent call for cultural and tourism services based on the interaction information.

[0095] Here, the agent can determine the agent corresponding to the interaction information as the passenger flow sub-agent among the configured multiple sub-agents, and obtain the service result through the service collaboration processing of the passenger flow sub-agent and the question-and-answer sub-agent.

[0096] Step S412, extract the reply text included in the service result and the configuration information of the agent interface of the question-and-answer sub-agent corresponding to the reply text.

[0097] Optionally, the reply text includes the service text generated by the question-and-answer sub-agent and the preset reply text corresponding to the passenger flow information queried by the question-and-answer sub-agent.

[0098] Step S414, configure the agent interface corresponding to the target reply text in the text area corresponding to the target reply text in the reply text according to the configuration information to obtain rich text.

[0099] Step S416, send the rich text to the user terminal.

[0100] Step S422, perform agent call for cultural and tourism services based on the target reply text to obtain the interaction text and send it to the user terminal.

[0101] Here, the agent queries the interaction text corresponding to the target reply text in the knowledge base in response to the agent call.

[0102] Among them, service collaboration processing is performed, including: the passenger flow sub-agent performs service processing according to the interaction information to obtain the passenger flow information of the target area; the passenger flow information is input into the Q&A sub-agent for text generation to obtain the service text, and the agent interface of the Q&A sub-agent that queries the target reply text corresponding to the passenger flow information in the knowledge base and generates the target reply text is obtained; the configuration information of the agent interface of the Q&A sub-agent, the service text, and the target reply text are used as the service result.

[0103] It should be noted that any one step or any combination of steps S408 to S416 and step S422 can be combined with any one step or any combination of steps S202 to S206 according to the needs of implementation and deployment to form a new implementation method; in addition, according to the actual deployment needs, any one or any combination of technical features in steps S408 to S416 and step S422 can be selected and combined with any one or more technical features provided in steps S202 to S206 to form a new implementation method; or, any one or any combination of technical features in steps S408 to S416 and step S422 can also be replaced by any one or more technical feature combinations provided in steps S202 to S206 according to the actual deployment needs to form a new implementation method, which will not be elaborated here one by one.

[0104] In addition, it should be noted that the above steps S408 to S416 and step S422 provided in this embodiment can be executed by the server. It should be noted that the above steps S408 to S416 and step S422 executed by the server can cooperate with the steps S404 to S406, steps S418 to S420, and step S424 executed by the user terminal in the following embodiments during the execution process. Therefore, when reading this embodiment, please refer to the corresponding contents of steps S404 to S406, steps S418 to S420, and step S424 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding contents of steps S408 to S416 and step S422 provided in this embodiment.

[0105] One or more embodiments of a service processing method based on an agent provided in this specification are as follows: Refer to Figure 5 , the service processing method based on an agent provided in this embodiment specifically includes steps S502 to S506.

[0106] Step S502: Obtain the interaction information submitted after the user triggers the intelligent agent interface for cultural and tourism service configuration.

[0107] The cultural and tourism service described in this embodiment may be a service related to culture and tourism. For example, it can be a cultural and tourism service related to a target area (city) provided by an application. The cultural and tourism service can be provided through the application and / or a subroutine of the application. Among them, the cultural and tourism service can provide multiple different functions. Users can access the cultural and tourism service to consult cultural and tourism information of the target area, query announcement information of the target area, query travel information of the target area, consult cultural and tourism reference information of the target area, and / or purchase tickets for the target area.

[0108] For example, users can ask questions about cultural and tourism reference information within the cultural and tourism service, and they can also ask questions about travel suggestions within the cultural and tourism service; or, users can also purchase tickets, query tickets, and make ticket reservations within the cultural and tourism service; or, users can also query regional information, regional passenger flow, and travel information within the cultural and tourism service; in addition, users can also make travel reservations and purchase cultural and tourism products within the cultural and tourism service.

[0109] Specifically, the cultural and tourism service can be configured with an intelligent agent. The cultural and tourism service can process services through the intelligent agent. For each function, the cultural and tourism service can generate and configure corresponding trigger controls and / or interfaces. Users can use the corresponding functions in the cultural and tourism service through the trigger controls and / or interfaces. This interface can be an intelligent agent interface for calling the intelligent agent of the cultural and tourism service. The intelligent agent call of the cultural and tourism service can be performed after detecting that the intelligent agent interface is triggered. The intelligent agent interface can be configured on the cultural and tourism service page, and users can trigger the intelligent agent interface to use the corresponding functions in the cultural and tourism service.

[0110] Among them, the intelligent agent refers to an intelligent agent connected to the cultural and tourism service or configured in the cultural and tourism service. The intelligent agent can cooperate with the cultural and tourism service to execute functions to achieve the functions of the cultural and tourism service. The intelligent agent can be independently deployed outside the program providing the cultural and tourism service, or deployed in the program providing the cultural and tourism service; the intelligent agent can be configured with multiple sub-intelligent agents, and each sub-intelligent agent can correspond to each function of the cultural and tourism service one by one to independently implement the functions of the cultural and tourism service through the sub-intelligent agent. Each sub-intelligent agent can also cooperate to implement each function of the cultural and tourism service to achieve each function of the cultural and tourism service through the collaborative processing of multiple sub-intelligent agents; optionally, the sub-intelligent agents include: question-and-answer sub-intelligent agents, query sub-intelligent agents, ticket sub-intelligent agents, guide sub-intelligent agents, and / or cultural and tourism product sub-intelligent agents.

[0111] For example, the question function of cultural and tourism reference information and the question function of appearance suggestions of cultural and tourism services can be realized through the Q&A sub-agent. The ticket query function, ticket purchase function and ticket query function of cultural and tourism services can be realized through the ticket sub-agent. The regional information query function, regional passenger flow query function and appearance information query function of cultural and tourism services can also be realized through the query sub-agent. The guiding function of cultural and tourism services can be realized through the guiding sub-agent. The travel reservation function and cultural and tourism commodity purchase function of cultural and tourism services can also be realized through the cultural and tourism commodity sub-agent.

[0112] In specific implementation, during the process of a user accessing cultural and tourism services, to improve the access efficiency and enhance the access convenience, near-field communication tags can be configured for cultural and tourism services. In this regard, a near-field communication connection can be established between the user terminal and the near-field communication tag of cultural and tourism services to enter the cultural and tourism services; optionally, the cultural and tourism services enter after near-field communication interaction with the near-field communication tag.

[0113] Specifically, fixed data can be configured in the near-field communication tag of cultural and tourism services, such as: the access address of the cultural and tourism service page. The cultural and tourism services can be entered according to the access address of the cultural and tourism service page obtained through near-field communication interaction with the near-field communication tag, which improves the access efficiency; in an optional implementation manner provided in this embodiment, the following method is adopted to enter the cultural and tourism services: analyze the access data transmitted by the near-field communication tag to obtain the access address of the cultural and tourism services, and enter the cultural and tourism services based on the access address.

[0114] During the specific execution process, there is also a situation where the user immediately uses the cultural and tourism services after entering the cultural and tourism services. The user terminal enters the cultural and tourism services after near-field communication interaction and sends interaction information to the server after submitting interaction information through the intelligent body interface configured by the cultural and tourism services; in another optional implementation manner provided in this embodiment, before the user terminal enters the cultural and tourism services, it further includes: analyzing the access data transmitted by the near-field communication tag to obtain the access address of the cultural and tourism services, and entering the cultural and tourism services based on the access address.

[0115] In practical applications, to enhance the security of cultural and tourism services, encrypted data can be configured in the near-field communication tag of cultural and tourism services, such as: encrypting the access instruction of cultural and tourism services and writing it into the near-field communication tag. Obtain the data transmission interface of cultural and tourism services by analyzing the encrypted data obtained through near-field communication interaction, call the data transmission interface to send encrypted data to the server. Before receiving the interaction information, the server can receive the encrypted access data, decrypt it to obtain the access instruction of the cultural and tourism service page, and send the cultural and tourism service page to the user terminal. Correspondingly, receive and display the cultural and tourism service page sent by the server to enter the cultural and tourism services; in another optional implementation manner provided in this embodiment, before obtaining the interaction information, it further includes: Calling the near-field communication component to perform near-field communication interaction with the near-field communication tag to obtain the encrypted access data transmitted by the near-field communication tag; Analyze the encrypted access data to obtain the data transmission interface of the cultural and tourism service, and call the data transmission interface by using the encrypted access data as the input for interface call; Receive the cultural and tourism service page sent by the server and display it.

[0116] During the specific execution process, there is also a situation where the user enters the cultural and tourism service but has not used the cultural and tourism service yet, and the user has not performed any operations after entering the cultural and tourism service. In view of this, in an optional implementation manner provided in this embodiment, the following method is used to enter the cultural and tourism service: receive the cultural and tourism service page sent by the server after decrypting the encrypted access data, and display the cultural and tourism service page; Optionally: the encrypted access data is obtained after the user terminal performs near-field communication with the near-field communication tag, and is sent to the server through the data transmission interface.

[0117] In addition, in actual applications, the user can also enter the cultural and tourism service in the application according to the access keyword of the cultural and tourism service. Specifically, the user terminal can obtain the access address of the cultural and tourism service by inputting the access keyword of the cultural and tourism service in the application in response to the user's operation instruction, and enter the cultural and tourism service based on the access address of the cultural and tourism service; In an optional implementation manner provided in this embodiment, the cultural and tourism service is entered in the following way: obtain the access address of the cultural and tourism service by inputting the access keyword of the cultural and tourism service in the application in response to the user's operation instruction, and enter the cultural and tourism service based on the access address of the cultural and tourism service.

[0118] In the actual scenario, the user terminal can enter the cultural and tourism service when the screen is unlocked. Specifically, the user can first unlock the user terminal and then perform near-field communication interaction with the near-field communication tag, or enter the cultural and tourism service by searching in the application; In addition, the user terminal can also enter the cultural and tourism service by performing near-field communication interaction with the near-field communication tag when the screen is locked, and the user terminal can enter the cultural and tourism service after unlocking; For the above two situations, the cultural and tourism service can be displayed on the user terminal in the form of a floating window and interacted through the floating window.

[0119] In this embodiment, the access and use of cultural and tourism services are carried out by means of page interaction of users in cultural and tourism services. An intelligent agent interface can be configured in the cultural and tourism services so that users can trigger the intelligent agent interface to use the corresponding functions. Specifically, when implemented, the user terminal first obtains the interaction information submitted after the user triggers the intelligent agent interface configured for the cultural and tourism services; during the specific execution process, the user terminal can obtain the interaction information submitted after the user triggers the intelligent agent interface configured for the cultural and tourism service page; in addition, the service can also be displayed in the form of a floating window. In this regard, the user terminal can obtain the interaction information submitted after the user triggers the intelligent agent interface configured for the cultural and tourism service window. Step S202 can be replaced with: obtaining the interaction information submitted after the user triggers the intelligent agent interface configured for the cultural and tourism service window; optionally, the cultural and tourism service window is configured on top of the application and / or the system desktop.

[0120] Among them, the interaction information refers to the information used to describe the user's operations generated after the user triggers the intelligent agent interface configured for the cultural and tourism services. The interaction information may include the configuration information of the intelligent agent interface triggered by the user and / or the interaction data entered by the user; optionally, the interaction information includes the configuration information of the intelligent agent interface and / or the interaction data; among them, the interaction data includes interaction text and / or interaction voice.

[0121] As described above, the intelligent agent interface refers to the call interface of the intelligent agent of the cultural and tourism services configured in the cultural and tourism services and / or the cultural and tourism service page. The interaction information can be submitted to the server through the user terminal after the user triggers the intelligent agent interface of the cultural and tourism services. Specifically, the interaction information can be sent to the server through the user terminal after triggering the intelligent agent interface of the question-and-answer sub-intelligent agent. Based on this, the interaction information contains the configuration information of the intelligent agent interface of the question-and-answer sub-intelligent agent and the interaction data entered by the user; or, the interaction information can also be sent to the server through the user terminal after triggering the intelligent agent interface of the remaining candidate sub-intelligent agents. Based on this, the interaction information contains the configuration information of the intelligent agent interface of the candidate sub-intelligent agents.

[0122] Step S504, sending the interaction information to the server.

[0123] Specifically, when implemented, the interaction information is sent to the server so that the server can call the intelligent agent of the cultural and tourism services based on the interaction information. Correspondingly, the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among the multiple configured sub-intelligent agents in response to the intelligent agent call of the server, and obtains the service result through service collaborative processing between the target sub-intelligent agent and the sub-intelligent agent adapted to the interaction information.

[0124] Specifically, during the process of agent invocation, the interaction information can be used as the invocation input for the agent invocation of cultural and tourism services to perform the agent invocation of cultural and tourism services. Specifically, the application programming interface (API) of the agent for cultural and tourism services can be invoked based on the interaction information to send the interaction information to the agent.

[0125] In practical applications, after receiving the interaction information, the server can query in the knowledge base whether there is a preset reply text that matches the interaction data in the interaction information. If it exists, the preset reply text can be sent to the user terminal to improve the response efficiency of cultural and tourism services; in an optional implementation provided in this embodiment, after receiving the interaction information, it further includes: querying in the knowledge base whether there is a preset reply text that matches the interaction data in the interaction information; if it exists, sending the preset reply text to the user terminal; if not, no processing is required. In addition, if no preset reply text that matches the interaction data is found in the knowledge base, step S204 can also be executed to perform the agent invocation of cultural and tourism services based on the interaction information.

[0126] After the above-mentioned invocation of cultural and tourism services based on the interaction information sent by the user terminal, correspondingly, the agent of cultural and tourism services processes in response to the agent invocation. During the specific execution process, the service result can be obtained by means of service collaboration processing through a sub-agent adapted to the interaction information; during the specific execution process, the agent can determine the target sub-agent according to the interaction information, and obtain the service result through the service collaboration processing of the target sub-agent and the sub-agent adapted to the interaction information; during the service collaboration process, the target sub-agent can be used as the main agent in the service collaboration process for service collaboration processing; in addition, the agent can also be used as the main agent for the service collaboration processing of the target sub-agent and the other sub-agents, or the target sub-agent and the other sub-agents can also perform service collaboration processing in a way of mutual invocation.

[0127] Among them, the service result can be the service collaboration result obtained after the service collaboration processing of each sub-agent. The service result can include the respective processing results of each sub-agent, or can also include the target processing result generated by the target sub-agent. Corresponding to the multiple sub-agents provided above, the service result can include the output data corresponding to each sub-agent; for example: the service text generated by the Q&A sub-agent, the regional information queried by the query sub-agent. Optionally, the service result includes services, access addresses of external programs, access addresses of sub-services of cultural and tourism services, service elements, and / or configuration information of agent interfaces; the service elements can include renderable elements submitted by external programs and / or renderable elements generated by sub-agents.

[0128] Specifically, during the process of determining the target sub-agent, after receiving the interaction information, the target sub-agent corresponding to the interaction information can be determined from multiple sub-agents configured in the agent according to the data included in the interaction information, so as to perform service processing through the target sub-agent, improving the user's perception; in an optional implementation provided in this embodiment, determining the target sub-agent corresponding to the interaction information from multiple configured sub-agents includes: detecting whether the interaction information contains interaction data entered by the user; if so, determining the Q&A sub-agent as the target sub-agent among each sub-agent; if not, no processing is required. Alternatively, the target sub-agent can also be directly determined according to the configuration information of the agent interface included in the interaction information; in an optional implementation provided in this embodiment, determining the target sub-agent corresponding to the interaction information from multiple configured sub-agents includes: extracting the configuration information of the agent interface included in the interaction information, and taking the sub-agent corresponding to the configuration information as the target sub-agent.

[0129] Specifically, during the process of service collaboration and processing, based on the multiple sub-agents provided above, the ways for the target sub-agent to perform service collaboration and processing with different agents may be different. The following will specifically describe the service collaboration and processing between the Q&A sub-agent and the sub-agent adapted to the interaction information, and the service collaboration and processing between the remaining candidate sub-agents and the sub-agent adapted to the interaction information.

[0130] (1) Service collaboration and processing between the Q&A sub-agent and the sub-agent corresponding to the interaction information If the target sub-agent is the Q&A sub-agent, the service result is obtained through the service collaboration and processing between the Q&A sub-agent and the sub-agent adapted to the interaction information. Specifically, the agent determines that the sub-agent corresponding to the interaction information among the multiple configured sub-agents is the Q&A sub-agent, and the service result is obtained through the service collaboration and processing between the Q&A sub-agent and the sub-agent adapted to the interaction information.

[0131] Specifically, during the process of service collaboration and processing, the agent and / or the Q&A sub-agent can select the candidate sub-agent adapted to the interaction data according to the interaction data in the interaction information, and perform service collaboration and processing according to the service collaboration method between the Q&A sub-agent and the candidate sub-agent; in an optional implementation provided in this embodiment, obtaining the service result through the service collaboration and processing between the Q&A sub-agent and the sub-agent adapted to the interaction information includes: Select candidate sub - agents adapted to the interaction data based on the interaction data included in the interaction information, and determine the service collaboration method of the Q&A sub - agent and the candidate sub - agents; perform service collaboration processing according to the service collaboration method to obtain a service result. Optionally, the service collaboration method includes: using the Q&A sub - agent as the main agent to call the candidate sub - agents for service collaboration processing, mutually calling the Q&A sub - agent and the candidate sub - agents at the same level for service collaboration processing, and / or using another agent as the main agent to call the Q&A sub - agent and the candidate sub - agents for service collaboration processing.

[0132] Specifically, in the process of selecting sub - agents adapted to the interaction information, the candidate sub - agents can be determined by the agent and / or the Q&A sub - agent according to the intention of the interaction information; in an optional implementation provided in this embodiment, the sub - agents adapted to the interaction information are determined in the following way: perform intention recognition on the interaction data in the interaction information to obtain an intention category, and determine the sub - agent corresponding to the intention category as the candidate sub - agent.

[0133] Specifically, in the process of intention recognition, the large - language model can be used for intention recognition. In the process of the large - language model performing intention recognition, it can first perform intention recognition on the interaction data to obtain the user intention, match the user intention with the preset intention categories of each sub - agent, and select the preset intention category corresponding to the matching result as the intention recognition result. Specifically, in the process of determining the candidate sub - agents, the candidate sub - agents adapted to the interaction information can be selected according to the intention category; in an optional implementation provided in this embodiment, the candidate sub - agents are determined in the following way: if the intention category includes the intention category corresponding to generating cultural and tourism reference texts, select the sub - agent corresponding to generating cultural and tourism reference texts as the candidate sub - agent among all sub - agents; if the intention category includes the intention category corresponding to querying regional information, select the sub - agent corresponding to querying regional information as the candidate sub - agent among all sub - agents; if the intention category includes the intention category corresponding to purchasing cultural and tourism tickets, select the sub - agent corresponding to purchasing cultural and tourism tickets as the candidate sub - agent among all sub - agents.

[0134] In addition, the association relationship between each sub - agent can be preset, and the service result can be obtained by performing service collaboration processing through the Q&A sub - agent and the sub - agent associated with the Q&A sub - agent; obtaining the service result by performing service collaboration processing through the Q&A sub - agent and the sub - agent adapted to the interaction information can be replaced with: obtaining the service result by performing service collaboration processing through the Q&A sub - agent and the sub - agent associated with the Q&A sub - agent, and combining it with the remaining steps and / or optional implementation methods provided in this embodiment to form a new implementation method.

[0135] Based on the three service collaboration processing methods provided above, during the specific execution process, the collaborative processing of the question-and-answer sub-agent and the sub-agent adapted to the interaction information can be carried out according to the service collaboration method. The following separately describes the service collaboration processing processes corresponding to the three service collaboration methods.

[0136] (a) Use the question-and-answer sub-agent as the main agent to call the candidate sub-agent for service collaboration processing During the specific execution process, the candidate sub-agent can be called for service processing based on the service data generated by the question-and-answer sub-agent to obtain a processing result, and the service data and the processing result are used as the service result; in the first optional implementation method provided in this embodiment, obtaining the service result by performing service collaboration processing according to the service collaboration method includes: The question-and-answer sub-agent inputs the interaction data in the interaction information into the large language model for data processing to generate service data, and extracts the regional keywords included in the service data; based on the regional keywords, the candidate sub-agent is called for service processing to obtain regional information, and the service data, the regional information, and / or the configuration information of the intelligent agent interface of the candidate sub-agent are used as the service result.

[0137] (b) Mutually call the question-and-answer sub-agent and the candidate sub-agent at the same level for service collaboration processing During the specific execution process, there is also a situation where the interaction data matches the preset call text of the candidate sub-agent. In response to this, after the candidate sub-agent generates a processing result, the question-and-answer sub-agent generates service data based on the processing result, and the processing result and the service data are used as the service result; in the second optional implementation method provided in this embodiment, obtaining the service result by performing service collaboration processing according to the service collaboration method includes: The candidate sub-agent performs service processing based on the interaction information to obtain the access address of the sub-service corresponding to the candidate sub-agent; the question-and-answer sub-agent generates service data according to the access address and uses the access address and / or the service data as the service result.

[0138] Specifically, the intelligent agent can input the interaction information into the candidate sub-agent as the main agent, then input the access address into the question-and-answer sub-agent, and use the access address and the service data as the service result.

[0139] (c) Use the intelligent agent as the main agent to call the question-and-answer sub-agent and the candidate sub-agent for service collaboration processing During the specific execution process, the intelligent agent can also be used as the main agent to call the question-and-answer sub-agent and the candidate sub-agent for service collaboration processing; in the third optional implementation method provided in this embodiment, obtaining the service result by performing service collaboration processing according to the service collaboration method includes: The agent performs intent recognition and keyword extraction on the interaction data in the interaction information to obtain multiple keywords corresponding to each intent category; inputs each keyword into the candidate sub-agent corresponding to the intent category for service processing to obtain the processing result and the service data generated by the Q&A sub-agent; and performs aggregation processing on the service data, the processing result, and / or the configuration information of the agent interface of the candidate sub-agent to obtain the service result.

[0140] In practical applications, during the process of service collaborative processing between the Q&A sub-agent and the other sub-agents, the sub-agent can also perform data interaction with the sub-program and / or sub-service to obtain external data for service processing. The sub-agent for service collaborative processing can be determined through the keywords in the interaction data. Here, specific descriptions are made based on the provided ticket sub-agent and tour guide sub-agent.

[0141] (i) The Q&A sub-agent and the ticket sub-agent perform service collaborative processing During the specific execution process, the Q&A sub-agent can extract the ticket keywords included in the interaction data, call the ticket sub-program through the ticket sub-agent to query the ticket information, and the Q&A sub-agent generates the service text based on the ticket information; in an optional implementation manner provided in this embodiment, obtaining the service result through service collaborative processing includes: The Q&A sub-agent extracts the ticket keywords from the interaction information, inputs the ticket keywords into the ticket sub-agent to query the ticket information to obtain the ticket information; inputs the ticket information and the interaction information into the Q&A sub-agent to generate the service text, and takes the ticket information, the service text, and the access address of the ticket sub-program as the service result. Optionally, the ticket information is obtained by querying the data query interface of the ticket sub-program with the ticket keywords as the input data.

[0142] (ii) The Q&A sub-agent and the tour guide sub-agent perform service collaborative processing During the specific execution process, the Q&A sub-agent can extract the tour guide keywords included in the interaction data, call the tour guide sub-service of the cultural and tourism service through the tour guide sub-agent to obtain the tour guide data, and the Q&A sub-agent generates the service text based on the tour guide data; in another optional implementation manner provided in this embodiment, obtaining the service result through service collaborative processing includes: The Q&A sub-agent extracts the tour guide keywords of the target area from the interaction information, inputs the area information of the target area into the tour guide sub-agent for service processing to obtain the tour guide data of the target area; inputs the tour guide data into the Q&A sub-agent to generate the service text, and takes the tour guide data, the service text, and the access address of the tour guide sub-service in the cultural and tourism service as the service result.

[0143] In addition to the two ways of providing question-and-answer sub-intelligent agents and sub-intelligent agents for service collaborative processing mentioned above, it is also possible to call the adapted sub-intelligent agents for service processing according to the extracted keywords. The specific execution method refers to the execution methods of the ticket sub-intelligent agent and the tour guide sub-intelligent agent provided above. For example: extract the passenger flow keywords of the target area from the interaction information, input the area information of the target area into the query sub-intelligent agent to query the passenger flow of the target area to obtain the passenger flow information; input the passenger flow information into the question-and-answer sub-intelligent agent to generate the service text, and use the passenger flow information, the service text, and the access address of the passenger flow subroutine as the service result.

[0144] In addition, during the service collaborative processing, it is also possible to perform the service collaborative processing of the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information without determining the service collaborative method. Specifically, the service collaborative processing can be carried out by the main intelligent agent collaborating with the sub-intelligent agent. The following will respectively explain the three service collaborative processes.

[0145] (A) The question-and-answer sub-intelligent agent serves as the main intelligent agent for service collaborative processing In the specific execution process, the question-and-answer sub-intelligent agent first generates service data based on the interaction data, and then calls the sub-intelligent agent adapted to the interaction information according to the service data generated by the question-and-answer sub-intelligent agent to obtain the service result; in the third optional implementation method provided in this embodiment, obtaining the service result through service collaborative processing includes: The question-and-answer sub-intelligent agent inputs the interaction data in the interaction information into the large language model for data processing to generate service data, and extracts the area keywords included in the service data; based on the area keywords, call the candidate sub-intelligent agents for service processing to obtain the area information, and use the service data, the area information, and / or the configuration information of the intelligent agent interface of the candidate sub-intelligent agents as the service result. Optionally, the target area includes cultural and tourism scenic spots.

[0146] Furthermore, the area information can be obtained after service processing by multiple candidate sub-intelligent agents. Multiple candidate sub-intelligent agents can be called based on the area keywords for service processing to obtain multiple processing results, and use the multiple results as the area information and / or aggregate the multiple results to obtain the area information; for example, call the query sub-intelligent agent to query the passenger flow of the target area to obtain the passenger flow volume of the target area, call the ticket sub-intelligent agent to query the ticket information of the target area and / or call the travel sub-intelligent agent to query the travel recommendation text of the target area, and use the passenger flow volume, the ticket information, and / or the travel recommendation text of the target area as the area information. Among them, the travel recommendation text can be the recommendation text of public transportation and / or the recommendation text of travel restrictions.

[0147] Specifically, in the process of generating service data through a large language model, the Q&A sub-agent can select a target large language model adapted to the interaction data according to the intent category and / or keywords of the interaction data for service data generation; in the first optional implementation provided in this embodiment, the service data is obtained in the following manner: perform intent recognition on the interaction data to obtain the user intent, and match the user intent with the preset intents of each large language model to obtain a matching result; select the target large language model according to the matching result, and input the interaction data into the target large language model for data processing to obtain the service data; Alternatively, the target prompt word can also be generated according to the keywords of the interaction data and the data can be processed through the large language model; in the second optional implementation provided in this embodiment, the service data is obtained in the following manner: extract the keywords from the interaction data and generate the target prompt word according to the extracted keywords, and input the target prompt word into the large language model for data processing to obtain the service data; Or, an expert model adapted to the intent category can be selected according to the intent type of the interaction data for data processing to obtain the service data; in the third optional implementation provided in this embodiment, the service data is obtained in the following manner: perform intent recognition on the interaction data to obtain the user intent, and match the user intent with the preset intents of each model in the model library to obtain a matching result; select the target model according to the matching result, and input the interaction data into the target model for data processing to obtain the service data.

[0148] (B)The Q&A sub-agent, as the main agent, first calls the candidate sub-agent for service collaborative processing During the specific execution process, there is also a situation where the interaction data corresponds to the preset call data of the candidate sub-agent. The candidate sub-agent can be called first for service processing to obtain the service data, and the Q&A sub-agent generates the service text based on the service data to obtain the service result; in the fourth optional implementation provided in this embodiment, obtaining the service result through service collaborative processing includes: The Q&A sub-agent inputs the interaction data in the interaction information into the candidate sub-agent for service processing to obtain the processing result; generate the preset interaction text according to the processing result, and generate the service result according to the processing result, the service text, and the configuration information of the intelligent agent interface corresponding to the preset interaction text.

[0149] (C)The intelligent agent, as the main agent, conducts service collaborative processing During the specific execution process, the intelligent agent can be used as the main agent to call the Q&A sub-agent and the sub-agent adapted to the interaction data in the interaction information for service collaborative processing, and aggregate the service processing results of the sub-agents; in the first optional implementation provided in this embodiment, obtaining the service result through service collaborative processing includes: The agent performs intention recognition and keyword extraction on the interaction data in the interaction information to obtain multiple keywords corresponding to each intention category; inputs each keyword into the candidate sub-agent corresponding to the intention category for service processing to obtain the processing result and the service data generated by the question-and-answer sub-agent; performs aggregation processing on the service data, the processing result, and / or the configuration information of the agent interface of the candidate sub-agent to obtain the service result.

[0150] (2)Service collaborative processing of the remaining candidate sub-agents and the sub-agent corresponding to the interaction information If the target sub-agent is a candidate sub-agent, the service result is obtained through the service collaborative processing of the candidate sub-agent and the sub-agent adapted to the interaction information, that is: the agent determines the sub-agent corresponding to the interaction information among the configured multiple sub-agents as the candidate sub-agent, and obtains the service result through the service collaborative processing of the candidate sub-agent and the sub-agent adapted to the interaction information. The following specifically describes the service collaborative processing of the two types of candidate sub-agents and the sub-agent adapted to the interaction information.

[0151] (A)Service collaborative processing through the candidate sub-agent and the question-and-answer sub-agent In the specific execution process, the service result can be obtained through the service collaborative processing of the candidate sub-agent and the question-and-answer sub-agent; in the first alternative implementation provided in this embodiment, if the target sub-agent is a candidate sub-agent, the service result obtained through service collaborative processing includes: obtaining the service result through the service collaborative processing of the candidate sub-agent and the question-and-answer sub-agent.

[0152] (B)Using the agent as the main agent for service collaborative processing In the specific execution process, the agent can be used as the main agent to collaboratively call the candidate sub-agent and the question-and-answer sub-agent for service processing to obtain the service result; in the second alternative implementation provided in this embodiment, the service result obtained through service collaborative processing includes: The agent calls the candidate sub-agent for service processing to obtain the access address of the sub-program and / or sub-service corresponding to the candidate sub-agent, and queries the candidate interaction text preset by the candidate sub-agent in the knowledge base; generates the agent interface of the question-and-answer sub-agent corresponding to the candidate interaction text, inputs the agent information of the candidate sub-agent into the question-and-answer sub-agent to generate the service text, and generates the service result according to the configuration information of the agent interface corresponding to the candidate interaction text and the service text.

[0153] Specifically, the agent inputs interaction information into candidate sub-agents for service processing to obtain the access addresses of the sub-programs and / or sub-services corresponding to the candidate sub-agents, queries the candidate interaction texts preset for the candidate sub-agents in the knowledge base, generates the agent interfaces of the Q&A sub-agents corresponding to the candidate interaction texts, inputs the agent information of the candidate sub-agents into the Q&A sub-agents to generate service texts, and uses the configuration information of the agent interfaces corresponding to the candidate interaction texts and the service texts as service results.

[0154] It should be noted that for the above-mentioned service collaborative processing methods of the remaining candidate sub-agents and the sub-agents corresponding to the interaction information, the service collaborative processing methods of the Q&A sub-agents and the sub-agents corresponding to the interaction information provided above can also be adopted according to actual needs.

[0155] It should also be noted that the Q&A sub-agent can be used as the target sub-agent or as the sub-agent adapted to the interaction information for service collaborative processing; when the agent determines the target sub-agent corresponding to the interaction information among the multiple configured sub-agents, if the target sub-agent is the Q&A sub-agent, the step of obtaining the service result through service collaborative processing between the Q&A sub-agent and the sub-agent adapted to the interaction information can be replaced by: the agent determines the target sub-agent corresponding to the interaction information among the multiple configured sub-agents, if the target sub-agent is the candidate sub-agent, obtains the service result through service collaborative processing between the candidate sub-agent and the sub-agent adapted to the interaction information, and combines it with the remaining steps and / or optional implementation manners provided in this embodiment to form a new embodiment.

[0156] In addition, the target sub-agent can also independently perform service processing to obtain the service result, and the target sub-agent performs service processing according to the interaction information to obtain the service result; when the agent determines the target sub-agent corresponding to the interaction information among the multiple configured sub-agents, if the target sub-agent is the Q&A sub-agent, the step of obtaining the service result through service collaborative processing between the Q&A sub-agent and the sub-agent adapted to the interaction information can be replaced by: the agent determines the sub-agent corresponding to the interaction information among the multiple configured sub-agents as the target sub-agent, and inputs the interaction information into the target sub-agent for service processing to obtain the service result.

[0157] It should be added that the server can directly call the sub-agent corresponding to the configuration information based on the configuration information of the agent interface in the interaction information. Step S204 can be replaced with: calling the target sub-agent for cultural and tourism services based on the configuration information of the agent interface of the target sub-agent in the interaction information, and combining it with the remaining steps and / or optional implementation manners provided in this embodiment to form a new embodiment; correspondingly, the agent determines the target sub-agent corresponding to the interaction information among the multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, obtaining the service result through service collaboration processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information can be replaced with: the target sub-agent can perform service collaboration processing with the sub-agent adapted to the interaction information to obtain the service result, and combine it with the remaining steps and / or optional implementation manners provided in this embodiment to form a new embodiment. The specific service collaboration method can be executed with reference to the multiple optional implementation manners and / or combinations of multiple optional implementation manners provided above, and will not be elaborated again in this embodiment.

[0158] In practical applications, the question-and-answer sub-agent and / or the agent can query the knowledge base for a preset reply text that matches the interaction data in the interaction information, and use the preset reply text as the service data and / or a part of the service data to improve the service response efficiency. In an optional implementation manner provided in this embodiment, before performing service collaboration processing, it further includes: querying the knowledge base to determine whether there is a preset reply text that matches the interaction data in the interaction information; if not, no processing is required; if so, obtaining the preset reply text to write the preset reply text into the service result. Optionally, the service result includes the preset reply text obtained by the question-and-answer sub-agent and / or the agent through text matching in the knowledge base based on the interaction data in the interaction information. Further, it can also be detected whether the interaction data is of the cultural and tourism intention category, and the preset reply text query can be performed when the intention category of the interaction data is of the cultural and tourism intention category. The specific implementation method can refer to the implementation method of intention recognition and cultural and tourism intention detection by the server described above.

[0159] Step S506, receiving the service response data generated and sent by the server according to the service result, and displaying it on the cultural and tourism service page.

[0160] Specifically, the service response data is generated by the server according to the processing result generated by the agent, and is sent to the user terminal after being generated. Correspondingly, the service response data is received and the service response data is rendered and displayed on the cultural and tourism service page.

[0161] Among them, the service response data refers to the response data in response to the interaction information sent by the user terminal. The user terminal can display the service response data in the cultural and tourism service, and the service response data can be displayed in the form of messages, rich texts, and / or waistcoats. Optionally, the service response data includes: text data, access addresses, rich texts, and / or configuration information of the agent interface.

[0162] Specifically, in the process of generating service response data, the processing results included in the service result can be classified according to the data type, and the service result can be written into a preset data template according to the data type; in an optional implementation manner provided in this embodiment, generating service response data according to the service result includes: Classify and process the data included in the service result according to the data type to obtain service data corresponding to each data type; Write the classified service data into the data template to obtain service response data.

[0163] In practical applications, the server can pre-store some service elements to generate service response messages according to the service elements. The service result can also include the configuration information of the agent interface of the sub-agent to configure the agent interface in the service response data; in view of this, service response data can be generated according to the service elements and the service result, and the agent interface can be configured in the service response data according to the configuration information of the agent interface in the service result; in an optional implementation manner provided in this embodiment, generating service response data according to the service result includes: Extract the configuration information of the agent interface of the Q&A sub-agent corresponding to the reply text and the candidate interaction text included in the service result, and generate a service response message based on the reply text and / or preset service elements; Configure the agent interface corresponding to the candidate interaction text in the service response message according to the configuration information, and use the configured service response message as the service response data.

[0164] In addition, the service result can also include the access addresses of the sub-services and / or external programs corresponding to the sub-agents. The access addresses can be configured in the text generated by the Q&A sub-agent to generate a rich text as the service response data; in another optional implementation manner provided in this embodiment, generating service response data according to the service result includes: Extract the access addresses of the sub-programs and / or sub-services corresponding to the candidate sub-agents included in the service result and the reply text generated by the Q&A sub-agent; Generate a rich text according to the access address and / or the reply text and use it as the service response data.

[0165] It should be noted that for the two implementation methods of generating service response data based on service results provided above, any one of the implementation methods can be selected for implementation according to actual needs during the specific implementation process. It should be noted that the above two implementation methods can also be combined as a whole according to actual needs, and corresponding technical means can also be selected from the two implementation methods for combination to form a new implementation method. For example, extract the access addresses of the subroutines and / or sub-services corresponding to the candidate sub-agents included in the service result, the reply text generated by the Q&A sub-agent, and the configuration information of the agent interface of the Q&A sub-agent corresponding to the candidate interaction text; according to the access address, generate rich text based on the agent interface and / or reply text corresponding to the candidate interaction text and use it as service response data.

[0166] Based on the service response data generated and sent by the server, the user terminal performs rendering and display processing based on the content included in the service response data. During the specific display process, the service response message can be rendered and displayed according to the service text included in the service response data and the configuration information of the agent interface of the candidate sub-agent; in an optional implementation manner provided in this embodiment, displaying the service response data includes: Parse the service response message included in the service response data to obtain the service text and the configuration information of the agent interface of the candidate sub-agent; Display the service text on the cultural and tourism service page and display the agent interface of the candidate sub-agent on the cultural and tourism service page according to the configuration information.

[0167] Specifically, render and display the service text on the cultural and tourism service page, and the agent interface of the candidate sub-agent can be configured in or outside the service text.

[0168] It should be noted that corresponding to the above-mentioned multiple generation methods of service response data, the user terminal can also perform corresponding rendering and display processing for the above-mentioned multiple service response data. For example, display the rich text sent by the server; or: render the reply text according to the reply text included in the service response data, configure the access addresses of the subroutines and / or sub-services corresponding to the candidate sub-agents included in the service response data in the text areas corresponding to the subroutines and / or sub-services in the reply text, and configure the agent interface in the text area corresponding to the candidate interaction text according to the configuration information of the agent interface of the Q&A sub-agent corresponding to the candidate interaction text.

[0169] In summary, another service processing method based on agents provided in this embodiment can be applied to the user terminal. During the process of the user accessing the cultural and tourism service, the user terminal obtains the interaction information submitted by the agent interface configured on the cultural and tourism service page triggered by the user and sends it to the server, receives the service response data sent by the server and displays it, and improves the user's interaction perception through the service response data; Further, the server invokes an intelligent agent for cultural and tourism services based on the interaction information; among them, the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among multiple configured sub-intelligent agents, and obtains the service result through the collaborative processing of the target sub-intelligent agent and the sub-intelligent agent adapted to the interaction information. The service response efficiency is improved through the way of intelligent agent invocation, and the efficiency and reliability of data processing are enhanced.

[0170] The following takes the application of a service processing method based on an intelligent agent provided in this embodiment in the first interaction scenario as an example, and in combination with Figure 3 , the service processing method based on an intelligent agent provided in this embodiment will be further described. Refer to Figure 3 , the service processing method based on an intelligent agent applied to the first interaction scenario specifically includes the following steps.

[0171] Step S302, call the near-field communication component to establish a near-field communication connection with the near-field communication tag of the cultural and tourism service, and enter the cultural and tourism service page according to the cultural and tourism service access address transmitted by the near-field communication tag.

[0172] Step S304, obtain the interaction information submitted by the user and send it to the server.

[0173] Optionally, the user submits the interaction information by triggering the intelligent agent interface of the question-and-answer sub-intelligent agent configured on the cultural and tourism service page.

[0174] Step S316, receive the service response message and display it on the cultural and tourism service page.

[0175] Step S318, jump to the ticket subroutine according to the trigger instruction submitted by the user touching the ticket purchase link to perform ticket query and / or ticket purchase.

[0176] It should be noted that any one step or any combination of steps among steps S302 to S304 and steps S316 to S318 can be combined with any one step or any combination of the above steps S502 to S506 according to the needs of implementation and deployment; in addition, according to the actual deployment needs, any one or any combination of technical features in steps S302 to S304 and steps S316 to S318 can be selected and combined with any one or more technical features provided in the above steps S502 to S506 to form a new implementation; or, any one or any combination of technical features in steps S302 to S304 and steps S316 to S318 can also be replaced by any one or more technical features provided in the above steps S502 to S506 according to the actual deployment needs to form a new implementation, which will not be elaborated here one by one.

[0177] The following takes the application of an agent-based service processing method provided in this embodiment in the second interaction scenario as an example, and in combination with Figure 4 , the agent-based service processing method provided in this embodiment will be further described. Refer to Figure 4 . The agent-based service processing method applied to the second interaction scenario specifically includes the following steps.

[0178] Step S402: Enter the cultural and tourism service page according to the access address of the cultural and tourism service.

[0179] Optionally, the access address is obtained by the user by entering the access keyword of the cultural and tourism service in the application.

[0180] Step S404: Obtain the interaction information submitted by the intelligent agent interface of the passenger flow sub-intelligent agent triggered by the user on the cultural and tourism service page configuration.

[0181] Step S406: Send the interaction information to the server.

[0182] Step S418: Receive the rich text and display it on the cultural and tourism service page.

[0183] Step S420: Obtain the target reply text submitted by the intelligent agent interface corresponding to the target reply text in the rich text triggered by the user and send it to the server.

[0184] Step S424: Receive the interaction text and display it on the cultural and tourism service page.

[0185] It should be noted that any one step or any combination of steps S404 to S406, steps S418 to S420, and steps S424 can be combined with any one step or any combination of the above steps S502 to S506 according to the needs of implementation deployment; in addition, according to the actual deployment needs, any one or any combination of technical features in steps S404 to S406, steps S418 to S420, and steps S424 can be selected and combined with any one or more technical features provided by the above steps S502 to S506 to form a new implementation method; or, any one or any combination of technical features in steps S404 to S406, steps S418 to S420, and steps S424 can also be replaced by any one or more technical feature combinations provided by the above steps S502 to S506 according to the actual deployment needs to form a new implementation method, which will not be elaborated here one by one.

[0186] The following is an embodiment of an agent-based service processing device provided in this specification: In the above embodiments, an agent-based service processing method is provided. Correspondingly, an agent-based service processing device is also provided, which will be described below with reference to the accompanying drawings.

[0187] Referring to Figure 6 , which shows a schematic diagram of an embodiment of an agent-based service processing device provided in this embodiment.

[0188] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiments described below are only illustrative.

[0189] This embodiment provides an agent-based service processing device, including: An interaction information receiving module 602, configured to receive interaction information submitted by a user terminal after an agent interface configured for a cultural and tourism service is triggered; the cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. An agent calling module 604, configured to perform agent calling for the cultural and tourism service based on the interaction information; the agent determines a target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, service collaboration processing is performed with a sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result. A service response data sending module 606, configured to generate service response data according to the service result and send it to the user terminal.

[0190] Another embodiment of the agent-based service processing device provided in this specification is as follows: In the above embodiments, another agent-based service processing method is provided. Correspondingly, another agent-based service processing device is also provided, which will be described below with reference to the accompanying drawings.

[0191] Referring to Figure 7 , which shows a schematic diagram of an embodiment of an agent-based service processing device provided in this embodiment.

[0192] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiments described below are only illustrative.

[0193] This embodiment provides an agent-based service processing device, and the device includes: An interaction information acquisition module 702, configured to acquire interaction information submitted after a user triggers an intelligent agent interface for cultural and tourism service configuration; the cultural and tourism service enters after performing near-field communication interaction with a near-field communication tag. An interaction information sending module 704, configured to send the interaction information to a server, so that the server invokes an intelligent agent for the cultural and tourism service based on the interaction information; the intelligent agent determines a target sub-intelligent agent corresponding to the interaction information among a plurality of configured sub-intelligent agents, and if the target sub-intelligent agent is a question-and-answer sub-intelligent agent, a service result is obtained through service collaborative processing between the question-and-answer sub-intelligent agent and a sub-intelligent agent adapted to the interaction information. A service response data display module 706, configured to receive service response data generated and sent by the server according to the service result and display it on a cultural and tourism service page.

[0194] An embodiment of a service processing device based on an intelligent agent provided in this specification is as follows: Corresponding to the above-described service processing method based on an intelligent agent, based on the same technical concept, one or more embodiments of this specification also provide a service processing device based on an intelligent agent, and this service processing device based on an intelligent agent is used to execute the above-provided service processing method based on an intelligent agent. Figure 8 It is a schematic structural diagram of a service processing device based on an intelligent agent provided by one or more embodiments of this specification.

[0195] A service processing device based on an intelligent agent provided in this embodiment includes: As Figure 8 shown, the service processing device based on an intelligent agent may vary greatly due to configuration or performance differences, and may include one or more processors 801 and a memory 802. One or more application programs or data may be stored in the memory 802. Among them, the memory 802 may be short-term storage or persistent storage. The application programs stored in the memory 802 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the service processing device based on an intelligent agent. Further, the processor 801 may be set to communicate with the memory 802 and execute a series of computer-executable instructions in the memory 802 on the service processing device based on an intelligent agent. The service processing device based on an intelligent agent may also include one or more power supplies 803, one or more wired or wireless network interfaces 804, one or more input / output interfaces 805, one or more keyboards 806, etc.

[0196] In a specific embodiment, the agent-based service processing device includes a memory and one or more programs, where one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in the agent-based service processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Receiving interaction information submitted by the user terminal after the agent interface configured for the cultural and tourism service is triggered; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Invoking the agent of the cultural and tourism service based on the interaction information; the agent determines the target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, the service result is obtained through service collaboration processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information; Generating service response data according to the service result and sending it to the user terminal.

[0197] Another embodiment of the agent-based service processing device provided in this specification is as follows: Corresponding to the above-described another agent-based service processing method, based on the same technical concept, one or more embodiments of this specification also provide another agent-based service processing device. This agent-based service processing device is used to execute the above-provided another agent-based service processing method. Figure 9 It is a schematic structural diagram of another agent-based service processing device provided by one or more embodiments of this specification.

[0198] An agent-based service processing device provided in this embodiment includes: Such as Figure 9As shown, the agent-based service processing device can vary greatly due to different configurations or performances, and may include one or more processors 901 and a memory 902. One or more storage application programs or data can be stored in the memory 902. Among them, the memory 902 can be short-term storage or persistent storage. The application programs stored in the memory 902 can include one or more modules (not shown in the figure), and each module can include a series of computer-executable instructions in the agent-based service processing device. Further, the processor 901 can be set to communicate with the memory 902 and execute a series of computer-executable instructions in the memory 902 on the agent-based service processing device. The agent-based service processing device can also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input / output interfaces 905, one or more keyboards 906, etc.

[0199] In a specific embodiment, the agent-based service processing device includes a memory and one or more programs, where one or more programs are stored in the memory, and one or more programs can include one or more modules, and each module can include a series of computer-executable instructions in the agent-based service processing device, and is configured to execute the one or more programs by one or more processors, and the one or more programs include the following computer-executable instructions for: Obtain the interaction information submitted after the user triggers the agent interface for configuring the cultural and tourism service; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Send the interaction information to the server so that the server can perform agent invocation of the cultural and tourism service based on the interaction information; the agent determines the target sub-agent corresponding to the interaction information among the configured multiple sub-agents. If the target sub-agent is a question-and-answer sub-agent, the service result is obtained through service collaboration processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information; Receive the service response data generated and sent by the server according to the service result and display it on the cultural and tourism service page.

[0200] An embodiment of a computer-readable storage medium provided in this specification is as follows: Corresponding to the above-described agent-based service processing method, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0201] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, and the computer-executable instructions, when executed, implement the following process: Receive the interaction information submitted by the user terminal after the intelligent agent interface configured for the cultural and tourism service is triggered; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Perform intelligent agent invocation of the cultural and tourism service based on the interaction information; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among multiple configured sub-intelligent agents. If the target sub-intelligent agent is a question-and-answer sub-intelligent agent, obtain a service result through service collaborative processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information; Generate service response data according to the service result and send it to the user terminal.

[0202] It should be noted that the embodiment of a computer-readable storage medium in this specification and the embodiment of a service processing method based on an intelligent agent in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding method described above, and the repeated parts will not be elaborated.

[0203] Another embodiment of the computer-readable storage medium provided in this specification is as follows: Corresponding to the above-described another service processing method based on an intelligent agent, based on the same technical concept, one or more embodiments of this specification also provide another computer-readable storage medium.

[0204] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, and the computer-executable instructions, when executed, implement the following processes: Obtain the interaction information submitted by the user after triggering the intelligent agent interface configured for the cultural and tourism service; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Send the interaction information to the server so that the server performs intelligent agent invocation of the cultural and tourism service based on the interaction information; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information among multiple configured sub-intelligent agents. If the target sub-intelligent agent is a question-and-answer sub-intelligent agent, obtain a service result through service collaborative processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information; Receive the service response data generated and sent by the server according to the service result and display it on the cultural and tourism service page.

[0205] It should be noted that the embodiment of another computer-readable storage medium in this specification and the embodiment of another service processing method based on an intelligent agent in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding method described above, and the repeated parts will not be elaborated.

[0206] An embodiment of a computer program product provided in this specification is as follows: Corresponding to the agent-based service processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0207] A computer program product includes computer programs / instructions, and when the computer programs / instructions are executed by a processor, the following steps are implemented: Receive the interaction information submitted by the user terminal after the agent interface configured for the cultural and tourism service is triggered; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Perform agent invocation of the cultural and tourism service based on the interaction information; the agent determines the target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, perform service collaborative processing with the sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result; Generate service response data according to the service result and send it to the user terminal.

[0208] It should be noted that the embodiments of a computer program product in this specification and the embodiments of an agent-based service processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding method described above, and the repeated parts will not be elaborated.

[0209] Another embodiment of the computer program product provided in this specification is as follows: Corresponding to another agent-based service processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another computer program product.

[0210] A computer program product includes computer programs / instructions, and when the computer programs / instructions are executed by a processor, the following steps are implemented: Obtain the interaction information submitted by the user after triggering the agent interface configured for the cultural and tourism service; the cultural and tourism service enters after performing near-field communication interaction with the near-field communication tag; Send the interaction information to the server so that the server performs agent invocation of the cultural and tourism service based on the interaction information; the agent determines the target sub-agent corresponding to the interaction information among multiple configured sub-agents. If the target sub-agent is a question-and-answer sub-agent, perform service collaborative processing with the sub-agent adapted to the interaction information through the question-and-answer sub-agent to obtain a service result; Receive the service response data generated and sent by the server according to the service result and display it on the cultural and tourism service page.

[0211] It should be noted that the embodiments of another computer program product in this specification and the embodiments of another agent-based service processing method in this specification are based on the same inventive concept. Therefore, for the specific implementation of this embodiment, reference may be made to the implementation of the corresponding method described above, and repeated parts will not be elaborated.

[0212] The various embodiments in this specification are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. For example, the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments are all similar to the method embodiments, so the descriptions are relatively simple. To read the relevant content in the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments, please refer to the corresponding part of the method embodiments.

[0213] The specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0214] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one type of HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing some logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0215] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0216] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0217] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0218] Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0219] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable agent-based service processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable agent-based service processing devices generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0220] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable agent-based service processing device to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0221] These computer program instructions can also be loaded onto a computer or other programmable agent-based service processing device, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0222] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0223] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0224] A computer-readable medium includes permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0225] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising at least one..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0226] One or more embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0227] The above are only embodiments of this document and are not used to limit this document. For those skilled in the art, this document can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this document shall be included within the scope of the claims of this document.

Claims

1. A service processing method based on an agent, comprising: Receiving interaction information submitted by the user terminal after the intelligent agent interface configured by the cultural and tourism service is triggered; The cultural tourism service is entered after near field communication interaction with the near field communication tag; Based on the interaction information, the intelligent agent of the cultural tourism service is called; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information from the configured multiple sub-intelligent agents, and if the target sub-intelligent agent is a question-and-answer sub-intelligent agent, the service result is obtained by performing service collaborative processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information; Generate service response data according to the service result and send it to the user terminal.

2. According to the agent-based service processing method of claim 1, the cultural and tourism service is entered in the following manner: The access data transmitted by the near field communication tag is parsed to obtain the access address of the cultural travel service, and the cultural travel service is entered based on the access address.

3. According to the agent-based service processing method of claim 1, the step of obtaining a service result by performing service collaborative processing between the question-answering sub-agent and the sub-agent adapted to the interactive information comprises: Selecting a candidate sub-agent adapted to the interaction data according to the interaction data included in the interaction information, and determining a service collaboration mode between the question-and-answer sub-agent and the candidate sub-agent; The service result is obtained by performing service collaborative processing according to the service collaborative method.

4. According to the agent-based service processing method of claim 3, the step of performing service collaborative processing in accordance with the service collaborative mode to obtain the service result comprises: The question-answering sub-agent inputs the interaction data in the interaction information into the large language model for data processing to generate service data, and extracts regional keywords contained in the service data; Based on the area keyword, the candidate sub-agent is called to perform service processing to obtain area information, and the service data, the area information and the configuration information of the agent interface of the candidate sub-agent are used as the service result.

5. According to the agent-based service processing method of claim 3, the step of performing service collaborative processing in accordance with the service collaborative mode to obtain the service result comprises: The candidate sub-agent performs service processing based on the interaction information to obtain the access address of the sub-service corresponding to the candidate sub-agent; The question-and-answer sub-agent generates service data according to the access address and uses the access address and the service data as the service result.

6. The agent-based service processing method according to claim 3, wherein the step of obtaining a service result by performing service collaborative processing between the question-answering sub-agent and the sub-agent adapted to the interactive information comprises: The intelligent agent performs intent recognition and keyword extraction on the interaction data in the interaction information to obtain a plurality of keywords corresponding to each intent category; Input each keyword into the candidate sub-agent corresponding to the intention category for service processing, and obtain the processing result and the service data generated by the question-answering sub-agent; The service result is obtained by aggregating the service data, the processing result and the configuration information of the agent interface of the candidate sub-agent.

7. The agent-based service processing method according to claim 1, after determining the target sub-agent operation corresponding to the interaction information among the configured multiple sub-agents, further comprising: If the target sub-agent is a candidate sub-agent, the service result is obtained by performing service collaborative processing between the candidate sub-agent and the question-and-answer sub-agent.

8. The agent-based service processing method according to claim 7, wherein the step of obtaining a service result by performing service collaborative processing between the candidate sub-agent and the question-answering sub-agent comprises: The agent calls the candidate sub-agent to perform service processing to obtain the access address of the subroutine corresponding to the candidate sub-agent, and searches the knowledge base for the candidate interaction text preset by the candidate sub-agent; Generate an agent interface for the question-and-answer sub-agent corresponding to the candidate interaction text, input the agent information of the candidate sub-agent into the question-and-answer sub-agent to generate a service text, and generate a service result based on the configuration information of the agent interface corresponding to the candidate interaction text and the service text.

9. According to the agent-based service processing method of claim 1, before the step of receiving the interactive information submitted by the user terminal after the agent interface configured on the cultural and tourism service page is triggered, the method further comprises: Obtaining encrypted access data submitted by the user terminal calling the data transmission interface of the cultural and tourism service; The data transmission interface is obtained by parsing the encrypted access data transmitted by the near field communication tag; The encrypted access data is decrypted to obtain an access instruction for the cultural and travel service page, and the cultural and travel service page is sent to the user terminal in response to the access instruction.

10. The agent-based service processing method according to claim 1, wherein generating service response data according to the service result comprises: Classify the data contained in the service result according to the data type to obtain service data corresponding to each data type; The classified service data is written into the data template to obtain the service response data.

11. The agent-based service processing method according to claim 1, after the operation of determining the target sub-agent corresponding to the interaction information among the configured multiple sub-agents is executed, and before the operation of obtaining the service result by performing service collaborative processing by the question-and-answer sub-agent and the sub-agent adapted to the interaction information, further comprising: Querying in the knowledge base whether there is a preset reply text matching the interaction data in the interaction information; If it exists, obtain the preset reply text to write the preset reply text into the service result.

12. The agent-based service processing method according to claim 3, wherein the step of performing service collaborative processing in accordance with the service collaborative mode to obtain the service result comprises: The agent extracts keywords from the interactive information to obtain ticket keywords, and inputs the ticket keywords into the ticket sub-agent to perform ticket information query to obtain ticket information; The ticket information is obtained by inquiring through a data query interface of a ticket subroutine by taking the ticket keyword as input data; The ticket information and the interaction information are input into the question-and-answer sub-agent to generate text to obtain a service text, and the ticket information, the service text and the access address of the ticket subroutine are used as the service result.

13. The agent-based service processing method according to claim 3, wherein generating service response data according to the service result comprises: Extracting the reply text contained in the service result and the configuration information of the agent interface of the question-answering sub-agent corresponding to the candidate interaction text, and generating a service response message based on the reply text and the preset service element; The agent interface corresponding to the candidate interaction text is configured in the service response message according to the configuration information, and the configured service response message is used as the service response data.

14. The agent-based service processing method according to claim 6, wherein generating service response data according to the service result comprises: Extracting the access address of the subroutine corresponding to the candidate sub-agent contained in the service result and the reply text generated by the question-and-answer sub-agent; Rich text is generated according to the access address and the reply text as the service response data.

15. A service processing method based on an agent, comprising: Obtain the interaction information submitted by the user after triggering the intelligent agent interface configured for cultural and tourism services; The cultural tourism service is entered after near field communication interaction with the near field communication tag; The interaction information is sent to a server so that the server calls an agent for cultural and tourism services based on the interaction information; the agent determines a target sub-agent corresponding to the interaction information from among multiple configured sub-agents, and if the target sub-agent is a question-and-answer sub-agent, the question-and-answer sub-agent performs service collaborative processing with a sub-agent adapted to the interaction information to obtain a service result; Receive the service response data generated and sent by the server according to the service result, and display it on the cultural and tourism service page.

16. According to the agent-based service processing method of claim 15, before the step of obtaining the interactive information submitted by the user after triggering the agent interface of the cultural and tourism service configuration is executed, it also includes: Calling a near field communication component to perform near field communication interaction with the near field communication tag to obtain encrypted access data transmitted by the near field communication tag; Parsing the encrypted access data to obtain the data transmission interface of the cultural and travel service, and using the encrypted access data as an interface call input to call the data transmission interface; Receive and display the cultural and tourism service page sent by the server.

17. According to the agent-based service processing method of claim 15, the cultural and tourism service page is entered in the following manner: The access data transmitted by the near field communication tag is parsed to obtain the access address of the cultural and travel service page, and the cultural and travel service page is entered based on the access address.

18. According to the agent-based service processing method of claim 15, the service response data is displayed in the following manner: Parsing the service response message included in the service response data to obtain the service text and the configuration information of the agent interface of the candidate sub-agent; The service text is displayed on the cultural and tourism service page and the agent interface of the candidate sub-agent is displayed on the cultural and tourism service page according to the configuration information.

19. The agent-based service processing method according to claim 15, after the step of receiving the service response data generated and sent by the server according to the service result and displaying it on the cultural and tourism service page is performed, it also includes: Obtain the target interaction text submitted by the agent interface of the question-and-answer sub-agent corresponding to the target interaction text configured on the cultural and tourism service page triggered by the user; Sending the target interactive text to the server, and receiving the rich text obtained by the server through calling the intelligent agent of the cultural and tourism service; The rich text is displayed on the cultural and tourism service page.

20. A service processing device based on an intelligent agent, comprising: An interactive information receiving module is configured to receive interactive information submitted by a user terminal after an intelligent agent interface configured by a cultural and tourism service is triggered; The cultural tourism service is entered after near field communication interaction with the near field communication tag; An agent calling module is configured to call an agent of the cultural tourism service based on the interaction information; the agent determines a target sub-agent corresponding to the interaction information from among multiple configured sub-agents, and if the target sub-agent is a question-and-answer sub-agent, the service result is obtained by performing service collaborative processing between the question-and-answer sub-agent and the sub-agent adapted to the interaction information; The service response data sending module is configured to generate service response data according to the service result and send it to the user terminal.

21. A service processing device based on an intelligent agent, comprising: An interaction information acquisition module is configured to acquire interaction information submitted by a user after triggering an intelligent agent interface configured for a cultural tourism service; The cultural tourism service is entered after near field communication interaction with the near field communication tag; The interactive information sending module is configured to send the interactive information to the server so that the server can call the intelligent agent of the cultural and tourism service based on the interactive information; the intelligent agent determines the target sub-intelligent agent corresponding to the interactive information from the configured multiple sub-intelligent agents, and if the target sub-intelligent agent is a question-and-answer sub-intelligent agent, the service result is obtained by performing service collaborative processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interactive information; The service response data display module is configured to receive the service response data generated and sent by the server according to the service result, and display it on the cultural and tourism service page.

22. A service processing device based on an intelligent agent, comprising: processor; and a memory configured to store computer executable instructions that, when executed, cause the processor to: Receiving interaction information submitted by a user terminal after an intelligent agent interface configured by a cultural and travel service is triggered; the cultural and travel service is entered after near field communication interaction with a near field communication tag; Based on the interaction information, the intelligent agent of the cultural tourism service is called; the intelligent agent determines the target sub-intelligent agent corresponding to the interaction information from the configured multiple sub-intelligent agents, and if the target sub-intelligent agent is a question-and-answer sub-intelligent agent, the service result is obtained by performing service collaborative processing between the question-and-answer sub-intelligent agent and the sub-intelligent agent adapted to the interaction information; Generate service response data according to the service result and send it to the user terminal.

23. A service processing device based on an intelligent agent, comprising: processor; and a memory configured to store computer executable instructions that, when executed, cause the processor to: Acquiring interaction information submitted by a user after triggering an intelligent agent interface configured for a cultural travel service; the cultural travel service is entered after near field communication interaction with a near field communication tag; The interaction information is sent to a server so that the server calls an agent for cultural and tourism services based on the interaction information; the agent determines a target sub-agent corresponding to the interaction information from among multiple configured sub-agents, and if the target sub-agent is a question-and-answer sub-agent, the question-and-answer sub-agent performs service collaborative processing with a sub-agent adapted to the interaction information to obtain a service result; Receive the service response data generated and sent by the server according to the service result, and display it on the cultural and tourism service page.

24. A computer-readable storage medium for storing computer-executable instructions, which implement the steps of the method of claim 1 or 15 when executed.

Images