Intelligent agent-based health question and answer interaction method and device, electronic device, and storage medium

Abstract

The present disclosure provides an agent-based health question and answer interaction method and device, electronic equipment and storage medium, which are related to the technical fields of artificial intelligence, smart medical treatment, intelligent customer service, smart marketing and the like. The agent-based health question and answer interaction method comprises: displaying an interaction page; in the process of carrying out a conversation with a target object based on the interaction page, using a first agent to identify a conversation stage attribute represented by conversation content, and using a second agent to process the conversation content according to a conversation strategy matched with the conversation stage attribute to obtain target reply information, the conversation strategy indicating that a guide prompt information is determined to prompt the target object to input health-related information, or the conversation strategy indicating that a health suggestion scheme is determined according to the conversation content, the target reply information comprising at least one of the guide prompt information and the health suggestion scheme; and in the case where the conversation stage attribute indicates that a scheme reply condition is met, displaying the health suggestion scheme determined by the second agent.

Description

Technical Field

[0001] This disclosure relates to the technical fields of artificial intelligence, smart healthcare, intelligent customer service, and smart marketing. More specifically, it relates to a health question-and-answer interaction method, device, electronic device, and storage medium based on intelligent agents. Background Technology

[0002] With the rapid development of technology, users can conveniently browse and purchase the products they need through smartphones and other terminal devices. Furthermore, users can also use these devices to communicate with customer service personnel from merchants or online platforms to meet their specific needs.

[0003] In realizing the present invention, the inventors discovered that the related technology has at least the following problems: in the process of dialogue with users, multiple rounds of question and answer are usually required to understand the user's needs, making it difficult to output information that meets the user's needs in a timely and effective manner, which affects the user experience. Summary of the Invention

[0004] In view of this, the present disclosure provides a health question-and-answer interaction method, device, electronic device and storage medium based on intelligent agents.

[0005] One aspect of this disclosure provides an agent-based health question-and-answer interaction method, comprising: displaying an interaction page; during a dialogue with a target object based on the interaction page, using a first agent to identify dialogue stage attributes represented by the dialogue content, and using a second agent to process the dialogue content according to a dialogue strategy matching the dialogue stage attributes to obtain target response information, wherein the dialogue strategy indicates prompting the target object to input health-related information by determining guidance prompts, or the dialogue strategy indicates determining a health suggestion scheme based on the dialogue content, and the target response information includes at least one of the guidance prompts and the health suggestion scheme; and displaying the health suggestion scheme determined by the second agent when the dialogue stage attributes meet the scheme response conditions.

[0006] According to embodiments of this disclosure, the agent-based health question-and-answer interaction method further includes: using an intent-recognition agent to process dialogue content to obtain the target object's demand intent, wherein a first agent, based on the demand intent, selects a second agent from multiple candidate agents that matches the demand intent to process the dialogue content according to a dialogue strategy, and outputs target response information to satisfy the demand intent.

[0007] According to embodiments of this disclosure, the method of using a first intelligent agent to identify dialogue stage attributes represented by dialogue content includes: using the first intelligent agent to process dialogue content according to the target emotional intent to obtain dialogue end stage attributes that indicate the satisfaction of the solution response conditions, wherein the demand intent includes the target emotional intent; and a second intelligent agent to process dialogue content according to the target emotional intent and output a health suggestion solution, wherein the target emotional intent represents at least one of the following emotional attributes: eagerness for symptom information or products related to symptom information; and negative emotion for guidance prompts.

[0008] According to embodiments of this disclosure, the demand intent includes at least one of the following: symptom information consultation intent, consultation intent for products related to symptom information, and disease information consultation intent.

[0009] According to embodiments of this disclosure, identifying dialogue stage attributes represented by dialogue content using a first intelligent agent includes: using the first intelligent agent to perform the following operations: performing a target task based on the demand intent represented by the dialogue content, and determining symptom and product demand information related to the demand intent; determining a guidance stage attribute or a solution generation stage attribute based on the difference information between the dialogue content and the symptom and the product demand information, wherein the guidance stage attribute is used to prompt a second intelligent agent to output guidance prompt information, and the solution generation stage attribute is used to prompt the second intelligent agent to output a health suggestion solution.

[0010] According to an embodiment of this disclosure, a first agent calls a second agent from among multiple candidate agents that corresponds to the guidance phase attributes and demand intent to process the dialogue content and obtain guidance prompt information. The guidance prompt information is used to prompt the target object to input health-related information related to the difference information.

[0011] According to embodiments of this disclosure, a second agent is used to process dialogue content based on a dialogue strategy that matches the attributes of the dialogue stage, including: using a second agent from among multiple candidate agents that corresponds to the attributes of the solution generation stage to analyze health-related information and guidance prompts in the dialogue content, and outputting a health suggestion solution.

[0012] According to embodiments of this disclosure, the agent-based health question-and-answer interaction method further includes: when the demand intent is the target demand intent, invoking a dialogue agent corresponding to the target demand intent to engage in dialogue with the target object, wherein the semantic difference between the target demand intent and the preset health demand intent satisfies a preset difference condition.

[0013] According to embodiments of this disclosure, the health recommendation scheme includes at least one of the following: recommended products that match health-related information; descriptive information describing the conditions of use of the recommended products; and document explanation information for interpreting the target document, wherein the dialogue content includes the target document.

[0014] Another aspect of this disclosure provides a health question-and-answer interaction device based on an intelligent agent, comprising: a first display module for displaying an interactive page; a target response information acquisition module for, during a dialogue with a target object based on the interactive page, using a first intelligent agent to identify dialogue stage attributes represented by the dialogue content, and using a second intelligent agent to process the dialogue content according to a dialogue strategy matching the dialogue stage attributes, to obtain target response information, wherein the dialogue strategy indicates prompting the target object to input health-related information by determining guidance prompts, or the dialogue strategy indicates determining a health suggestion scheme based on the dialogue content, and the target response information includes at least one of guidance prompts and a health suggestion scheme; and a second display module for displaying the health suggestion scheme determined by the second intelligent agent when the dialogue stage attributes indicate that the scheme response conditions are met.

[0015] Another aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described above.

[0016] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0017] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, are used to implement the method described above.

[0018] According to embodiments of this disclosure, during a dialogue with a target, a first agent identifies the dialogue stage attributes based on the dialogue content. This allows a second agent to flexibly adjust its dialogue strategy based on the dialogue stage attributes and output guiding prompts or health advice. This ensures that health advice is displayed promptly when the dialogue stage attributes meet the response conditions, avoiding excessive waiting time for users to respond to multiple rounds of follow-up questions. This multi-agent collaboration enables timely output of health advice during the dialogue, preventing excessive waiting time for suggestions regarding symptom information and other health-related content, thus improving the user experience. Attached Figure Description

[0019] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1The illustration schematically depicts an exemplary system architecture for applying agent-based health question-and-answer interaction methods and devices according to embodiments of the present disclosure.

[0021] Figure 2 A flowchart illustrating an agent-based health question-and-answer interaction method according to an embodiment of the present disclosure is shown.

[0022] Figure 3 The diagram illustrates an application scenario of the agent-based health question-and-answer interaction method according to an embodiment of the present disclosure.

[0023] Figure 4 A flowchart illustrating an agent-based health question-and-answer interaction method according to another embodiment of the present disclosure is shown.

[0024] Figure 5 A block diagram of an agent-based health question-and-answer interaction device according to an embodiment of the present disclosure is shown schematically.

[0025] Figure 6 A block diagram of an electronic device suitable for implementing an agent-based health question-and-answer interaction method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0026] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0027] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0028] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0029] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0030] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security and network security.

[0031] In the embodiments disclosed herein, user authorization or consent is obtained before acquiring or collecting user personal information.

[0032] The inventors discovered that in dialogue interactions between intelligent agents and users, the agent typically needs to engage in multiple rounds of conversation to collect detailed needs information in order to output accurate recommendations. For example, in a Q&A scenario involving medical products, the agent needs to prompt the user to input detailed needs and symptoms based on the product's usage information. This allows the agent to generate a comprehensive and accurate product usage recommendation based on the relatively complete information provided by the user. This results in a high frequency of interaction with the target audience during the Q&A process, and users may not receive a solution from the agent even when they urgently need to purchase the product or are feeling frustrated, thus negatively impacting the user experience.

[0033] Embodiments of this disclosure provide a health question-and-answer interaction method, apparatus, electronic device, and storage medium based on intelligent agents. The health question-and-answer interaction method based on intelligent agents includes: displaying an interactive page; during a dialogue with a target object based on the interactive page, using a first intelligent agent to identify dialogue stage attributes represented by the dialogue content, and using a second intelligent agent to process the dialogue content according to a dialogue strategy matching the dialogue stage attributes to obtain target response information. The dialogue strategy indicates either prompting the target object to input health-related information by determining guidance prompts, or determining a health suggestion plan based on the dialogue content. The target response information includes at least one of the guidance prompts and the health suggestion plan; when the dialogue stage attributes indicate that the response conditions are met, displaying the health suggestion plan determined by the second intelligent agent.

[0034] Figure 1This illustration schematically depicts an exemplary system architecture for applying an agent-based health question-and-answer interaction method and apparatus according to embodiments of this disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0035] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0036] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software, etc. (for example only).

[0037] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0038] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0039] It should be noted that the agent-based health question-and-answer interaction method provided in this embodiment can generally be executed by server 105. Correspondingly, the agent-based health question-and-answer interaction device provided in this embodiment can generally be located in server 105. The agent-based health question-and-answer interaction method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the agent-based health question-and-answer interaction device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Alternatively, the agent-based health question-and-answer interaction method provided in this embodiment can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the health question-and-answer interaction device based on intelligent agents provided in this embodiment can also be set in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0040] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0041] Figure 2 A flowchart illustrating an agent-based health question-and-answer interaction method according to an embodiment of the present disclosure is shown.

[0042] like Figure 2 As shown, the agent-based health question-and-answer interaction method includes operations S210~S230.

[0043] When operating S210, the interactive page is displayed.

[0044] During operation S220, in the process of having a dialogue with the target object based on the interactive page, the first agent is used to identify the dialogue stage attributes represented by the dialogue content, and the second agent is used to process the dialogue content according to the dialogue strategy that matches the dialogue stage attributes to obtain the target response information.

[0045] In operation S230, if the attribute indication in the dialogue phase meets the response conditions, the health recommendation plan determined by the second agent is displayed.

[0046] According to embodiments of this disclosure, the interactive page can be a page for dialogue between a target object and an intelligent agent, such as a customer service page for dialogue with a user. However, it is not limited to this; the interactive page can also be any type of page such as a product collection page or a product details page. Embodiments of this disclosure do not limit the specific page type of the interactive page.

[0047] In some embodiments, the target object inputs text, images, or other modal input information into a dialog box on the interactive page. The agent processes the input information and the dialogue content during the conversation to output the target object's response, thereby enabling the agent to engage in dialogue with the target object.

[0048] According to embodiments of this disclosure, an intelligent agent can be a software entity that uses generative task execution capabilities based on a large language model to engage in conversational interactions with users in scenarios such as medical information Q&A and e-commerce after-sales consultation. The intelligent agent can use task planning capabilities to plan tasks to be executed from information of any modality, such as natural language text, and schedule any service resources from large models and retrieval tools to execute the tasks, thereby outputting feedback information that satisfies the intent of the target object. The intelligent agent can output data of any modality, such as text, images, and page links; embodiments of this disclosure do not limit the modal type of the information output by the intelligent agent.

[0049] It should be noted that the intelligent agents involved in the embodiments of this disclosure, including but not limited to the first intelligent agent and the second intelligent agent, can all be constructed based on the generative task execution capabilities of large language models. The embodiments of this disclosure will not be described in detail here.

[0050] In some embodiments, the first agent and the second agent can be two different agents with different capabilities. The first agent may have the ability to determine the dialogue stage attribute; for example, the first agent may determine that the current dialogue content indicates a dialogue stage attribute that is to end the dialogue and output a health suggestion. The second agent may be an agent with dialogue capabilities. Using the second agent to process the target object's input information and contextual content, and output target response information, can improve the information quality of the target response information displayed to the target object during the dialogue, thereby enhancing the target object's interactive experience.

[0051] According to embodiments of this disclosure, the dialogue stage attribute represents the dialogue development stage characterized by the current dialogue content. For example, the dialogue stage attribute can represent the complete information gathering stage, the dialogue end stage, or the solution response stage where information gathering is completed and a health advice solution is output.

[0052] According to embodiments of this disclosure, the dialogue strategy refers to prompting the target object to input health-related information by determining guidance prompts, or the dialogue strategy refers to determining a health recommendation plan based on the dialogue content.

[0053] Guiding prompts are used to prompt the target user to input the information needed to generate a health recommendation plan. For example, guiding prompts could be "Where is the pain located?" or "How long has the pain lasted?". Thus, the target user can input the health-related information that the second agent needs to understand by browsing the guiding prompts displayed on the interactive page during the dialogue. This allows the second agent to output a more complete and accurate health recommendation plan based on the health-related information input by the target user during the dialogue.

[0054] According to embodiments of this disclosure, a health advice solution can be a response to the health needs of a target audience in a dialogue. The health advice solution may include text information such as a description of the drug's function, instructions for use, and the name of the relevant department for which appointments are required. The health advice solution may also include product links to health-related products and services. Embodiments of this disclosure do not limit the specific types of information included in the health advice solution.

[0055] It should be understood that the target response information can be information displayed on the interactive page. Target response information includes at least one of guided prompts and health advice solutions. For example, if the dialogue stage attribute indicates a complete information collection stage, the target response information that can be displayed could be guided prompts to prompt the target user to input health-related information. As another example, if the dialogue stage attribute indicates a solution response stage where the solution response conditions are met, the displayed target response information would be a health advice solution.

[0056] In some embodiments, the dialogue content includes target response information already displayed on the interactive page, as well as health-related information or other input information entered by the target object.

[0057] According to embodiments of this disclosure, a first intelligent agent can perform semantic understanding of the dialogue content to determine whether the information contained in the dialogue content can generate a health suggestion plan that meets the needs of the target object, and output a dialogue stage attribute accordingly. Alternatively, the first intelligent agent can also determine whether to output a dialogue stage attribute indicating that the response conditions of the suggestion plan are met by understanding the intent of the target object in the dialogue content. Therefore, by using the first intelligent agent to output dialogue stage attributes indicating that the response conditions of the suggestion plan are met, the timing of outputting a health suggestion plan can be more accurately identified, and a second intelligent agent can be promptly invoked according to the corresponding dialogue strategy to output a health suggestion plan based on the dialogue stage attribute, thus avoiding excessively long waiting times for the health suggestion plan by the target object, which could negatively impact the user experience.

[0058] According to embodiments of this disclosure, the health recommendation scheme includes at least one of the following: recommended products that match health-related information; descriptive information describing the conditions of use of the recommended products; and document explanation information for interpreting the target document, wherein the dialogue content includes the target document.

[0059] In some examples, recommended products may include physical products such as health supplements that meet the target audience's health needs, or service products such as rehabilitation appointment services that meet the target audience's related needs. The second intelligent agent understands the intended needs expressed in the dialogue content to output recommended products that can meet the target audience's actual needs, thereby reducing the number of operations the target audience needs to perform to query product resources, reducing the frequency of operations, and improving the interactive experience.

[0060] In some examples, the descriptive information may include details about the product's usage cycle, dosage per use, and precautions. By displaying descriptive information within the health advice plan, the target audience can more accurately use recommended products such as health supplements and rehabilitation products, thereby reducing the frequency of interaction required for the target audience to query the usage conditions of related products and improving the user experience.

[0061] In some examples, the target file can be a health check report, laboratory report, or similar document related to the target object. Document explanation information can be used to summarize the precautions and examination conclusions in the target file, allowing the target object to understand its content. The target object can copy or upload the target file to the file transfer component of the dialogue page, enabling the second agent to understand the target file within the dialogue content.

[0062] According to embodiments of this disclosure, by utilizing a first intelligent agent to identify the dialogue stage attributes represented by the dialogue content, and invoking a second intelligent agent to output guiding prompts or health advice based on the dialogue strategy corresponding to the dialogue stage attributes, it is possible to accurately identify the dialogue method with the target object and output target response information that can more accurately meet the actual needs and intentions of the target object through the collaboration of multiple intelligent agents. This allows for more precise output of the health advice content needed by the target object, avoiding excessive waiting time for the target object due to too many dialogue interaction rounds caused by limitations in the understanding capabilities of the intelligent agents. Simultaneously, it avoids reduced accuracy and completeness of health advice due to misunderstandings of health-related information. Therefore, the quality of dialogue with the target object is improved and the interactive experience is enhanced through multi-agent collaboration.

[0063] According to embodiments of this disclosure, the agent-based health question-and-answer interaction method may further include: using an intent-recognition agent to process dialogue content and obtain the target object's demand intent.

[0064] According to embodiments of this disclosure, the demand intent can include any type of demand intent such as the target object's intent to consult about a disease or a product. Based on the demand intent, a first intelligent agent selects a second intelligent agent from a pool of candidate intelligent agents that matches the demand intent. The second intelligent agent then processes the dialogue content according to a dialogue strategy and outputs target response information to satisfy the demand intent.

[0065] In some embodiments, multiple candidate agents can be expert agents, each designed to handle different needs and intentions. This allows the use of expert agents, suitable for handling needs and intentions, as second agents to understand the dialogue content and output more precise guidance prompts to guide the target object to input accurate health-related information. The health recommendations output by the second agent can more accurately meet the needs and intentions of the target object. This enables the first agent to flexibly schedule and adapt the second agent to the dialogue with the target object according to the needs and intentions, so as to output target response information that meets the needs and intentions of the target object, thereby improving the actual needs and intentions of the target object.

[0066] In some embodiments, the dialogue content in the first time period represents a need intent that is a product usage guidance intent regarding product usage conditions. The first intelligent agent can invoke a product expert intelligent agent that matches the product usage guidance intent to act as a second intelligent agent and engage in dialogue with the target object. In the second time period adjacent to the first time period, if the intent recognition intelligent agent identifies that the need intent represented by the dialogue content is a rehabilitation training need intent, the first intelligent agent invokes a rehabilitation expert intelligent agent that matches the rehabilitation training need intent to act as a second intelligent agent and engage in dialogue with the target object, so that the target's response information can meet the target object's needs for rehabilitation training.

[0067] According to embodiments of this disclosure, by utilizing an intent-recognition agent to identify the target object's needs and intentions, and by using a first agent to flexibly invoke a suitable second agent to output target response information related to the needs and intentions, it is possible to promptly select suitable agents to engage in dialogue with the target object based on the needs and intentions represented by the current dialogue content during the dialogue interaction process. Furthermore, while accurately identifying the attributes of the dialogue stage, target response information that satisfies the target object's needs and intentions is displayed more precisely, thus avoiding a decline in response information quality, improving the fit between the target response information and the target object's needs and intentions, and enhancing the target object's interactive experience.

[0068] In some embodiments, using a first agent to identify dialogue stage attributes represented by dialogue content may include: using the first agent to process dialogue content according to the target's emotional intent to obtain dialogue end stage attributes that represent the fulfillment of the solution response conditions.

[0069] According to embodiments of this disclosure, the demand intent includes the target emotional intent, which can indicate that the target object has a relatively urgent need to obtain health advice. For example, the target emotional intent can indicate that the target object has impatience, or expresses a desire to end the guidance prompts.

[0070] In some embodiments, the target emotional intent can characterize at least one of the following emotional attributes: eagerness for symptom information or products related to symptom information; negative emotion for guidance prompts.

[0071] Anxiety about symptom information or related products can be determined using an intent-based intelligent agent through semantic understanding of the target's input, such as speech or text. For example, the dialogue could include, "Tell me quickly how many capsules of brand A to take each time."

[0072] Negative emotions associated with guidance prompts can indicate negative emotions such as dissatisfaction from the target audience towards one or more guidance prompts displayed on the interactive page.

[0073] In some embodiments, the second agent processes the dialogue content based on the target's emotional intent and outputs a health suggestion solution. For example, the second agent can understand the health-related information in the current dialogue content based on the intent of urgency, and perform generative tasks by calling information such as medical knowledge bases and product information knowledge bases to output a health suggestion solution.

[0074] It should be noted that the health advice output by the second agent can include informational formats such as images, text, and tables. Alternatively, the health advice can be concise and address the target audience's current emotional needs. For example, a health advice suggestion could be "Take one tablet three times a day after meals." This concise approach effectively meets the target audience's needs and avoids the negative impact of multiple rounds of health-related information collection, which could degrade the user experience.

[0075] The first agent processes the dialogue content by utilizing the target emotional intent output by the intent recognition agent. This allows for timely and accurate transmission of dialogue end-stage attributes to the second agent. The second agent, based on the information in the current dialogue and the target's emotional intent, executes generative tasks according to a dialogue strategy matching the dialogue end-stage attributes. This results in timely display of health advice solutions, such as product usage suggestions and rehabilitation training recommendations, on the interactive page. This multi-agent collaboration enables timely identification of target emotional intent and display of health advice solutions that meet that intent, avoiding a decline in the user experience caused by continuously seeking complete health-related information through dialogue.

[0076] According to embodiments of this disclosure, the demand intent may further include at least one of the following: symptom information consultation intent, consultation intent for products related to symptom information, and disease information consultation intent.

[0077] The symptom information consultation intent indicates the target individual's intention to consult about symptoms such as pain, swelling, and insomnia. The intent recognition agent can understand information from any modality, such as text and images, within the dialogue content and output the symptom information consultation intent. The second agent can then process the corresponding knowledge content from the health knowledge base based on the symptom information consultation intent and output information including expected symptom development and rehabilitation training content, as well as health recommendations.

[0078] The intent to consult about products related to symptom information indicates the target audience's intention to consult about physical products or services for treating or alleviating symptoms. The second agent can then process product usage rules and logistics information based on this intent to provide timely feedback on product-related health recommendations.

[0079] The intent to seek disease information indicates the target audience's desire to inquire about disease-related information such as symptoms and treatment cycles. The second agent can process disease-related knowledge based on this intent and output health recommendations describing preventative measures and treatment processes, ensuring the recommendations accurately meet the target audience's actual needs.

[0080] In some embodiments, using a first agent to identify dialogue stage attributes represented by dialogue content may include: using the first agent to perform the following operations: performing a target task based on the demand intent represented by the dialogue content, determining symptoms and product demand information related to the demand intent; and determining guidance stage attributes or solution generation stage attributes based on the difference information between the dialogue content and symptoms and the product demand information.

[0081] According to embodiments of this disclosure, the guidance phase attribute is used to prompt the second intelligent agent to output guidance prompt information, and the scheme generation phase attribute is used to prompt the second intelligent agent to output a health suggestion scheme.

[0082] According to embodiments of this disclosure, the target task may include a retrieval task. A first intelligent agent may construct retrieval task parameters based on demand intent and execute the retrieval task according to the retrieval task parameters by calling a retrieval tool to obtain information related to symptoms and product demand.

[0083] In some embodiments, symptom and product demand information may include knowledge content related to at least one of the symptoms and products. The symptom and product demand information is used to represent the demand conditions that the health-related information content required to output a health recommendation plan must meet. A first agent can perform a query operation based on the demand intent to obtain health knowledge content related to the demand intent, and determine the symptom and product demand information by understanding the health knowledge content.

[0084] For example, symptom and product need information could be "treatment is needed when there is pain 3 times a week, each lasting about 3 hours." The first agent can then process the symptom and product need information along with the health-related information input by the target user in the dialogue to understand the discrepancy between the dialogue content and the symptom / product need information: "The user did not input the duration of the pain." Based on this discrepancy, the first agent can output guidance stage attributes, which in turn call the second agent to process the dialogue content and the user's intent according to a dialogue strategy matching the guidance stage attributes, outputting guidance prompts. These prompts could be something like "How long does each pain last?", precisely guiding the target user to input health-related information as prompted. This allows the second agent to output more complete and accurate health recommendations based on the health-related information in the dialogue, improving the user's interactive experience.

[0085] In some embodiments, the first agent calls upon a second agent from among multiple candidate agents that corresponds to the guidance phase attributes and the desired intent to process the dialogue content and obtain guidance prompts.

[0086] According to embodiments of this disclosure, multiple candidate agents can each have different capability attributes. Candidate agents can be associated with preset guidance phase attributes or solution generation phase attributes, and can also be associated with preset demand intentions. Thus, a first agent can determine a second agent from among the multiple candidate agents that corresponds to the guidance phase attributes and demand intentions based on the output dialogue phase attributes and the received demand intentions. The first agent then sends instructions to the second agent to invoke it to process the dialogue content and output the target response information.

[0087] In some embodiments, multiple candidate agents can be represented based on the contents of Table 1.

[0088] Table 1

[0089]

[0090] As shown in Table 1, the first intelligent agent can, for example, call upon the "shopping guide-product-illness collection agent" as the second intelligent agent to process the dialogue content and output guidance prompts based on the received product consultation intent and the output guidance stage attributes.

[0091] In some embodiments, guidance prompts are used to prompt the target object to input health-related information related to the discrepancy. The second agent can determine the discrepancy by understanding the dialogue content and symptom and product demand information, and output guidance prompts by performing a text generation task. This prompts the target object to accurately input health-related information related to the discrepancy, avoiding situations where the target object has difficulty understanding the content of the guidance prompts, resulting in repeated questioning, reducing the frequency of the target object's interaction, lowering the risk of negative emotions, and improving the interactive experience.

[0092] In some embodiments, processing dialogue content using a second agent according to a dialogue strategy that matches the dialogue stage attributes may include: using a second agent from among multiple candidate agents that corresponds to the scheme generation stage attributes to analyze health-related information and guidance prompts in the dialogue content, and outputting a health suggestion scheme.

[0093] For example, in the case of the first agent outputting the solution generation stage attributes, a "shopping guide-product-solution agent" can be called from multiple candidate agents based on the product consultation intent. This agent performs generative tasks based on relatively complete health-related information in the dialogue content, outputting accurate and complete health advice solutions. This allows the target audience to obtain more accurate information from the health advice solutions, thereby improving the interactive experience.

[0094] Figure 3 The diagram illustrates an application scenario of the agent-based health question-and-answer interaction method according to an embodiment of the present disclosure.

[0095] like Figure 3 As shown, the interactive page displayed in the interface is a page for dialogue interaction with the target object. The target object can enter dialogue content such as text, images, and files in the input box 331, and the target response information output by the second intelligent agent can also be displayed on the interactive page.

[0096] When the target user inputs the first input information 301, the first agent processes the first input information 301 according to the symptom consultation intent and outputs the guidance stage attributes. The first agent calls a second agent that matches the guidance stage attributes and symptom consultation intent to process the dialogue content, the target user's historical interaction information, and knowledge base content, and outputs the first target response information 311. The first target response information 311 can be a guidance prompt to prompt the target user to input health-related information related to the duration of symptoms.

[0097] When the target inputs the second input information 302 as health-related information, a first agent processes the product consultation intent and dialogue content, outputting a guidance stage attribute. The first agent then calls a second agent that matches the guidance stage attribute of the product consultation intent to process the dialogue content and product information, outputting the second target response content 312. The first target response information 311 and the second target response content 312 can be displayed as dialogue content on the interactive page.

[0098] During the dialogue interaction between the target object and multiple intelligent agents, the first intelligent agent can invoke the corresponding second intelligent agent to output target response information based on changes in the demand intent expressed in the dialogue content, until the dialogue stage attribute output by the first intelligent agent after processing the dialogue content meets the solution generation stage attribute that satisfies the solution response condition. The first intelligent agent then invokes the second intelligent agent that matches the solution generation stage attribute and the demand intent to execute the solution generation task, outputting health suggestion solution 321.

[0099] In some embodiments, the intent of the need in the dialogue content may change. Therefore, a first agent can be used to promptly and accurately invoke a second agent that is adapted to the changing intent, and to conduct dialogue with the target object according to the dialogue strategy corresponding to the dialogue stage attributes. This ensures that the displayed target response information can more accurately meet the target object's intent in each dialogue round, and to output health advice solutions in a timely manner to meet the target object's actual dialogue needs for health-related advice content. This avoids the target object's urgent need for health advice content being ignored due to multiple rounds of guiding prompts, thereby improving the user experience of the interaction process.

[0100] In some embodiments, the agent-based health question-and-answer interaction method may further include: when the demand intent is the target demand intent, invoking a dialogue agent corresponding to the target demand intent to engage in dialogue with the target object.

[0101] According to embodiments of this disclosure, a preset health need intent can represent the target object's intention to consult about health information such as symptoms and health-related products. The semantic difference between the target need intent and the preset health need intent satisfies a preset difference condition. For example, if the semantic similarity between the target need intent and the preset health need intent is greater than a preset similarity threshold, it can be indicated that the semantic difference between the target need intent and the preset health need intent satisfies the preset difference condition.

[0102] In some embodiments, the target demand intent may include an intent representing the target object's negative emotions, such as annoyance at the target object's response. Alternatively, the target demand intent may also represent the user's demand intent for products with low relevance to health needs, such as clothing and footwear. Thus, the first agent can be used to break out of the current health consultation dialogue mode based on the dialogue stage attributes and demand intent, and invoke other second agents with low relevance to the preset health demand intent to process the dialogue content, outputting response information that satisfies the target object's current target demand intent. This enables flexible scheduling of the agent workflow to engage in dialogue with the target object, enhancing the target object's diverse interactive experience.

[0103] Figure 4 A flowchart illustrating an agent-based health question-and-answer interaction method according to another embodiment of the present disclosure is shown.

[0104] like Figure 4 As shown, the agent-based interaction scheme includes operations S401 to S409.

[0105] In operation S401, the input information of the target object during the dialogue process is parsed to obtain the parsed content.

[0106] In operation S402, if the parsed content indicates that the keywords correspond to the intention of health consultation are matched, the dialogue content is processed based on the health consultation mode.

[0107] In operation S403, it is determined whether the target object has selected the card. If the result is no, operation S404 is executed, which calls the intent recognition agent and the first agent to perform the task and output the dialogue stage attributes of the demand intent.

[0108] In operation S405, it is determined whether the attributes of the dialogue stage meet the response conditions of the solution. If the result is no, operation S406 is executed, whereby the second agent processes the dialogue content according to the dialogue strategy and outputs guiding prompts. Operations S402 to S405 are then executed repeatedly to guide the target object to input health-related information.

[0109] If the judgment result of operation S405 is yes, the second agent can be used to process the dialogue content according to the dialogue strategy that meets the response conditions of the solution, and output a health suggestion solution.

[0110] If the judgment result of operation S403 is yes, execute operation S408 to determine the guidance stage attribute corresponding to the health consultation mode, and call the second agent to output guidance prompt information based on the guidance stage attribute. In operation S409, determine whether the dialogue content has completed the information collection task. If the judgment result is yes, execute operation S407. If the judgment result is no, repeat operations S402 through S406.

[0111] In some embodiments, the agent-based health question-and-answer interaction method can be implemented based on the following specific example: the user inputs "I have a cold and fever, I want to buy some [brand name] cold medicine." During the dialogue, an intent recognition agent is used to identify the intent based on the input information and context, and outputs the desired intent. Demand intents include multiple types such as: intent to purchase medicine, intent to consult about treatment methods, and intent for casual conversation. Users can input information through voice, text, or by clicking on interactive cards such as tabs and labels provided on the interactive page to input health-related information and other dialogue content.

[0112] After obtaining the specific needs and intentions corresponding to the user's current input information, the first agent invokes the corresponding workflow in real time based on the needs and intentions and dialogue stage attributes in the dialogue. The workflow includes a second agent corresponding to the needs and intentions and dialogue stage attributes. The invoked workflow can execute the response content generation task based on the dialogue strategy corresponding to the subdivided needs and intentions and dialogue stage attributes, and output the target response information. This enables the switching between three different dialogue modes during the dialogue process based on multi-agent collaboration: "maintaining the consultation mode", "ending the consultation mode", and "exiting the consultation mode".

[0113] In the consultation maintenance mode, users answer questions according to the standard consultation path to input health-related information, so that the second intelligent agent can collect complete health-related information that meets the consultation needs of the target subject.

[0114] During the dialogue, when the intent recognition agent detects the user's impatience, irritability, urgency, or other target emotional intents, the first agent outputs the dialogue end stage attribute to switch to "end of consultation mode," and the second agent interprets the acquired dialogue content and outputs health advice.

[0115] When the intent recognition agent identifies that the user has expressed other target needs, the first agent calls on the dialogue agent that matches the target needs to engage in dialogue with the user, so as to switch the dialogue process to "diagnosis exit mode".

[0116] The first agent generates the target response information by invoking a second agent that matches the user's intent and the attributes of the dialogue stage to process the dialogue content. In the guidance attribute stage corresponding to the symptom collection stage, the symptom information guidance agent is invoked to output guidance prompts. In the solution response stage, the solution generation agent is invoked to output health advice solutions. Different agents can correspond to different user intents, thereby improving the accuracy and timeliness of the target response information and meeting diverse user needs.

[0117] It should be noted that the acquisition and processing of information involved in the embodiments of this disclosure are all obtained under the condition of obtaining authorization from relevant personnel or institutions, and the acquired information is subject to necessary encryption and desensitization measures to avoid information leakage. Furthermore, the "consultation" and "treatment plan" involved in the embodiments of this disclosure are not information content used to treat users, but rather information to prompt users' intention to seek health advice. Under necessary and prominent conditions, the relevant prompts need to be displayed to prevent users from directly using the displayed prompts in the treatment process.

[0118] In some embodiments, the target response information output by this disclosure may also be reviewed by qualified personnel before being released to avoid abnormal situations such as information errors.

[0119] Figure 5 A block diagram of an agent-based health question-and-answer interaction device according to an embodiment of the present disclosure is shown schematically.

[0120] like Figure 5 As shown, the health question-and-answer interaction device 500 based on intelligent agents includes a first display module 510, a target reply information acquisition module 520, and a second display module 530.

[0121] The first display module 510 is used to display the interactive page.

[0122] The target response information acquisition module 520 is used to, during the process of dialogue with a target object based on an interactive page, use a first intelligent agent to identify the dialogue stage attributes represented by the dialogue content, and use a second intelligent agent to process the dialogue content according to a dialogue strategy that matches the dialogue stage attributes to obtain target response information. The dialogue strategy indicates that the target object is prompted to input health-related information by determining guidance prompts, or the dialogue strategy indicates that a health suggestion plan is determined based on the dialogue content. The target response information includes at least one of the guidance prompts and the health suggestion plan.

[0123] The second display module 530 is used to display the health recommendation scheme determined by the second agent when the attribute representation in the dialogue phase meets the scheme response conditions.

[0124] According to embodiments of this disclosure, the interaction device of the intelligent agent further includes a demand intent acquisition module.

[0125] The demand intent acquisition module is used to process the dialogue content using an intent recognition agent to obtain the demand intent of the target object. The first agent, based on the demand intent, selects a second agent from multiple candidate agents that matches the demand intent, processes the dialogue content according to the dialogue strategy, and outputs target response information to satisfy the demand intent.

[0126] According to embodiments of this disclosure, the target response information acquisition module includes a first processing unit.

[0127] The first processing unit is used to process the dialogue content according to the target emotional intent using the first intelligent agent to obtain the dialogue end stage attribute that represents the condition for satisfying the solution response. The demand intent includes the target emotional intent. The second intelligent agent processes the dialogue content according to the target emotional intent and outputs a health suggestion solution. The target emotional intent represents at least one of the following emotional attributes: eagerness for symptom information or products related to symptom information; negative emotion for guidance prompts.

[0128] According to embodiments of this disclosure, the demand intent includes at least one of the following: symptom information consultation intent, consultation intent for products related to symptom information, and disease information consultation intent.

[0129] According to embodiments of this disclosure, the target response information acquisition module includes an execution unit.

[0130] The execution unit is used to perform the following operations using the first intelligent agent: execute the target task according to the demand intention represented by the dialogue content, and determine the symptoms and product demand information related to the demand intention; determine the guidance stage attribute or the solution generation stage attribute according to the difference information between the dialogue content, symptoms and product demand information, wherein the guidance stage attribute is used to prompt the second intelligent agent to output guidance prompt information, and the solution generation stage attribute is used to prompt the second intelligent agent to output health suggestion solutions.

[0131] According to an embodiment of this disclosure, a first agent calls a second agent from among multiple candidate agents that corresponds to the guidance phase attributes and demand intent to process the dialogue content and obtain guidance prompt information. The guidance prompt information is used to prompt the target object to input health-related information related to the difference information.

[0132] According to embodiments of this disclosure, the target response information acquisition module includes an analysis unit.

[0133] The analysis unit is used to analyze the health-related information and guidance prompts in the dialogue content using a second agent from among multiple candidate agents that corresponds to the attributes of the solution generation stage, and output a health suggestion solution.

[0134] According to embodiments of this disclosure, the agent-based health question-and-answer interaction device further includes a dialogue module.

[0135] The dialogue module is used to invoke the dialogue agent corresponding to the target demand intent to conduct dialogue with the target object when the demand intent is the target demand intent. The semantic difference between the target demand intent and the preset health demand intent meets the preset difference condition.

[0136] According to embodiments of this disclosure, the health recommendation scheme includes at least one of the following: recommended products that match health-related information; descriptive information describing the conditions of use of the recommended products; and document explanation information for interpreting the target document, wherein the dialogue content includes the target document.

[0137] Any one or more of the modules, units, and subunits according to the embodiments of this disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, units, and subunits according to the embodiments of this disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, units, and subunits according to the embodiments of this disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, units, and subunits according to the embodiments of this disclosure can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0138] For example, any plurality of the first display module 510, the target response information acquisition module 520, and the second display module 530 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this disclosure, at least one of the first display module 510, the target response information acquisition module 520, and the second display module 530 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the first display module 510, the target response information acquisition module 520, and the second display module 530 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0139] It should be noted that the agent-based health question-and-answer interaction device part in the embodiments of this disclosure corresponds to the agent-based health question-and-answer interaction method part in the embodiments of this disclosure. For a detailed description of the agent-based health question-and-answer interaction device part, please refer to the agent-based health question-and-answer interaction method part, which will not be repeated here.

[0140] Figure 6 A block diagram of an electronic device suitable for implementing an agent-based health question-and-answer interaction method according to an embodiment of the present disclosure is shown schematically. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0141] like Figure 6As shown, an electronic device 600 according to an embodiment of this disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0142] RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0143] According to embodiments of this disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device 600 may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0144] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by processor 601, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0145] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0146] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0147] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0148] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the agent-based health question-and-answer interaction method provided in the embodiments of this disclosure.

[0149] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0150] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0151] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0153] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A health question-and-answer interaction method based on intelligent agents, comprising: Display the interactive page; During the dialogue with the target object based on the interactive page, a first agent is used to identify the dialogue stage attributes represented by the dialogue content, and a second agent is used to process the dialogue content according to a dialogue strategy that matches the dialogue stage attributes to obtain target response information. The dialogue strategy indicates that the target object is prompted to input health-related information by determining guidance prompt information, or the dialogue strategy indicates that a health suggestion plan is determined based on the dialogue content. The target response information includes at least one of the guidance prompt information and the health suggestion plan. If the attribute indication in the dialogue phase meets the response conditions, the health recommendation scheme determined by the second agent is displayed.

2. The method according to claim 1, wherein, The method further includes: An intent-recognition agent processes the dialogue content to obtain the target object's demand intent. The first agent, based on the demand intent, selects a second agent from multiple candidate agents that matches the demand intent, processes the dialogue content according to the dialogue strategy, and outputs target response information to satisfy the demand intent.

3. The method according to claim 2, wherein, The dialogue stage attributes represented by the dialogue content identified by the first intelligent agent include: The first agent processes the dialogue content based on the target emotional intent to obtain a dialogue end-stage attribute representing the satisfaction of the proposed response conditions. The demand intent includes the target emotional intent. The second agent processes the dialogue content based on the target emotional intent and outputs the health suggestion proposal. The target emotional intent represents at least one of the following emotional attributes: Anxiety about symptom information or products related to said symptom information; The negative emotions associated with the aforementioned guidance and prompts.

4. The method according to claim 2, wherein, The intent to demand includes at least one of the following: Intent to seek symptom information, intent to seek information about products related to the symptom information, and intent to seek information about the disease.

5. The method according to claim 1 or 2, wherein, The dialogue stage attributes represented by the dialogue content identified by the first intelligent agent include: The first intelligent agent performs the following operations: Based on the demand intent represented by the dialogue content, execute the target task and determine the symptoms and product demand information related to the demand intent; Based on the dialogue content and the differences between the symptoms and product demand information, a guidance stage attribute or a solution generation stage attribute is determined. The guidance stage attribute is used to prompt the second agent to output the guidance prompt information, and the solution generation stage attribute is used to prompt the second agent to output the health suggestion solution.

6. The method according to claim 5, wherein, The first agent calls upon a second agent from among multiple candidate agents, which corresponds to the guidance stage attribute and the demand intent, to process the dialogue content and obtain the guidance prompt information. The guidance prompt information is used to prompt the target object to input health-related information related to the difference information.

7. The method according to claim 5, wherein, The process of using a second agent to process the dialogue content according to a dialogue strategy that matches the attributes of the dialogue stage includes: The second agent, which corresponds to the attribute of the scheme generation stage among multiple candidate agents, analyzes the health-related information and guidance prompts in the dialogue content and outputs the health suggestion scheme.

8. The method according to claim 2, further comprising: When the demand intent is the target demand intent, the dialogue agent corresponding to the target demand intent is invoked to conduct a dialogue with the target object, wherein the semantic difference between the target demand intent and the preset health demand intent satisfies the preset difference condition.

9. The method according to claim 1, wherein, The health recommendation program includes at least one of the following: Recommended products that match the aforementioned health-related information; Descriptive information used to describe the product usage conditions of the recommended product; The dialog content includes the target file and is used to interpret file explanation information for the target file.

10. A health question-and-answer interaction device based on intelligent agents, comprising: The first display module is used to display the interactive page; The target response information acquisition module is used to, during the process of dialogue with a target object based on the interactive page, use a first agent to identify the dialogue stage attributes represented by the dialogue content, and use a second agent to process the dialogue content according to a dialogue strategy that matches the dialogue stage attributes to obtain target response information. The dialogue strategy indicates that the target object is prompted to input health-related information by determining guidance prompt information, or the dialogue strategy indicates that a health suggestion plan is determined based on the dialogue content. The target response information includes at least one of the guidance prompt information and the health suggestion plan. The second display module is used to display the health recommendation scheme determined by the second agent when the attribute indication in the dialogue phase meets the scheme response conditions.

11. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 9.

12. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images