Interactive method, device, equipment and medium for medical guidance

Abstract

The present disclosure provides an interaction method, device, equipment and medium for medical guidance, which relates to the technical fields of internet medical treatment, artificial intelligence and the like. The method comprises: in response to input text representing a medical treatment intention input by an object, displaying an interaction interface for obtaining a medical treatment preference, wherein the interaction interface comprises at least one first interaction content generated by a first large model based on the input text; in response to an interaction operation of the object on the interaction interface, obtaining and displaying medical treatment preference information of the object, wherein the medical treatment preference information comprises first sub-preference information obtained by the interaction operation on the first interaction content; and displaying medical guidance information generated based on the medical treatment preference information, wherein the medical guidance information is used to guide the object to perform a medical treatment process.

Description

Technical Field

[0001] This disclosure relates to the fields of internet healthcare, artificial intelligence, and other technologies. Specifically, it relates to an interactive method, device, equipment, and medium for medical guidance. Background Technology

[0002] Currently, with the continuous development of artificial intelligence technology, online users can search for and answer questions about medical resources through dialogue with AI (such as large language models or intelligent agents). For example, intelligent agents can currently be used for medical guidance.

[0003] In related technologies, medical triage typically presents users with fixed interactive items, which users then search and select based on their needs. However, users may not have much knowledge about available medical resources, leading to a poor user experience. Furthermore, medical triage based on intelligent agent question answering places high demands on input information. If user input is limited or vague, the agent's responses become highly random, further negatively impacting the user experience. Summary of the Invention

[0004] In view of this, the present disclosure provides an interactive method, device, equipment and medium for medical guidance.

[0005] One aspect of this disclosure provides an interactive method for medical treatment guidance, comprising: responding to input text representing a medical treatment intention input by an object, displaying an interactive interface for obtaining medical treatment preferences, wherein the interactive interface includes at least one first interactive content generated by a first model based on the input text; responding to an interactive operation by the object on the interactive interface, obtaining and displaying the object's medical treatment preference information, wherein the medical treatment preference information includes first sub-preference information obtained from interactive operations on the first interactive content; and displaying medical treatment guidance information generated based on the medical treatment preference information, wherein the medical treatment guidance information is used to guide the object to perform a medical treatment process.

[0006] Another aspect of this disclosure provides an interactive device for medical treatment guidance, comprising: a first display module for displaying an interactive interface for obtaining medical treatment preferences in response to input text representing a medical treatment intention input by an object, wherein the interactive interface includes at least one first interactive content generated by a first model based on the input text; a second display module for obtaining and displaying the object's medical treatment preference information in response to the object's interactive operation on the interactive interface, wherein the medical treatment preference information includes first sub-preference information obtained from interactive operations on the first interactive content; and a third display module for displaying medical treatment guidance information generated based on the medical treatment preference information, wherein the medical treatment guidance information is used to guide the object to perform a medical treatment process.

[0007] 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.

[0008] 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.

[0009] 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.

[0010] In this embodiment, since users' medical preferences are often multi-dimensional, collecting this information solely through general question-and-answer sessions may lead to lengthy questions, frequent dialogue rounds, tedious user responses, and even omissions of key preferences, affecting triage efficiency and user experience. This disclosure, based on the medical preference information obtained from the first interactive content generated from user input text, can specifically confirm or supplement core medical preferences, avoiding users inputting unnecessary information aimlessly, thereby improving the efficiency and accuracy of the interaction and enhancing the accuracy and efficiency of subsequent medical triage information generation. Furthermore, throughout the process, users only need to represent their medical needs with a proactive, vague, and minimally detailed input text. Subsequently, they can supplement their medical preference information by following the guidance of the interactive interface, achieving simple, convenient, and fast (compared to multi-turn dialogues) accurate completion of medical preference information. Attached Figure Description

[0011] 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:

[0012] Figure 1 The illustration shows an application scenario diagram of an interactive method for medical guidance according to an embodiment of this application.

[0013] Figure 2 A flowchart illustrating an interactive method for medical guidance according to an embodiment of the present disclosure is shown.

[0014] Figure 3A The illustration schematically depicts a first scenario diagram of acquiring and displaying medical preference information according to an embodiment of the present disclosure.

[0015] Figure 3B The illustration schematically depicts a second scenario diagram of acquiring and displaying medical preference information according to an embodiment of this disclosure.

[0016] Figure 3C The illustration depicts a scenario of displaying medical guidance information according to an embodiment of the present disclosure.

[0017] Figure 4 The illustration depicts a scenario in which a preference modification control is triggered according to an embodiment of the present disclosure.

[0018] Figure 5A The illustration depicts a scenario where text input is performed by triggering a dialog page according to an embodiment of the present disclosure.

[0019] Figure 5B The illustration depicts a scenario where an embodiment of this disclosure accesses other channels via a dialog page.

[0020] Figure 6 The diagram illustrates a data flow diagram for obtaining medical preference information according to an embodiment of the present disclosure.

[0021] Figure 7 A block diagram of an interactive device for medical guidance according to an embodiment of the present disclosure is shown schematically.

[0022] Figure 8 A block diagram of an electronic device suitable for implementing an interactive method for medical guidance according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.).

[0027] In the embodiments of this disclosure, 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 maintain the security of user personal information, network security, and other security. In the embodiments of this disclosure, user authorization or consent has been obtained before acquiring or collecting user personal information.

[0028] For example, traditional medical referral systems offer options to filter doctors by department and disease. However, the specific details of departments and diseases are relatively fixed, requiring all users to search and filter according to a fixed logic. This makes it difficult to adapt to user needs, often requiring extensive searching and filtering to find available medical resources. Alternatively, users can ask the AI ​​agent, "Find me a doctor specializing in XXX treatment," and the agent will then recommend doctors based on preset rules and a knowledge base. However, if the user manually inputs few conditions, the medical resources provided by the AI ​​agent are relatively random, and the information provided may not be helpful to the user (e.g., distance, time, whether the treatment is appropriate).

[0029] Therefore, embodiments of this disclosure provide an interactive method for medical guidance, comprising: responding to input text representing a medical intention input by an object, displaying an interactive interface for obtaining medical preferences, wherein the interactive interface includes at least one first interactive content generated by a first model based on the input text; responding to an object's interactive operation on the interactive interface, obtaining and displaying the object's medical preference information, wherein the medical preference information includes first sub-preference information obtained from interactive operations on the first interactive content; and displaying medical guidance information generated based on the medical preference information, wherein the medical guidance information is used to guide the object in performing a medical process. Embodiments of this disclosure accurately understand the user's current situation and true intention through input text and an interactive interface before providing medical guidance, thereby achieving accurate generation of subsequent medical guidance information. Furthermore, throughout the process, the displayed interactive content is closely related to the user's input, and the interactive operations required by the user are relatively convenient, resulting in a good user experience.

[0030] Figure 1 The illustration shows an application scenario diagram of an interactive method for medical guidance according to an embodiment of this application.

[0031] It is important to note 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.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] It should be noted that the interactive method for medical guidance provided in this embodiment can generally be implemented by any one of the first terminal device 101, the second terminal device 102, and the third terminal device 103. Correspondingly, the interactive device for medical guidance can also be set in the aforementioned terminal devices. Alternatively, the interactive method for medical guidance provided in this embodiment can also be implemented jointly by the server 105 and the terminal device, wherein the server 105 can be used to acquire and process data to display the processed data on the terminal device.

[0037] For example, a user can input text representing their intention to seek medical treatment through any one of the first terminal device 101, the second terminal device 102, and the third terminal device 103. Then, any one of the terminal devices can display an interactive interface, respond to the user's interactive operations on the interface, obtain and display medical treatment preference information, and display medical guidance information generated based on the medical treatment preference information. Alternatively, the terminal device can send the obtained information to the server 105, and the server 105 can generate corresponding information based on the obtained information, such as responding to the input text representing the user's intention to seek medical treatment, displaying an interactive interface for obtaining medical treatment preferences, and generating medical guidance information based on the obtained medical treatment preference information.

[0038] 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.

[0039] Figure 2 A flowchart illustrating an interactive method for medical referral according to an embodiment of this disclosure is shown schematically. Figure 2 As shown, the method includes operations S210~S230.

[0040] In operation S210, in response to the input text representing the intention to seek medical treatment from the object input, an interactive interface for obtaining medical treatment preferences is displayed, wherein the interactive interface includes at least one first interactive content generated by the first model based on the input text.

[0041] An object (such as a user) can input text information in various ways; this text information is called input text.

[0042] Input text can have various intentions, such as a desire for casual conversation, a need to seek medical attention, or a request for medication. The intention of input text can be determined through semantic analysis, keyword extraction, and other methods. For example, an individual might directly input "I've been coughing a lot lately and want to see a doctor," directly expressing the intention to seek medical attention. Alternatively, they might input "What are some good respiratory hospitals nearby?" While the word "medical attention" isn't explicitly mentioned, the semantic information such as "nearby" and "respiratory hospitals" allows us to infer their underlying intention to seek medical attention.

[0043] When the input text indicates the user's intention to seek medical treatment, an interactive interface is displayed to retrieve the user's medical preferences. This interface can be diverse and take many forms, such as pop-up windows, expanded versions of the original input interface, or dialogue cards simulating a natural conversation with the user. Different forms of interactive interfaces can be selected and designed based on the specific application scenario and user habits.

[0044] Since the interactive interface is triggered when the input text represents the user's intention to seek medical treatment, and is used to further understand the user's medical preferences, the interactive content of the interface must at least include first interactive content generated based on the user's input text. This first interactive content can be targeted questions generated based on information in the input text that is directly related to the user's intention to seek medical treatment.

[0045] In embodiments of this disclosure, the first large model may be a large language model (LLM) used to generate first interactive content based on the input text. For example, the first large model may parse medical-related information from the input text, such as symptoms mentioned by the user (e.g., cough, fever, headache, etc.), duration of symptoms, initial measures taken, specific requirements for hospitals or doctors (e.g., tertiary hospitals, specialist clinics, etc.), and generate targeted first interactive content based on the parsed information.

[0046] For example, when the input text is "I've been coughing a lot lately and want to see a doctor," the first interactive element could be "How long have your cough symptoms lasted: 1 day, 3 days, 7 days, or more than two weeks?" Users can then interact further with this first interactive element to obtain more detailed information about their medical preferences. Alternatively, when the input text is "What are some good respiratory hospitals nearby?", the first interactive element could be "Which areas would you like to search for nearby respiratory hospitals: Area 1, Area 2, Area 3?" This first interactive element can specify the vague geographical location information of "nearby" to provide more accurate hospital recommendations later.

[0047] It is understood that the interactive interface includes at least the first interactive content generated based on the input text. On this basis, the interactive interface may or may not include other predetermined interactive content.

[0048] For different input texts, the first interactive content generated based on the input text can be different. Therefore, for multiple input texts from multiple users, the first interactive content of the interactive interface can be flexibly changed to achieve targeted acquisition of medical preference information.

[0049] In operation S220, in response to the object's interactive operation on the interactive interface, the object's medical preference information is obtained and displayed, wherein the medical preference information includes first sub-preference information obtained from the interactive operation on the first interactive content.

[0050] Interactive actions can be clicks, selections, inputs, swipes, etc., performed by the user on the primary interactive content within the interactive interface. For example, if the primary interactive content is "How long have your cough symptoms lasted: 1 day, 3 days, 7 days, more than two weeks," the user's interactive action could be clicking "3 days," in which case the primary sub-preference information obtained would be "Cough symptoms have lasted for 3 days." If the primary interactive content is a text box that requires the user to input information, such as "Please enter your age," the user could enter "35 years old" in the text box and submit, and the primary sub-preference information obtained through this interactive action would be "Age 35 years old."

[0051] In this embodiment, the interactive interface includes at least first interactive content generated based on the input text. The object's interactive operations include at least interactive operations on the first interactive content. This allows for the accurate capture of the object's needs (the object's specific medical preferences) through interactive operations on the first interactive content, so as to provide accurate medical guidance information in the future.

[0052] When operating S230, medical guidance information generated based on medical preference information is displayed.

[0053] Medical service guidance information is used to guide individuals through the medical process. This information can be a collection of various guidelines and information to help patients receive medical care smoothly and efficiently. For example, it may include information recommending departments and doctors corresponding to the symptoms entered in the text; it may also include information guiding patients on registration channels, times, available appointments, costs, and appointment rules; and it may include information assisting in completing processes such as waiting, being called, seeing a doctor, and picking up examinations and medications.

[0054] Medical care guidance information can be obtained by processing medical care preference information through various methods such as knowledge base matching and LLM generation.

[0055] In this embodiment, since users' medical preferences are often multi-dimensional, collecting this information solely through general question-and-answer sessions may lead to lengthy questions, frequent dialogue rounds, tedious user responses, and even omissions of key preferences, affecting triage efficiency and user experience. This disclosure, based on the medical preference information obtained from the first interactive content generated from user input text, can specifically confirm or supplement core medical preferences, avoiding users inputting unnecessary information aimlessly, thereby improving the efficiency and accuracy of the interaction and enhancing the accuracy and efficiency of subsequent medical triage information generation. Furthermore, throughout the process, users only need to represent their medical needs with a proactive, vague, and minimally detailed input text. Subsequently, they can supplement their medical preference information by following the guidance of the interactive interface, achieving simple, convenient, and fast (compared to multi-turn dialogues) accurate completion of medical preference information.

[0056] In one specific embodiment, users can input text, display and operate the interactive interface, and display medical preference information and medical guidance information within the dialog window / interface.

[0057] According to embodiments of this disclosure, in response to an object's interactive operation on an interactive interface, obtaining and displaying the object's medical preference information includes: in response to an object's selection operation on at least one first interactive content, obtaining first sub-preference information; in response to an object's confirmation operation on an interactive interface, canceling the display of the interactive interface and displaying the medical preference information in the form of dialogue text.

[0058] The first interactive content can exist in the form of an option list, button group, drop-down menu, or other selectable controls. Each first interactive content corresponds to one or more specific options (that is, one or more options in each first interactive content can be generated through the first main model). Users can select an option from the first interactive content and use the selected option as their first sub-preference information.

[0059] Since the interactive interface is used to obtain medical preference information, and one or more primary interactive elements and one or more options for each primary interactive element can result in lengthy interactive content, users need to scroll up and down the interface to see all the information, or scroll up and down the page to see the input text separated by the interactive interface. Therefore, to ensure the intuitiveness and continuity of the user's medical guidance, the interface is canceled by a confirmation action, and the medical preference information obtained through the interactive interface is presented in a concise and brief manner.

[0060] For example, buttons such as "Confirm," "Next," and "Done" can be set on the interactive interface. Clicking these buttons constitutes a confirmation action. It's understood that when a user performs a confirmation action, it indicates that they have completed supplementing their medical preference information for this round and acknowledged their selections. Based on this, the user's primary preference information can be obtained and organized to form a simple, comprehensive, and dialog-style medical preference information document.

[0061] Figure 3A The illustration schematically depicts a first scenario diagram of acquiring and displaying medical preference information according to an embodiment of this disclosure. For example... Figure 3A As shown, users can input text 311 representing their medical needs on the dialogue interface 310, such as "Consult a Beijing expert for XX disease". In response to the input text 311, an interactive interface 312 can be displayed. The interactive interface 312 can include first interactive content generated based on the input text, such as "What symptoms do you currently have: Symptom 1, Symptom 2, Symptom 3". For example, if "XX disease" is cardiovascular, then the symptoms 1-3 generated based on the input text could be: chest pain, chest tightness, difficulty breathing, etc.; if "XX disease" is thyroid disease, then the symptoms 1-3 generated based on the input text could be: goiter, palpitations, heart palpitations, etc.

[0062] For example, a user can click on symptom 3 321, selecting symptom 3 as the first sub-preference information, and then confirm the medical preference information by clicking the "Confirm" control 322. After clicking the "Confirm" control 322, the interactive interface 321 in the dialog box disappears, and the medical preference information 313 is displayed. Compared with the interactive interface 321, the medical preference information 313 typically only displays the user's selected preference information, concisely and completely showcasing the user's medical preferences. Subsequently, the medical guidance information 314 generated based on the medical preference information 313 can be further displayed on the dialog page.

[0063] In the embodiments of this disclosure, the generated first interactive content is displayed through an interactive interface, allowing users to make quick and easy selections based on the interface without having to think about what information needs to be provided, thus reducing the interactive burden and optimizing the interactive experience. Furthermore, if the user confirms the medical preference information within the interactive interface, the interface is canceled and the medical preference information is displayed in the form of dialogue text. This not only allows the user to clearly review and confirm their provided medical preferences to ensure the accuracy of the information, but also makes the entire information supplementation process smoother (avoiding dialogue fragmentation due to an overly long interactive interface) and more user-friendly, conforming to user interaction habits.

[0064] According to embodiments of this disclosure, the interactive interface further includes at least one predetermined second interactive content. Responding to an object's interactive operation on the interactive interface, obtaining and displaying the object's medical preference information includes: responding to an object's selection operation on at least one first interactive content, obtaining first sub-preference information; responding to an object's selection operation on at least one second interactive content, obtaining second sub-preference information; responding to an object's confirmation operation on the interactive interface, canceling the display of the interactive interface and displaying the medical preference information in the form of dialogue text, wherein the medical preference information further includes the second sub-preference information.

[0065] The second interactive content can be basic content related to medical needs. In one specific embodiment, the second interactive content may include at least one of the following: treatment route, doctor's level, expected appointment time, expected treatment location, historical treatment information (e.g., whether to seek medical treatment offline and suggestions for offline treatment), and the problem to be solved. To facilitate rapid recommendation of nearby medical resources, the expected treatment address can be determined based on the address information in the input text and / or the address information of the object. For example, if the input text includes "XX City", then "XX City" can be directly displayed as the expected treatment location on the interactive page (which can be modified through the interactive interface); if the input text does not include "XX City", then "XX City" can be displayed as the expected treatment location based on the user's real-time address information, such as "XX City" (which can be modified through the interactive interface).

[0066] The second interactive content can be part of the interactive interface template, and can be provided for various diseases to improve medical preference information.

[0067] The selection operation for the first interactive content and the confirmation operation for the interactive interface are the same as described above, and will not be repeated here. The interactive operation for the second interactive content can be either a selection operation or an input operation.

[0068] Figure 3B The illustration schematically depicts a second scenario diagram of acquiring and displaying medical preference information according to an embodiment of this disclosure. Figure 3B The right side shows an enlarged view of the interactive interface 312 in the dialogue page 310. In the dialogue page 310, users can scroll up and down to display various interactive elements on the interactive interface 312. The size of the interactive interface 312 in the dialogue page 310 can also be the same as the enlarged view on the right, allowing users to scroll up and down to display various interactive elements.

[0069] In the interactive interface 312, sections 323 and 324 (highlighted by boxes) represent hospital level and disease symptom description, respectively, serving as different primary interactive elements. Other elements can be secondary interactive elements, such as: patient needs (outpatient assistance, inpatient assistance, and online consultation); hospital selection (top ten in XX department, key clinical specialty, tertiary hospital, top five in regional specialty reputation); doctor selection (renowned expert, chief physician, associate chief physician); desired appointment time; desired appointment location; whether to seek medical treatment offline (yes or no); and offline doctor recommendations. Patient needs, hospital selection, and doctor selection can respectively represent the treatment method, hospital level, and doctor level.

[0070] The second interactive content can take various control forms. For example, the options for medical needs, hospital selection, doctor selection, and whether to seek medical treatment offline can be presented as a group of radio buttons, allowing users to select their medical preferences by clicking each button. The desired medical location can be presented as a drop-down selection box, allowing users to choose a suitable location from a preset list of options. The desired medical time can be presented as a slider, allowing users to adjust the desired time by dragging the slider on a time progress bar. Offline doctor suggestions can be presented as an input box, allowing users to manually enter information to supplement their second sub-preferences. These different control forms can be flexibly configured according to the specific type of the second interactive content and user operating habits, thereby improving the convenience and accuracy of user interaction.

[0071] Understandably, the first and second interactive content can be highlighted in gray to reflect the user's choice. Furthermore, the display of certain parts of the second interactive content can be dynamic, determined by the user's choice. For example, if the user selects "No" for "Whether to seek medical treatment offline," then offline doctor recommendations will not be displayed.

[0072] In the embodiments of this disclosure, displaying the first and second interactive content through an interactive interface allows for targeted acquisition of medical preference information while maintaining completeness, facilitating the accurate generation of subsequent medical guidance information. Furthermore, information can be quickly and conveniently obtained through at least one simple interactive operation (such as selection) on an interactive interface. After confirming the operation, canceling the interactive interface and displaying the medical preference information via dialogue text provides a straightforward and simple way to reconfirm the information with the user, and also facilitates the rapid generation of subsequent medical guidance information based on this format of medical preference information.

[0073] According to embodiments of this disclosure, the first interactive content includes: mandatory interactive content. In response to a confirmation operation by the object on the interactive interface, canceling the display of the interactive interface and displaying medical preference information in the form of dialogue text includes: in response to a confirmation operation by the object on the interactive interface, if the selection operation for at least one first interactive content does not include a selection operation for mandatory interactive content, displaying prompt information for prompting the operation of mandatory interactive content; and if the selection operation for at least one first interactive content includes a selection operation for mandatory interactive content, canceling the display of the interactive interface and displaying medical preference information in the form of dialogue text.

[0074] Required interactive content consists of information that users must select or provide. This content is used to enable core functions such as subsequent triage logic, department recommendation, and doctor matching. If the user does not select or provide these required interactive contents during the interaction, the system cannot obtain the necessary medical preference information for accurate triage. In this case, a prompt message is triggered to guide the user to complete the operation of the required interactive content. Conversely, if the user has selected or provided these required interactive contents during the interaction (this may or may not involve secondary interactive content, or it may be optional to select or provide secondary interactive content), the system proceeds to the subsequent stages of displaying medical preference information and generating triage information.

[0075] In one embodiment, if the number of first interactive elements in the interactive interface is less than a certain threshold, all first interactive elements can be determined as mandatory interactive elements. For example, if only one first interactive element is included, that first interactive element can be determined as mandatory. Alternatively, it can be determined based on the specific content of the first interactive element, such as the duration of symptoms, which can be considered mandatory interactive elements.

[0076] For example, if the required interactive content is "symptom duration", when the user does not select "symptom duration", the prompt message could be "Please select symptom duration to complete the medical preference information".

[0077] In other embodiments, while displaying the prompt message, the user can also be redirected to the mandatory interactive content for which no selection has been made. For example, if the user does not select "symptom duration", in addition to displaying the prompt message as mentioned above, the interface can automatically redirect to the "symptom duration" section to highlight the mandatory interactive content that requires user action, guiding the user to quickly locate and complete the selection.

[0078] In the embodiments of this disclosure, since the first interactive content of the interactive interface is information obtained after targeted mining of the input text, in order to ensure that the medical guidance information that meets the actual needs of the object can be generated accurately and effectively, the selectivity of the first interactive content can be restricted to ensure the smooth progress of the entire medical guidance process and the accuracy of the guidance results.

[0079] According to embodiments of this disclosure, the mandatory interactive content includes a hospital level generated based on the disease department and / or disease direction in the input text; the first interactive content also includes optional interactive content, which includes a description of disease symptoms generated based on the disease department and / or disease direction.

[0080] Disease departments refer to the physical departments within a hospital designated for patient reception, diagnosis, treatment, and management. Disease specializations typically refer to specialized diagnostic, research, and service areas subdivided based on etiology, pathology, disease type, or specific medical specialty. Understandably, users with medical needs will usually include at least one of these two categories in their input text (users may even use both interchangeably). Hospital levels typically include Level 1, Level 2, and Level 3, and Grade A, Grade B, and Grade C. Alternatively, levels can be based on specific diseases within various medical fields, such as "Key Hospital for Disease XX."

[0081] Users typically specify the relevant department and / or disease area in their input text, such as cardiology, dermatology, or neurology. The hospital rating usually serves as a crucial basis for medical resource recommendations and the generation of patient guidance information. Therefore, the hospital rating is often a mandatory interactive element, providing clear guidance for the subsequent generation of patient guidance information, making the entire guidance process more targeted and accurate.

[0082] In addition, the first interactive content will also include optional interactive content. Optional interactive content refers to information that users can selectively provide based on their actual situation during the medical guidance process. It is not necessary to complete the basic guidance service, but it can further optimize the accuracy and personalization of the guidance results.

[0083] In some embodiments, disease description information is a specific description of the disease or physical discomfort suffered by the subject. Disease description information may include the time, frequency, duration, main symptoms, triggering or relieving factors of the symptoms, whether there is a similar medical history, whether relevant examinations or treatments have been performed and their results, etc.

[0084] Considering the differences in users' understanding and expression of disease description information, some users may find it difficult to accurately and comprehensively describe their symptoms. Making this a mandatory option could create operational pressure for users, and might even cause some users to abandon the referral service due to their inability to clearly express themselves. Therefore, making disease description information an optional interactive element lowers the interaction threshold for users and the generation threshold for medical referral information, ensuring the availability of basic referral services and the user experience.

[0085] According to embodiments of this disclosure, a single mandatory interactive content includes multiple sub-interactive content. When a selection operation for at least one first interactive content includes a selection operation for a mandatory interactive content, canceling the display of the interactive interface and displaying medical preference information in the form of dialogue text includes: when a selection operation for a mandatory interactive content includes a selection operation for one or more sub-interactive content, canceling the display of the interactive interface and displaying medical preference information in the form of dialogue text.

[0086] It is understandable that the interactive interface can include one or more primary interactive elements, and each primary interactive element can include one or more sub-interactive elements to support multi-dimensional improvement and supplementation of the same primary interactive element.

[0087] For example, let's take hospital level as a mandatory interactive element. If the input text is "Coronary heart disease, accompanied by hyperlipidemia, looking for recent specialist appointments, no regional restrictions," the first interactive element generated based on this input text includes hospital level, such as "Top 10 Cardiovascular Hospitals, Top 100 Hospitals, Tertiary Hospitals, Specialized Hospitals," etc., as well as multiple second interactive elements such as treatment needs. Users can select one or more of the four options (i.e., all four options are sub-interactive elements) to better describe their preferences. Afterwards, in response to the confirmation operation on the interactive interface, the interactive interface will be canceled, and the confirmed medical preference information will be displayed: "Medical preferences and condition confirmed. Treatment needs: Outpatient appointment. Hospital preferences: Top 10 Cardiovascular Hospitals nationwide, Top 100 Hospitals nationwide, Tertiary Hospitals. Specialist preferences: Renowned Specialist, Chief Physician, Associate Chief Physician. Treatment time: Within 14 days. Offline treatment: No. Desired treatment region: Beijing. Desired problem to be solved: Arrange for coronary artery bypass surgery and evaluation as soon as possible. Current symptoms: Chest pain, chest tightness. Duration of symptoms: More than 1 year. Current medications: XX-ting, XXX oil."

[0088] In this embodiment, by providing multiple sub-interaction content, users have more detailed and comprehensive space to express their needs when making selections for the same mandatory interaction content, thereby making the medical preference information collected by the system more accurate and richer.

[0089] According to embodiments of this disclosure, the medical referral information includes a recommendation reason and at least one recommended doctor's information; displaying the medical referral information generated based on medical preference information includes: displaying the recommendation reason and at least one recommended doctor's information through an interactive card control.

[0090] Recommended doctor information can include detailed information such as the doctor's name, hospital name, department, professional title, area of ​​expertise, consultation hours (online consultation hours), and patient reviews, so that users can fully understand the doctor's professional background and the services they can provide. One doctor can correspond to one recommended doctor. In some embodiments, information such as the area of ​​expertise in the recommended doctor information can be summarized by an LLM (Limited Management System) to refine or clarify the specific doctor recommendation information.

[0091] The recommendation reason is used to explain to the user the specific reasons for recommending the doctor, and can be generated based on at least one dimension of the recommended doctor information mentioned above.

[0092] Interactive card controls refer to interactive elements in a user interface (such as the dialogue page above) that present information in the form of cards, typically with independent visual boundaries and layout structures. In this embodiment, recommended doctor information can be presented to the user as a medical resource, and the user may have interactive needs for each recommended doctor. Therefore, the reasons for the recommendation and at least one recommended doctor can be displayed in the form of interactive cards to support the user's subsequent interactive needs.

[0093] Furthermore, interactive card controls can integrate relevant content such as recommendation reasons and recommended doctor information into a compact and easily recognizable area, conforming to users' reading habits and guiding them to quickly obtain core content, thereby improving the user experience in browsing and selecting doctors.

[0094] Figure 3C The illustration schematically depicts a scenario of displaying medical guidance information according to an embodiment of this disclosure. For example... Figure 3C As shown, the dialogue page 310, input text 311, and medical preference information 313 are... Figure 3A and 3B Similarly, this will not be repeated here. The medical referral information 314 is displayed in the form of an interactive card, including the reason for recommendation 341 and the recommended doctor information 342. For example, the reason for recommendation is "You mentioned having symptom 3 and hope to find XX doctor XXXXXXXXX in Beijing. Considering XX in the selection of doctors, you can contact the consultant through the doctor information below to assist with registration."

[0095] Users can select recommended doctors to choose those that match their preferences, or they can use interactive controls 315 such as "Consultant" on the dialogue page 310 to perform further medical guidance operations.

[0096] In this embodiment, for the recommendation reasons and recommended doctor information displayed in the form of interactive card controls, users can also click control 343 to view detailed doctor recommendation information (limited by the size of the interactive card, it usually displays important information such as name, doctor level, and doctor photo).

[0097] In the online healthcare field, for medical needs such as registration, hospitalization, and consultation, a vast amount of medical resources (such as doctor resources) are scattered across multiple channels, such as official websites, apps, mini-programs, and public accounts. If a user has a medical need, they need to spend a lot of time and energy searching for scattered doctor information on multiple platforms or channels. In the embodiments disclosed in this disclosure, a unified page allows users to input text independently. Then, the system takes the lead in displaying medical preference information and generating and displaying medical guidance information based on the user's selection. The entire complex medical resource matching process is presented to the user in a clear and easy-to-understand form. Moreover, the change of control and interaction are all based on the input text or the user's interaction with the content, without the need for page jumps or other complex operations, thereby improving the transparency of medical guidance services and the user experience.

[0098] According to embodiments of this disclosure, the interactive card control further includes a preference modification control; the method further includes: displaying an interactive interface in response to a triggering operation on the preference modification control, so that an object can modify medical preference information through interactive operations on the interactive interface.

[0099] After the medical referral information (i.e., recommendation results) is displayed, users may find omissions or errors in the interactive interface, or they may have new considerations regarding the recommended doctor's specialty and consultation hours, or wish to adjust the distance to the medical facility, hospital level, etc. At this point, users will request to modify their preferences.

[0100] To meet users' needs for modifying preferences, the interactive card control can include a preference modification control, which can take various forms. The triggering action for the preference modification control can be clicking, long-pressing, swiping, or other preset actions. When the user triggers the preference modification control, the system will respond immediately and display the interactive interface described above. This interface retains the user's first and second sub-preference information and supports further selection and confirmation actions by the user to modify their medical treatment preferences.

[0101] In one embodiment, the interactive interface that is re-displayed through the triggering operation of the preference modification control can be implemented through an interactive window, or it can be triggered during a dialogue. After the user completes the modification of the medical treatment preference information, the modified medical treatment preference information can be displayed in the form of dialogue text, or the medical treatment guidance information can be updated directly based on the modified medical treatment preference information.

[0102] Figure 4 The illustration schematically depicts a scenario in which a preference modification control is triggered according to an embodiment of this disclosure. For example... Figure 4 As shown, users can click on the preference modification control 401 in the interactive card control. At this time, the interactive interface 410 that was canceled above can be brought up. In this interactive interface 410, the previously selected sub-preference information, such as "Top-tier Hospital", is still displayed in gray.

[0103] Both the first and second interactive content in the interactive interface 410 can be modified. Users can click on the two sub-interactive content "Key Clinical Specialties" and "Renowned Experts" to add information based on the existing medical preference information. Users can also adjust the slider in the expected consultation time, changing it from "within seven days" to "within three days". In other embodiments, the interactive interface also supports user deletion operations. The modified medical preference information is shown in the interactive interface 420.

[0104] In the embodiments of this disclosure, when displaying medical guidance information, the system supports simple operations via a preference modification control for this information, allowing for the quick reuse of canceled interactive interfaces. This enables users to quickly modify their preferences on the same page (such as the dialogue page above), ensuring the continuity and convenience of the interaction. After modification, the system will quickly re-match medical resources and generate new medical guidance information based on the updated medical preference information, allowing users to obtain timely recommendations that meet their current update needs, further improving the flexibility of the medical guidance service and the user experience.

[0105] According to an embodiment of this disclosure, for operation S210, in response to input text representing the intention to seek medical treatment input by an object, an interactive interface for obtaining medical treatment preferences is displayed, including: displaying a dialogue page for online triage, wherein the dialogue page is triggered through a channel entry representing the intention to seek medical treatment; in response to the object inputting input text on the dialogue page, if the intention of the input text is identified as the intention to seek medical treatment, the interactive interface for obtaining medical treatment preferences is displayed.

[0106] The dialogue page is triggered through an entry point representing the intent to seek medical treatment; that is, the first dialogue page corresponds to the intent to seek medical treatment. For example, clicking the medical referral function entry point will trigger the display of the dialogue page. Since the dialogue page corresponds to the intent to seek medical treatment, if the user enters text on this dialogue page, it is preliminarily confirmed that the user has the intent to seek medical treatment.

[0107] In one specific embodiment, the backend can detect medical intent through the channel entry point by detecting whether the channel entry field (such as biz) that triggers the dialog page is a predetermined field representing the channel entry point of medical intent.

[0108] While triggering the dialogue page can initially confirm a user's intention to seek medical treatment, the user may also input non-medical-related inquiries under this trigger. To save resources for generating and displaying subsequent interactive interfaces, the input text can be further subjected to intent recognition, and the interactive interface can be triggered and displayed only when both the trigger and text semantics confirm a medical treatment intent.

[0109] Figure 5A The illustration schematically depicts a scenario where text input is initiated by triggering a dialog page according to an embodiment of this disclosure. For example... Figure 5A As shown, the initial page 510 can be a medical referral page. Users can click the "Smart Matching" control 511 to start matching recommended doctor information. This control 511 can serve as an entry point for medical treatment intentions. Clicking the control will redirect to the dialogue page 520. It is understandable that the initial page 510 may also include other function entry points, such as Medical Service 1 and Medical Service 2, which can be used to view historical information (such as the number of times) of the above-mentioned various medical treatment needs, or to activate other sub-medical treatment needs.

[0110] On the dialogue page 520, users can enter text describing their intention to seek medical treatment through the input box 523. In this embodiment, the dialogue page 520 may also display guidance information 521 to guide the interaction process, or recommended medical needs 522 for the user. It is understood that if the user does not start a new dialogue or the interval between leaving the dialogue is less than a certain predetermined value, when the user triggers the dialogue page again through the channel entry, the aforementioned guidance information 521 and recommended medical needs 522 may not be displayed.

[0111] For example, the guidance information 521 may include information such as "Medical tips: 1. Describe your needs; 2. Select your preferences; 3. Add a number immediately", and may also include fixed template information such as "Hello, I am a smart doctor, I will match you with 1-on-1 medical services to assist you in your medical treatment".

[0112] The recommended medical needs 522 for the user can be based on historical information. For example, if the user has inquired about a disease or purchased related medications on the online platform, various recommended medical needs can be generated based on the aforementioned diseases, such as "You may be interested in the following issues: XXXX hospital registration assistance, XXX disease hospitalization assistance, XX specialist appointment assistance," etc. If the aforementioned historical information does not exist or the user's dwell time on the dialogue page exceeds a threshold (e.g., more than 1 second), various recommended medical needs can be generated based on statistical information, such as recommending frequently asked questions on the online platform recently. Alternatively, pre-determined general medical needs can be directly displayed. In the above embodiment, the amount of information on the dialogue page can be controlled by limiting the number of recommended medical needs 522 for the user; for example, the number of recommendations can not exceed 3.

[0113] In the embodiments of this disclosure, when a user inputs the aforementioned text through a dialogue page corresponding to their medical treatment intention, the medical treatment intention can be initially identified through the triggering channel entry point of the dialogue page. Furthermore, by performing semantic intent recognition on the input text, and if the intent of the input text is also a medical treatment intention, the interactive interface is then triggered. Thus, this embodiment of the disclosure achieves dual verification of the channel entry intent and the input text intent through the strong correlation between the dialogue page itself and the medical treatment intention, and the semantic triggering of the text. This minimizes the possibility of accidental triggering of the interactive interface, ensuring that the subsequent process of obtaining medical preference information is more targeted and accurate, and avoiding unnecessary operational interference for the user.

[0114] In other embodiments, if a user triggers the online triage page through other entry points, such as a pharmacy purchase entry or customer service entry, this page will not correspond to their medical treatment intention. In this case, intent recognition of the input text can still ensure the smooth generation of subsequent medical triage information. It is understood that if the dialogue page is triggered through other entry points, the information displayed on the first trigger can be the same as or different from the guidance information mentioned above, depending on the actual needs.

[0115] In addition, the chat page also displays entry points to other channels, allowing users to access other channels through the chat page. Figure 5B This illustration schematically depicts a scenario where an embodiment of this disclosure accesses other channels via a dialog page. For example... Figure 5B As shown, controls such as "Buy Medicine," "Health Record," "Online Doctor," and "Shopping Cart" can be displayed above the input box on the chat page. Clicking these controls will take users to the corresponding other channels. It's understandable that these controls will also be displayed if a user enters the chat page through other channels.

[0116] Figure 6A data flow diagram illustrating the acquisition of medical preference information according to an embodiment of this disclosure is shown schematically. Figure 6 As shown, users can input a query (i.e., text) on the dialogue page. If the query indicates a different intent, the processing flow for that intent is executed. If the query indicates a medical treatment intent, slot identification is performed on the query to obtain multiple target slots, such as the department and hospital for the disease, or the address of the recipient. Simultaneously, an interactive interface can be triggered to display these medical preference collection cards.

[0117] During the interaction phase of the medical preference collection card, the first interaction content obtained from the user's query can be incorporated into the medical preference collection card and editable. Furthermore, the medical preference collection card can also include second interaction content. For example, the second interaction content includes medical needs, supporting requests for outpatient assistance, inpatient assistance, and online consultations. The first interaction content can include hospital level, doctor level, and desired treatment area obtained based on hospital, department, and address (where the address can be determined using the user's real-time address, rather than being the target slot).

[0118] Furthermore, if a user selects online consultation as their medical need on the interactive interface, there's no need to recommend and display their desired consultation location. Instead, information about their condition is collected through the consultation on the current chat page and historical / interactive symptom descriptions. This information is then used to recommend and conduct online consultations with doctors based on the selected desired consultation information. For example, in the case of online doctor consultations, the recommended doctor information can serve as an entry point for the online consultation, allowing users to access it by clicking the link.

[0119] If a user selects outpatient assistance or inpatient assistance in the user interface, the interface should display the desired treatment location and allow the user to edit it. Based on the user's selection of whether to seek medical treatment offline, the interface should confirm whether to display offline treatment information and suggestions. If the user chooses offline treatment, the interface should display the above information and allow the user to add offline treatment information and suggestions through editing, then proceed to supplementing the issues to be resolved for this treatment. If the above information is not displayed, the user should directly proceed to supplementing the issues to be resolved for this treatment. Afterwards, based on the displayed and edited desired treatment location on the interface, the user can confirm the time and request offline doctor recommendations.

[0120] In some embodiments, the hospital level in the first interactive content can be a required interactive content that supports multiple selections. When the interactive interface is triggered, one option can be displayed by default, and users can edit it. The disease symptom description in the first interactive content is an optional interactive content that supports multiple selections, allowing users to select 2 to 4 or more pieces of information. When the interactive interface is triggered, it can be in a collapsed state by default (but users can expand and select). The medical needs, doctor level, expected appointment time, expected appointment location, and whether to seek medical treatment offline in the second interactive content are all required content (the interaction logic is similar to the required interactive content in the first interactive content, and will not be repeated here). They support single selection, multiple selection, single selection, single selection, and single selection, respectively. When the interactive interface is triggered, one option can be displayed by default. In addition, the problem to be solved in the second interactive content can be an optional option that supports user input.

[0121] According to embodiments of this disclosure, the intent to seek medical treatment in input text is identified by: determining the degree of matching between the semantic features of the input text and the semantic features of a plurality of predetermined intents, wherein the plurality of predetermined intents includes the intent to seek medical treatment; and determining the intent of the input text as the intent to seek medical treatment when the degree of matching between the semantic features of the input text and the semantic features of the intent to seek medical treatment meets predetermined conditions.

[0122] For example, natural language processing techniques can be used to extract features from the input text, thereby transforming the input text into a vector representation that the computer can understand. This vector representation can serve as semantic features, such as those obtained through models like Word2Vec and BERT.

[0123] In addition to the intention to seek medical treatment, multiple pre-arranged intentions may also include the intention to inquire about drug information, the intention to look up hospital addresses, the intention to understand medical insurance policies, the intention to make complaints and suggestions, the intention to chat, and other common intentions that users may have in medical-related scenarios.

[0124] Each predetermined intent can have its corresponding semantic features pre-stored. Then, the similarity between the semantic features of the input text and the semantic features of each predetermined intent can be directly determined, and this similarity can be used as the matching score. For example, this similarity score can be cosine similarity, Euclidean distance, etc. If the matching score between the semantic features of the input text and the semantic features of the medical treatment intent reaches or exceeds a threshold (i.e., meets the predetermined conditions), the intent of the input text is determined to be the medical treatment intent.

[0125] For example, if a user enters "I've had a bad cough lately and want to go to the hospital, which department should I go to?", after feature extraction of the input text, the similarity between the semantic features of the input text and the semantic features of the intention to seek medical treatment is 0.85, which is greater than the preset threshold of 0.7. Therefore, the intention of the input text is determined to be the intention to seek medical treatment.

[0126] According to embodiments of this disclosure, displaying an interactive interface for obtaining medical preferences in response to input text representing a medical treatment intention from an object input includes: performing slot recognition on the input text representing a medical treatment intention from an object input to obtain a slot recognition result; if the slot recognition result indicates that the input text includes multiple target slots for triggering the interactive interface, inputting the multiple target slots into a first large model to generate at least one first interactive content; and rendering and displaying the interactive interface based on at least one first interactive content and an interactive interface rendering template.

[0127] If word segmentation was performed during the intent recognition stage of the input text, the semantic features of the segmented keywords can be directly reused here. By calculating the matching degree between each keyword semantic feature and the keyword semantic features of multiple pre-constructed target slots, the slot recognition result is obtained. The slot recognition result indicates whether the input text includes multiple target slots used to trigger the interactive interface.

[0128] Target slots are typically predetermined. For example, target slots may include: disease direction and / or disease department. The object's address information and hospital name / level can be selected as target slots as needed. Alternatively, disease direction and / or disease department can be mandatory target slots, while address information and hospital name / level can be optional. The interactive interface is triggered whenever disease direction and / or disease department are detected. For example, for the input text "I've had a terrible headache lately and want to see a doctor. Which department should I go to?", the system will identify "head" as belonging to the "disease direction" slot or match it to the disease department "neurology".

[0129] Considering the differences in users' expressive abilities and their grasp of medical knowledge, there may be instances of colloquial expressions, vague symptom descriptions, and mixed use of disease terms, making it difficult to accurately extract effective target slot information when directly identifying slots. Therefore, in one specific embodiment, for the disease direction, the keyword can first be expanded with synonyms, and then the semantic features of at least one expanded synonym can be matched with the target slot; alternatively, compared to other target slots, the matching degree restriction between the semantic features of the keyword in the disease direction and the semantic features of the keyword in the corresponding target slot can be reduced (e.g., the comparison threshold can be lowered) to achieve fuzzy matching.

[0130] For information such as disease department, address, hospital name / level, etc., this part of the information is usually closely related to the user's medical preferences and usually has relatively well-known descriptions. Therefore, exact matching can be used for slot matching of this part of the keywords.

[0131] If the input text reveals information related to the user's medical preferences, the target slot can be input into the first main model to expand and generate the first interactive content.

[0132] For example, if the target slot in the input text includes "thyroid", after inputting "thyroid" into the first major model, the first major model can analyze the pathophysiological association between "thyroid" diseases and various symptoms. For example, abnormal secretion of thyroid hormones may affect the cardiovascular system, leading to related symptoms such as "chest tightness". Hyperthyroidism is often accompanied by symptoms such as "palpitations", "excessive sweating", and "weight loss". Thyroiditis may cause "neck pain" and "fever". Large thyroid nodules may cause "difficulty swallowing" and "neck pressure". Thus, the first interactive content such as disease symptom descriptions can be generated so that users can display the above symptoms on the interactive interface and supplement medical preference information through selection operations.

[0133] Alternatively, after inputting "thyroid" into the primary model, the model can further analyze the hospital levels and departmental setups under "thyroid" diseases. For example, tertiary hospitals typically have specialized endocrinology departments to diagnose and treat thyroid-related diseases, and some general hospitals also have specialized outpatient clinics in thyroid surgery for conditions such as thyroid nodules and tumors requiring surgical treatment. Community hospitals or secondary hospitals may only handle basic issues such as preliminary thyroid function screening within the scope of general practice or internal medicine. Based on this, the model generates hospital levels that can provide thyroid treatment services.

[0134] Understandably, the first major model can use the target slot and at least one prompt word template to obtain the above-mentioned disease symptom description and / or hospital level.

[0135] An interactive interface rendering template can be a pre-designed layout framework and style set for presenting interactive content on a user terminal interface (UI). For example, it can include setting which controls and interactive logic for which primary interactive content.

[0136] In the embodiments of this disclosure, after the first model generates first interactive content related to medical treatment preferences based on multiple target slots extracted from the input text, the first interactive content is filled into the corresponding interactive interface rendering template, so that the interactive interface can be quickly rendered and displayed, allowing users to smoothly interact with medical treatment preferences during the conversation.

[0137] According to embodiments of this disclosure, the method further includes: when the slot identification result indicates that the input text includes multiple target slots for triggering the interactive interface, obtaining at least one predetermined second interactive content; and rendering and displaying the interactive interface based on at least one first interactive content, the second interactive content, and the interactive interface rendering template.

[0138] For the predetermined second interactive content, the corresponding format can be pre-set in the interactive interface rendering template. After obtaining the second interactive content from the local machine or the cloud, the second interactive content and the first interactive content can be filled into the corresponding interactive interface rendering template to quickly render and display the interactive interface, so that users can smoothly interact with their medical preferences during the dialogue.

[0139] In another embodiment, the predetermined second interactive content can be merged with the interactive interface rendering template. During the rendering stage, the first interactive content can be directly filled into the interactive interface rendering template containing the second interactive content.

[0140] For example, during the design phase of the interactive interface rendering template, the fixed display area, style (such as font size, color, border style, etc.), and default fill text of the second interactive content are integrated into the template's underlying architecture. After the first interactive content is generated from the first main model, there is no need to retrieve the second interactive content separately from local or cloud sources. Instead, the second interactive content already integrated into the template, along with the real-time generated first interactive content, is used directly to quickly complete the construction and display of the entire interactive interface.

[0141] In the embodiments of this disclosure, the first and second interactive content are processed quickly through the interactive interface rendering template, which can quickly render and display the interactive interface so that users can smoothly interact with their medical preferences during the dialogue.

[0142] According to embodiments of this disclosure, the medical referral information includes a recommendation reason and at least one recommended doctor information. The method further includes: selecting at least one recommended doctor information from a candidate doctor database based on multiple target slots and medical preference information in the input text; and inputting at least one recommended doctor information and medical preference information into a second model to generate a recommendation reason.

[0143] Considering that the target slots in the input text usually represent the user's core medical needs, and that medical preference information can be used as supplementary and improved medical needs, in order to avoid the core medical needs being affected by medical preference information, when making doctor recommendations, multiple target slots obtained by slot recognition of the input text and medical preference information obtained through interaction are used together as input for the doctor recommendation operation.

[0144] For example, the target slot and the various sub-preference information in the medical preference information can be processed into structured data (such as fields and field values). Then, the structured data can be used as matching conditions to perform multi-dimensional filtering in the candidate doctor database through a preset matching algorithm. The candidate doctor database is a pre-maintained database of doctors that supports at least one medical need (such as online consultation, outpatient assistance, and inpatient assistance).

[0145] For example, if a user's target slot is "allergic rhinitis" and they need an "ENT" doctor, and their medical preference information is "weekend clinic", then the system will first filter out all ENT doctors who are good at treating allergic rhinitis from the candidate doctor database, and then further filter out doctors who have weekend clinic schedules.

[0146] After determining the information of each recommended doctor, the second model can extract the core elements of the recommended doctor information that match the user's preference information based on the semantic relationship between the recommended doctor information and the medical preference information, and organize them into a natural language description in a logical order to form the recommendation reason.

[0147] In the embodiments of this disclosure, target slots and medical preference information can be used to determine recommended doctor information that meets both core medical needs and personalized preferences, thereby improving the accuracy of doctor recommendations and user experience. Furthermore, since the user's original input typically only includes text, and the entire recommendation process involves multiple interactive operations and stages, to facilitate the integration of all information throughout the interaction process and optimize the contextual dialogue experience, recommendation reasons can be generated based on medical preference information and recommended doctor information. This allows users to intuitively understand the preference matching logic throughout the interaction, resulting in a better user experience.

[0148] According to embodiments of this disclosure, the medical preference information includes multiple sub-preference information, and each of the multiple sub-preference information and multiple target slots has a matching priority; based on the multiple target slots and medical preference information in the input text, at least one recommended doctor information is selected from the candidate doctor database, including: if the candidate doctor database does not contain recommended doctor information that matches all of the multiple target slots and multiple sub-preference information, a predetermined number of recommended doctor information is selected from the candidate doctor database according to the matching priority of each of the multiple sub-preference information and multiple target slots.

[0149] Understandably, the more matching criteria used, the fewer recommended doctors will meet all of them, and there may even be cases where none of the criteria are met. Therefore, while ensuring that users have certain medical preferences, it is preferable to reduce the number of matching criteria.

[0150] Matching priority indicates the priority at which sub-preference information and / or target slots are used to filter recommended doctor information. The higher the matching priority, the earlier it is used as a matching condition.

[0151] In one embodiment, the matching priority of the target slot is higher than the matching priority of the sub-preference information, so as to ensure that the core needs in the input text are guaranteed before filtering the medical preference information.

[0152] In another embodiment, there may be differences in matching priorities among multiple target slots, and there may also be differences in matching priorities among multiple sub-preference information. For example, if the target slots include disease direction and disease department, the matching priority of disease direction is higher than that of disease department (the recommended doctor information can be determined by fuzzy matching for disease direction); if the multiple sub-preference information includes at least one first sub-preference information for at least one first interaction content and / or at least one second sub-preference information for at least one second interaction content, then the matching priority of the first sub-preference information may be higher than that of the second sub-preference information.

[0153] In one specific embodiment, the matching priority of disease direction, disease department, desired treatment area, hospital level, doctor level, and expert tags (such as whether the expert is a well-known expert) decreases in that order. When matching layer by layer according to the above matching priority, if there are 0 recommended doctors that match all four of the medical preference information (disease direction, disease department, desired treatment area, hospital level, and doctor level), one or more recommended doctors that match all four of the doctor level information can be returned. For example, if a total of 4 recommended doctors are matched, these 4 are returned. In other embodiments, if the candidate doctor database does not include recommended doctors that match multiple target slots and multiple sub-preference information, a human interaction portal can be displayed. After the user operates the human interaction portal, auxiliary personnel (such as customer service, online consultants, or doctors specializing in medical resource recommendations) can be accessed on the dialogue page or other windows to interact with the user and complete the doctor information recommendation.

[0154] Furthermore, to reduce the amount of recommended doctor information that can be displayed on the dialogue page, and to decrease the difficulty of selection and browsing costs, the number of recommended doctors in the medical guidance information can be limited by quantity rules. For example, if the predetermined quantity is 3, and the number of recommended doctors matched according to the matching priority above is 4, then only the top 3 recommended doctors that best match the medical preference information and target slot can be returned. Similarly, if the number of recommended doctors that satisfy all medical preference information and target slots is 5, then the top 3 that best match the medical preference information and target slot can be returned.

[0155] In the embodiments of this disclosure, by limiting the matching priority, the selection of recommended doctor information can first meet the user's core medical needs, and then meet other more comprehensive information. Furthermore, the embodiments of this disclosure can also avoid situations where no recommended doctor information is returned and displayed if all matching conditions are not met, thus improving the user experience.

[0156] Figure 7A block diagram illustrating an interactive device for medical consultation guidance according to an embodiment of the present disclosure is shown schematically. Figure 7 As shown, the interactive device 700 for medical guidance includes a first display module 710, a second display module 720 and a third display module 730.

[0157] The first display module 710 is used to display an interactive interface for obtaining medical treatment preferences in response to input text representing the intention to seek medical treatment from an object input, wherein the interactive interface includes at least one first interactive content generated by the first model based on the input text.

[0158] The second display module 720 is used to respond to the object's interactive operation on the interactive interface, obtain and display the object's medical preference information, wherein the medical preference information includes first sub-preference information obtained from the interactive operation on the first interactive content;

[0159] The third display module 730 is used to display medical guidance information generated based on medical preference information, wherein the medical guidance information is used to guide the subject to perform the medical process.

[0160] According to an embodiment of this disclosure, the second display module 720 includes: a first acquisition submodule, configured to acquire first sub-preference information in response to an object's selection operation on at least one first interactive content; and a first display submodule, configured to cancel the display of the interactive interface and display the medical preference information in the form of dialogue text in response to an object's confirmation operation on the interactive interface.

[0161] According to embodiments of this disclosure, the interactive interface further includes at least one predetermined second interactive content. The second display module 720 includes a first acquisition submodule, configured to acquire first sub-preference information in response to an object's selection operation on at least one first interactive content; a second acquisition submodule, configured to acquire second sub-preference information in response to an object's interactive operation on at least one second interactive content; and a first display submodule, configured to cancel the display of the interactive interface and display medical preference information in the form of dialogue text in response to an object's confirmation operation on the interactive interface, wherein the medical preference information further includes the second sub-preference information.

[0162] According to embodiments of this disclosure, the first interactive content includes: a mandatory interactive content first display submodule includes: a first display unit, configured to, in response to a confirmation operation by an object on the interactive interface, display prompt information for prompting the operation of the mandatory interactive content when the selection operation for at least one first interactive content does not include the selection operation for the mandatory interactive content; and a second display unit, configured to, when the selection operation for at least one first interactive content includes the selection operation for the mandatory interactive content, cancel the display of the interactive interface and display medical preference information in the form of dialogue text.

[0163] According to embodiments of this disclosure, the mandatory interactive content includes a hospital level generated based on the disease department and / or disease direction in the input text; the first interactive content also includes optional interactive content, which includes a description of disease symptoms generated based on the disease department and / or disease direction.

[0164] According to embodiments of this disclosure, a single mandatory interactive content includes multiple sub-interactive content, and the second display unit includes: a first display subunit, used to cancel the display of the interactive interface and display medical preference information in the form of dialogue text when the selection operation for the mandatory interactive content includes the selection operation for one or more sub-interactive content.

[0165] According to embodiments of this disclosure, the medical referral information includes a recommendation reason and at least one recommended doctor's information; the third display module 730 includes: a second display submodule, used to display the recommendation reason and at least one recommended doctor's information through an interactive card control.

[0166] According to embodiments of this disclosure, the interactive card control further includes a preference modification control; the second display submodule is further configured to: display an interactive interface in response to a trigger operation on the preference modification control, so that the object can modify its medical preference information through interactive operations on the interactive interface.

[0167] According to an embodiment of this disclosure, the first display module 710 includes: a third display submodule for displaying a dialogue page for online triage, wherein the dialogue page is triggered through a channel entry for representing medical treatment intention; and a fourth display submodule for displaying an interactive interface for obtaining medical treatment preferences in response to an object inputting input text on the dialogue page, provided that the intent of the input text is identified as a medical treatment intention.

[0168] According to embodiments of this disclosure, the intent to seek medical treatment in input text is identified by: determining the degree of matching between the semantic features of the input text and the semantic features of a plurality of predetermined intents, wherein the plurality of predetermined intents includes the intent to seek medical treatment; and determining the intent of the input text as the intent to seek medical treatment when the degree of matching between the semantic features of the input text and the semantic features of the intent to seek medical treatment meets predetermined conditions.

[0169] According to an embodiment of this disclosure, the first display module 710 includes: an identification submodule, configured to perform slot identification on the input text representing a medical treatment intention in response to an input text representing a medical treatment intention, and obtain a slot identification result; a generation submodule, configured to input multiple target slots into a first large model to generate at least one first interactive content when the slot identification result represents that the input text includes multiple target slots for triggering an interactive interface; and a first rendering submodule, configured to render and display an interactive interface based on at least one first interactive content and an interactive interface rendering template.

[0170] According to an embodiment of this disclosure, the first display module 710 further includes: an acquisition submodule, configured to acquire at least one predetermined second interactive content when the slot identification result indicates that the input text includes multiple target slots for triggering the interactive interface; and a second rendering submodule, configured to render and display the interactive interface based on at least one first interactive content, the second interactive content, and the interactive interface rendering template.

[0171] According to embodiments of this disclosure, the medical referral information includes a recommendation reason and at least one recommended doctor information. The device further includes: a filtering module, used to filter at least one recommended doctor information from a candidate doctor database based on multiple target slots and medical preference information in the input text; and a generation module, used to input at least one recommended doctor information and medical preference information into a second model to generate a recommendation reason.

[0172] According to embodiments of this disclosure, the medical preference information includes multiple sub-preference information, and each of the multiple sub-preference information and multiple target slots has a matching priority; the filtering module is further configured to: when the candidate doctor database does not contain recommended doctor information that matches multiple target slots and multiple sub-preference information, filter out a predetermined number of recommended doctor information from the candidate doctor database according to the matching priority of each of the multiple sub-preference information and multiple target slots.

[0173] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present 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, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present 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 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, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0174] It should be noted that the apparatus portion in the embodiments of this disclosure corresponds to the method portion in the embodiments of this disclosure. The description of the apparatus portion is specifically referred to in the method portion, and will not be repeated here.

[0175] Figure 8A block diagram of an electronic device suitable for implementing an interactive method for medical guidance according to an embodiment of the present disclosure is shown schematically. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0176] like Figure 8 As shown, an electronic device 800 according to an embodiment of this disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 into a random access memory (RAM) 803. The processor 801 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 801 may also include onboard memory for caching purposes. The processor 801 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.

[0177] RAM 803 stores various programs and data required for the operation of electronic device 800. Processor 801, ROM 802, and RAM 803 are interconnected via bus 804. Processor 801 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 802 and / or RAM 803. It should be noted that the programs may also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 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.

[0178] According to embodiments of this disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the input / output (I / O) interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0179] 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 809, and / or installed from removable medium 811. When the computer program is executed by processor 801, 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.

[0180] 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.

[0181] 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.

[0182] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0183] 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 information display methods provided in the embodiments of this disclosure.

[0184] When the computer program is executed by the processor 801, 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.

[0185] 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 may be downloaded and installed via the communication section 809, and / or installed from a removable medium 811. 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.

[0186] 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).

[0187] 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.

[0188] 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. An interactive method for medical triage, comprising: In response to input text representing a medical treatment intention from object input, an interactive interface for obtaining medical treatment preferences is displayed, wherein the interactive interface includes at least one first interactive content generated by a first model based on the input text; In response to the object's interactive operation on the interactive interface, the medical treatment preference information of the object is obtained and displayed, wherein the medical treatment preference information includes first sub-preference information obtained from the interactive operation on the first interactive content; The system displays medical guidance information generated based on the medical preference information, wherein the medical guidance information is used to guide the subject in performing the medical treatment process.

2. The method according to claim 1, wherein, The step of obtaining and displaying the object's medical preference information in response to the object's interactive operation on the interactive interface includes: In response to the object's selection operation for at least one of the first interactive contents, the first sub-preference information is obtained; In response to the object's confirmation operation on the interactive interface, the interactive interface is canceled from display, and the medical preference information is displayed in the form of dialogue text.

3. The method according to claim 1, wherein, The interactive interface further includes at least one pre-determined second interactive content, and the step of obtaining and displaying the object's medical preference information in response to the object's interactive operation on the interactive interface includes: In response to the object's selection operation for at least one of the first interactive contents, the first sub-preference information is obtained; In response to the object's interaction with at least one of the second interactive contents, second sub-preference information is obtained; In response to the object's confirmation operation on the interactive interface, the interactive interface is canceled from display, and the medical preference information is displayed in the form of dialogue text, wherein the medical preference information further includes the second sub-preference information.

4. The method according to claim 2 or 3, wherein, The first interactive content includes: mandatory interactive content. The step of responding to the object's confirmation operation on the interactive interface, canceling the display of the interactive interface, and displaying the medical preference information in the form of dialogue text includes: In response to the object's confirmation operation on the interactive interface, If the selection operation for at least one of the first interactive contents does not include the selection operation for the required interactive content, a prompt message for prompting the operation of the required interactive content is displayed; If the selection operation for at least one of the first interactive contents includes the selection operation for the required interactive content, the interactive interface is canceled and the medical preference information is displayed in the form of dialogue text.

5. The method according to claim 4, wherein, The mandatory interactive content includes the hospital level generated based on the disease department and / or disease direction in the input text; The first interactive content also includes optional interactive content, which includes: a description of disease symptoms generated based on the disease department and / or the disease direction.

6. The method according to claim 4, wherein, A single required interactive content includes multiple sub-interactive content. When a selection operation for at least one of the first interactive content includes a selection operation for the required interactive content, canceling the display of the interactive interface and displaying the medical preference information in the form of dialogue text includes: If the selection operation for the required interactive content includes the selection operation for one or more of the sub-interactive content, the interactive interface is canceled and the medical preference information is displayed in the form of dialogue text.

7. The method according to claim 1, wherein, The medical guidance information includes the reasons for the recommendation and information on at least one recommended doctor; The display of medical guidance information generated based on the medical preference information includes: The reason for the recommendation and information on at least one recommended doctor are displayed through an interactive card control.

8. The method according to claim 7, wherein, The interactive card control also includes a preference modification control; the method further includes: In response to a triggering operation on the preference modification control, the interactive interface is displayed so that the object can modify the medical preference information through interactive operations on the interactive interface.

9. The method according to claim 1, wherein, The input text representing the intention to seek medical treatment, which responds to object input, displays an interactive interface for obtaining medical treatment preferences, including: Displays a dialogue page for online triage, wherein the dialogue page is triggered through a channel entry used to represent the intention to seek medical treatment; In response to the object inputting the input text on the dialog page, if the intent of the input text is recognized as the intent to seek medical treatment, an interactive interface for obtaining medical treatment preferences is displayed.

10. The method according to claim 1 or 9, wherein, The intent to seek medical treatment in the input text is identified in the following way: Determine the matching degree between the semantic features of the input text and the semantic features of multiple predetermined intentions, wherein the multiple predetermined intentions include the intention to seek medical treatment; and If the matching degree between the semantic features of the input text and the semantic features of the medical treatment intention meets a predetermined condition, the intention of the input text is determined to be the medical treatment intention.

11. The method according to claim 1, wherein, The interactive interface for obtaining medical treatment preferences, which responds to input text representing the intent to seek medical treatment in response to object input, includes: In response to input text representing the intention to seek medical treatment, slot identification is performed on the input text to obtain slot identification results; If the slot identification result indicates that the input text includes multiple target slots for triggering the interactive interface, the multiple target slots are input into the first large model to generate the at least one first interactive content; Based on the at least one first interactive content and the interactive interface rendering template, the interactive interface is rendered and displayed.

12. The method according to claim 11, wherein, The method further includes: If the slot identification result indicates that the input text includes multiple target slots for triggering the interactive interface, at least one predetermined second interactive content is obtained. Based on the at least one first interactive content, the second interactive content, and the interactive interface rendering template, the interactive interface is rendered and displayed.

13. The method according to claim 1, wherein, The medical referral information includes a reason for recommendation and information on at least one recommended doctor; the method further includes: Based on multiple target slots in the input text and the medical preference information, at least one recommended doctor is selected from the candidate doctor database; and Input at least one of the recommended doctor's information and the medical treatment preference information into the second large model to generate the recommendation reason.

14. The method according to claim 13, wherein, The medical preference information includes multiple sub-preference information, and each of the multiple sub-preference information and the multiple target slots has a matching priority; the step of filtering at least one of the recommended doctor information from the candidate doctor database based on the multiple target slots in the input text and the medical preference information includes: If the candidate doctor database does not contain recommended doctor information that matches multiple target slots and multiple sub-preference information, a predetermined number of recommended doctor information are selected from the candidate doctor database according to the matching priority of each of the multiple sub-preference information and multiple target slots.

15. An interactive device for medical consultation guidance, comprising: The first display module is used to display an interactive interface for obtaining medical treatment preferences in response to input text representing the intention to seek medical treatment from an object input, wherein the interactive interface includes at least one first interactive content generated by the first model based on the input text. The second display module is used to respond to the object's interactive operation on the interactive interface, acquire and display the object's medical treatment preference information, wherein the medical treatment preference information includes first sub-preference information obtained from the interactive operation on the first interactive content; The third display module is used to display medical guidance information generated based on the medical preference information, wherein the medical guidance information is used to guide the object to perform the medical process.

16. An electronic device comprising: One or more processors; Memory, used to store one or more programs. 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 14.

17. 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 14.

18. 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 14.

Images