Intelligent medical inquiry method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention provides an intelligent medical inquiry method, device and equipment and a computer readable storage medium. The intelligent medical inquiry method provided by the embodiment of the invention is applied to a man-machine conversation application program, and the method comprises the following steps: in response to the situation that a user accesses the man-machine conversation application program through one of multiple access modes used for accessing the man-machine conversation application program, presenting a man-machine conversation interface; displaying one or more pieces of recommendation prompt information in the man-machine conversation interface, wherein the one or more pieces of recommendation prompt information are used for triggering the man-machine conversation application program to output reply associated with the medical scene; wherein the one or more pieces of recommendation prompt information are matched with one access mode in the multiple access modes.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more specifically, to an intelligent medical consultation method, device, equipment, and computer-readable storage medium. Background Art

[0002] As an important branch of computer science, human-computer dialogue interaction is used to realize natural language communication between humans and computers. Human-computer dialogue is an important challenge for artificial intelligence technology. With the rapid development of artificial intelligence, the research on human-computer dialogue is becoming more and more popular. The main goal of human-computer dialogue interaction technology is to enable computers to understand and generate human language and have natural conversations with humans. This requires computers to have multiple capabilities such as natural language processing, machine learning, and knowledge representation. In recent years, with the breakthrough of deep learning technology, human-computer dialogue interaction technology has made great progress. Deep learning models can learn language patterns and semantic knowledge from massive text data, thereby improving the computer's ability to understand and generate natural language.

[0003] At present, human-computer dialogue interaction technology has become the core technology of many intelligent dialogue applications, greatly affecting the efficiency and convenience of human-computer interaction. For example, in the medical field, medical assistants that simulate doctor consultations are a new type of medical tool that can simulate doctor consultations through human-computer dialogue interaction, thereby providing users with convenient and efficient medical services. Therefore, an effective human-computer dialogue interaction method is needed to achieve better intelligent medical consultations. Summary of the invention

[0004] Embodiments of the present disclosure provide an intelligent medical consultation method, apparatus, device, and computer-readable storage medium.

[0005] An embodiment of the present disclosure provides an intelligent medical consultation method, which is applied to a human-computer dialogue application. The method includes: in response to a user accessing the human-computer dialogue application through one of multiple access methods for accessing the human-computer dialogue application, presenting a human-computer dialogue interface; and displaying one or more recommended prompt information in the human-computer dialogue interface, wherein the one or more recommended prompt information is used to trigger the human-computer dialogue application to output a reply associated with a medical scenario; wherein the one or more recommended prompt information is adapted to the one of the multiple access methods.

[0006] According to the method of an embodiment of the present disclosure, the multiple access methods include a first access method, and the first access method includes accessing the human-computer dialogue application based on an identifier associated with a health check result of the user.

[0007] According to the method of an embodiment of the present disclosure, the identifier associated with the health check result of the user is obtained through one or more of the following operations: image recognition; near field communication; and radio frequency identification.

[0008] According to the method of an embodiment of the present disclosure, the one or more recommended prompt information adapted to the first access method include one or more of the following: the recommended prompt information regarding inquiries associated with the health check result as a whole; the recommended prompt information regarding inquiries associated with abnormal items in one or more items in the health check result; and the recommended prompt information regarding inquiries associated with a portion of items in one or more items in the health check result.

[0009] According to the method of an embodiment of the present disclosure, the multiple access methods include a second access method, which includes accessing the human-computer dialogue application in the presence of a historical human-computer dialogue, wherein in the historical human-computer dialogue, the user inputs information indicating that the user is in an unhealthy state.

[0010] According to the method of an embodiment of the present disclosure, the one or more recommended prompt information adapted to the second access mode include one or more of the following: recommended prompt information regarding an inquiry about the information indicating that the user is in an unhealthy state; and recommended prompt information regarding an inquiry about the execution status of an operation to alleviate the unhealthy state, wherein the operation to alleviate the unhealthy state is included in the reply of the human-computer dialogue application in the historical human-computer dialogue.

[0011] According to the method of an embodiment of the present disclosure, the multiple access methods include a third access method, and the third access method includes one or more of the following: accessing the human-computer dialogue application based on a user's network search for the human-computer dialogue application; accessing the human-computer dialogue application based on a user creating a new human-computer dialogue application within the human-computer dialogue application.

[0012] According to the method of an embodiment of the present disclosure, the one or more recommendation prompt information adapted to the third access mode includes one or more of the following: random recommendation prompt information; recommendation prompt information associated with the current season; and recommendation prompt information with a high selection frequency determined based on big data.

[0013] According to the method of an embodiment of the present disclosure, it also includes displaying one or more of the following function indicators in the human-computer dialogue interface: an indicator for voice calls; an indicator for taking images; and an indicator for uploading files.

[0014] According to the method of an embodiment of the present disclosure, it also includes: in response to the user accessing the human-computer dialogue application again within a time period not exceeding a first threshold after exiting the human-computer dialogue application, continuing the human-computer dialogue; and in response to the user accessing the human-computer dialogue application again after exiting the human-computer dialogue application for more than the first threshold time period, creating a new human-computer dialogue.

[0015] The method according to an embodiment of the present disclosure further includes: creating a historical human-computer dialogue for the human-computer dialogue, displaying a historical human-computer dialogue indicator in the human-computer dialogue interface, and displaying one or more created historical human-computer dialogues to the user in response to the user selecting the historical human-computer dialogue indicator.

[0016] According to the method of an embodiment of the present disclosure, the method further includes, in response to a historical human-computer dialogue selected by a user to be created, displaying the content of the human-computer dialogue corresponding to the historical human-computer dialogue and the time when the human-computer dialogue corresponding to the historical human-computer dialogue occurred in the human-computer dialogue interface.

[0017] According to the method of an embodiment of the present disclosure, the human-computer dialogue interface includes a first area and a second area, wherein the second area is configured to receive user input, wherein the user input includes text input and voice input, and wherein the first area is configured to display the one or more recommendation prompt information and the response of the human-computer dialogue application to the user input and the one or more recommendation prompt information.

[0018] According to the method of an embodiment of the present disclosure, it also includes: in response to the user continuously selecting one of the recommendation prompt information, the user input, and the response of the human-computer dialogue application for a second threshold time, displaying one or more of the following function indicators: an indicator for executing a voice broadcast function; an indicator for executing a copy function.

[0019] An embodiment of the present disclosure provides an intelligent medical consultation device, which is configured to execute a human-computer dialogue application. The device includes: a human-computer dialogue presentation module, which is configured to present a human-computer dialogue interface in response to a user accessing the human-computer dialogue application through one of multiple access methods for accessing the human-computer dialogue application; a recommendation prompt information display module, which is configured to display one or more recommendation prompt information in the human-computer dialogue interface, and the one or more recommendation prompt information is used to trigger the human-computer dialogue application to output a reply associated with a medical scenario; wherein the one or more recommendation prompt information is adapted to the one of the one or more access methods.

[0020] An embodiment of the present disclosure provides an intelligent medical consultation device, comprising: one or more processors; and one or more memories, wherein a computer executable program is stored, and when the computer executable program is executed by the processor, the above method is performed.

[0021] An embodiment of the present disclosure provides a computer-readable storage medium on which computer-executable instructions are stored. When the instructions are executed by a processor, the above method is implemented.

[0022] The method provided by the embodiments of the present disclosure generates and displays to the user recommendation prompt information that is compatible with the user's access method to the human-computer dialogue application based on the user's access method to the human-computer dialogue application, so that the user can conveniently and efficiently select the recommendation prompt information, enhance the user's trust in the human-computer dialogue application and willingness to use it, thereby greatly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some exemplary embodiments of the present disclosure, and a person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

[0024] Figure 1A is a schematic diagram showing a scenario of a human-computer dialogue according to an embodiment of the present disclosure;

[0025] Figure 1B is a schematic diagram showing a dialog interface at a user terminal according to an embodiment of the present disclosure;

[0026] Figure 2 is a flow chart showing an intelligent medical consultation method according to an embodiment of the present disclosure;

[0027] Figure 3A is a diagram of an example health check result;

[0028] Figure 3B is a schematic diagram showing a first access method according to an embodiment of the present disclosure;

[0029] Figure 4A is a schematic diagram showing a historical human-computer dialogue according to an embodiment of the present disclosure;

[0030] Figure 4B is a schematic diagram showing a second access method according to an embodiment of the present disclosure;

[0031] Figure 5 is a schematic diagram showing a third access method according to an embodiment of the present disclosure;

[0032] Figure 6 is another flow chart showing the intelligent medical consultation method according to an embodiment of the present disclosure;

[0033] Figure 7 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure;

[0034] Figure 8 A schematic diagram showing a human-machine dialogue device 800 according to an embodiment of the present disclosure; and

[0035] Fig. 9 A schematic diagram illustrating the architecture of an exemplary computing device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0037] In this specification and the accompanying drawings, substantially the same or similar steps and elements are represented by the same or similar reference numerals, and repeated descriptions of these steps and elements will be omitted. At the same time, in the description of the present disclosure, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance or ranking.

[0038] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure pertains. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0040] To facilitate description of the present disclosure, concepts related to the present disclosure are introduced below.

[0041] The intelligent medical consultation method disclosed in the present invention may be based on artificial intelligence (AI). Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. By studying the design principles and implementation methods of various intelligent machines, artificial intelligence enables the intelligent medical consultation method disclosed in the present invention to have the function of dynamically updating the category probability distribution associated with scene classification in real time and accurately according to the feedback information input by the user for the question and displaying it to the user.

[0042] The intelligent medical consultation method disclosed in the present invention can be based on natural language processing (Natural Language Processing, NLP). Natural language processing is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that can achieve effective communication between people and computers using natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field will involve natural language, that is, the language used by people in daily life, so it is closely related to the study of linguistics. Natural language processing technology generally includes text processing, semantic understanding, machine translation, robot question answering, knowledge graphs and other technologies.

[0043] The intelligent medical consultation method disclosed in the present invention can be based on a large language model (LLM). A large language model is a language model in the field of NLP that is trained on a large amount of language corpus using an autoregressive method for analyzing and processing language texts, and is intended to understand and generate human language. The large language model is trained on a large amount of text data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, and the like. The large language model is characterized by its large scale, which can contain billions of parameters to help it learn complex patterns in language text data. Therefore, in the intelligent medical consultation method disclosed in the present invention, the trained large language model can be applied to interactive information processing in human-computer dialogue interaction to provide efficient and accurate dialogue services, thereby improving the user experience.

[0044] In summary, the solutions provided by the embodiments of the present disclosure involve technologies such as artificial intelligence, natural language processing, and large language models. The embodiments of the present disclosure will be further described below in conjunction with the accompanying drawings. In summary, the solutions provided by the embodiments of the present disclosure involve technologies such as artificial intelligence, natural language processing, and large language models. The embodiments of the present disclosure will be further described below in conjunction with the accompanying drawings.

[0045] Figure 1A It is a schematic diagram showing a scenario of human-computer dialogue interaction according to an embodiment of the present disclosure. Figure 1B is a schematic diagram showing a dialog interface at a user terminal according to an embodiment of the present disclosure.

[0046] like Figure 1A As shown, the user can send user input (for example, a request for obtaining information from the server, or a question from the user to the server) to the server through the user terminal, so that the server can reply to the user input. Subsequently, the server can return the generated machine reply information to the user terminal through the network. Optionally, the user terminal may specifically include a smart phone, a tablet computer, a laptop, a desktop computer, a vehicle-mounted terminal, a wearable device, etc., but is not limited to this. The user terminal can also be a client that installs a browser or various applications (including system applications and third-party applications). Optionally, the network can be an Internet of Things based on the Internet and / or telecommunications network, which can be a wired network or a wireless network. For example, it can be a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a cellular data communication network, etc., which can realize an electronic network that can realize an information exchange function. The user terminal and the server can be directly or indirectly connected by wired or wireless communication, and this application is not limited here. Optionally, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Figure 1A In addition to the interaction scenarios shown, human-computer dialogue interaction can be implemented only on the user terminal side, and the present disclosure does not limit this. For example, a functional module for human-computer dialogue interaction can be deployed on the user terminal side, so that the user terminal can independently implement human-computer dialogue interaction without relying on the server.

[0047] The construction of intelligent assistants based on LLM is one of the important research directions in the field of NLP. As an NLP model based on deep learning, LLM has a wide range of applications, including language generation, text classification, information retrieval, etc. At present, the intelligent assistant construction scheme based on LLM mainly involves inputting relevant knowledge during the LLM training process, training LLM through autoregressive tasks, so that it has the ability of intelligent question answering. In this scheme, LLM is regarded as a general intelligent model that can learn and simulate human language ability, thereby realizing natural language understanding and generation. Therefore, the intelligent assistant construction scheme based on LLM has important research and application value, especially for intelligent assistants in specific fields (such as law, medical care, customer service, etc.), which is currently a very promising application scheme.

[0048] In the construction of intelligent assistants based on LLM, human-computer dialogues can include three types: task completion, question and answer, and chat, depending on the function. Among them, the task completion type of human-computer dialogue interaction can be mainly used to complete the user's specific task requirements, such as movie ticket reservations, air ticket reservations, music playback, etc. The characteristics of this type of dialogue are that the user needs are clear and often need to be solved through multiple rounds. As an example, in the medical field, a medical assistant that simulates a doctor's consultation is a new type of medical tool that can truly simulate a doctor's consultation through a task completion type of human-computer dialogue interaction, thereby providing users with convenient and efficient medical services.

[0049] The above-mentioned medical assistants have become a technology that has attracted much attention in the medical field. They can be used to understand users' queries and extract relevant medical information, store structured knowledge about diseases, symptoms and treatment plans, and predict possible diseases based on users' symptoms and medical history. Figure 1B As shown, the user and the medical assistant can interact through text dialogue. For example, when the user accesses the medical assistant, the medical assistant can display one or more recommended prompts to the user, such as "What habits before bedtime affect blood sugar?", "What foods before bedtime can easily make you fat?" and "The benefits of exercising before bedtime?".

[0050] like Figure 1BAs shown, in the interaction process of the existing medical assistant as described above, when the user accesses the medical assistant, no matter how the user accesses the medical assistant, the medical assistant always displays fixed recommendation prompt information to the user. However, such recommendation prompt information may have a low correlation with the user's expectations. For example, most (if not all) of one or more recommendation prompts may not be expected by the user, so the user may not select one or more recommendation prompts but choose to manually enter the prompt information. In addition, if the medical assistant displays one or more recommendation prompts that are fixed and not expected by the user in each visit of the user during multiple visits to the medical assistant, the user may feel uncomfortable and therefore will reduce the trust in the medical assistant and the willingness to continue using the medical assistant.

[0051] Based on this, the present disclosure provides an intelligent medical consultation method, which is applied to a human-computer dialogue application. The method includes: in response to a user accessing the human-computer dialogue application through one of multiple access methods for accessing the human-computer dialogue application, presenting a human-computer dialogue interface; and displaying one or more recommendation prompt information in the human-computer dialogue interface, the one or more recommendation prompt information being used to trigger the human-computer dialogue application to output a reply associated with a medical scenario; wherein the one or more recommendation prompt information is adapted to one of the multiple access methods.

[0052] The intelligent medical consultation method disclosed in the present invention can provide a more accurate and convenient consultation experience, wherein, based on the user's access method to the human-computer dialogue application, recommendation prompt information that is compatible with the user's access method to the human-computer dialogue application can be generated and displayed to the user, allowing the user to conveniently and efficiently select the recommendation prompt information, thereby enhancing the user's trust in the human-computer dialogue application and willingness to use it, thereby greatly improving the user experience.

[0053] Figure 2 Detailed description is a flow chart showing an intelligent medical consultation method according to an embodiment of the present disclosure.

[0054] like Figure 2 As shown, the intelligent medical consultation method may include steps S210 and S220. The intelligent medical consultation method may be performed by a medical assistant. Hereinafter, the human-computer dialogue program may also be referred to as a medical assistant.

[0055] In step S210, in response to a user accessing the human-machine dialogue application through one of the multiple access methods for accessing the human-machine dialogue application, a human-machine dialogue interface may be presented. For example, there may be multiple access methods for a user to access the human-machine dialogue application. When a user accesses the human-machine dialogue application, the user may access the application through one of the multiple access methods. The human-machine dialogue program may determine the access method used by the user for access.

[0056] In step S220, one or more recommendation prompt information may be displayed in the human-computer dialogue interface, and the one or more recommendation prompt information is used to trigger the human-computer dialogue application to output a reply associated with the medical scenario, wherein the one or more recommendation prompt information is adapted to one of the multiple access methods. For example, one or more recommendation prompt information may be displayed in the human-computer dialogue area in the human-computer dialogue interface. The one or more recommendation prompt information may be prompt information associated with the medical scenario, so such recommendation prompt information may be used to trigger the human-computer dialogue application to output a reply associated with the medical scenario. In addition, the one or more recommendation prompt information displayed in the human-computer dialogue interface such as the human-computer dialogue area may be associated with the access method for the user to access the human-computer dialogue program. For example, the one or more recommendation prompt information may be specific to the access method for the user to access the human-computer dialogue program. In this way, the user can conveniently and efficiently select the recommendation prompt information, enhance the user's trust in the human-computer dialogue application and willingness to use, thereby greatly improving the user experience.

[0057] Figure 3A A diagram of health check results that may be an example. Figure 3B is a schematic diagram showing a first access method according to an embodiment of the present disclosure. Figure 3B It may be a human-machine dialogue interface displayed by the human-machine dialogue application when the user accesses the human-machine dialogue application through a first access method among multiple access methods for accessing the human-machine dialogue application.

[0058] Figure 3A The health check results shown may be health check results of the user made by a medical service institution such as a clinic, hospital, or physical examination center. For example, a user may go to the above medical service institution due to physical discomfort, undergo an examination at the above medical service institution, and the above medical service institution makes the above health check results. The health check results may include a check list, a pathology report, and other offline activities related to the health check results. The health check results may be physical or virtual. For example, Figure 3A As shown, the health check result can be implemented in a printed form on a physical form such as paper, etc. For another example, the health check result can be implemented in an electronic document in the form of electronic data.

[0059] like Figure 3A As shown, the health check result may be a biochemical test result of the user's blood. The health check result may include items such as "total cholesterol", "high-density lipoprotein", "low-density lipoprotein", "triglycerides", "lipoprotein", "AST", "ALT", "blood sugar", and "glycosylated hemoglobin". Figure 3A As shown, the "glutamic oxaloacetate aminotransferase" in the items included in the health check result exceeds the normal range, and the other items included in the health check result are within the normal range. The health check result may include a two-dimensional pattern 301 implemented in the form of a two-dimensional code for obtaining an identifier associated with the health check result of the user. Figure 3A The two-dimensional pattern 301 is shown in the form of a two-dimensional code, but those skilled in the art will appreciate that the two-dimensional pattern 301 may also be implemented in the form of a quick response (QR) code, a barcode, etc. Although not shown, Figure 3A The health check results shown may also include a chip, etc. for obtaining an identifier associated with the user's health check results.

[0060] The user can obtain an identifier associated with the user's health check result in a variety of ways. In one embodiment, the health check result can be physical. The health check result implemented in a physical form can include a two-dimensional pattern (such as a two-dimensional code, a quick response (QR) code, a barcode, etc.), a chip for near field communication (NFC), a chip for radio frequency identification (RFID), etc. For example, the user can use a camera of an electronic device such as a smart phone to scan a two-dimensional pattern to obtain an identifier associated with the user's health check result. For another example, the user can communicate with a chip for NFC and a chip for RFID through a communication module of an electronic device such as a smart phone to obtain an identifier associated with the user's health check result. However, the present disclosure is not limited to this, and other ways for the user to obtain an identifier associated with the user's health check result from a health check result implemented in a physical form are also possible. In another embodiment, the health check result can be virtual. The health check result implemented in a virtual form can include a two-dimensional pattern (such as a two-dimensional code, a quick response (QR) code, a barcode, etc.), a link for jumping, etc. For example, the user can use a corresponding application in an electronic device such as a smart phone to scan a two-dimensional pattern to obtain an identifier associated with the user's health check result. For another example, the user can obtain an identifier associated with the user's health check result by selecting (e.g., clicking) a link for jumping. For another example, the user can obtain an identifier associated with the user's health check result by uploading the health check result in the human-computer dialogue program. The identifier associated with the user's health check result can identify that the user is accessing the human-computer dialogue in the first access mode. In addition, as an example, the human-computer dialogue application can obtain the user's health check result through an identifier associated with the user's health check result. In addition, the user can directly shoot the user's health check result using a camera of an electronic device such as a smart phone to obtain an identifier associated with the user's health check result. For example, the user can identify the text information in the health check result through traditional optical character recognition (OCR, Optical Character Recognition) technology or computer vision (CV, Computer Vision) technology. Then, the identified text information can be input into the large model included in the human-computer dialogue program. For another example, the large model included in the human-computer dialogue program can be trained in an end-to-end manner so that the large model has the ability to recognize pictures. Thus, the health check results are identified based on the image recognition capability of the large model itself.

[0061] In response to obtaining an identifier associated with a health check result for a user, a display such as Figure 3B As shown in the human-computer dialogue interface. Figure 3BAs shown, the human-computer dialogue interface may include a first area 340 and a second area 342. For example, the first area 340 may be a human-computer dialogue display area. For example, the first area 340 may display one or more recommended prompt information and the human-computer dialogue application's response to the user input and one or more recommended prompt information. The second area 342 may be a user input area. For example, the second area 342 may receive user input, wherein the user input may include text input and voice input. For example, a user may enter text in the second area 342 and select the send icon 334 to send the entered text. In addition, a user may perform voice input by long pressing the voice input icon 330 in the user input area 342 and select the send icon 334 to send the entered voice. In addition, there may also be a function of converting the input voice into text, which is not described in detail here.

[0062] In response to the user continuing to select the recommendation prompt information, the user input ( Figure 3B ) and the response of the human-computer dialogue application ( Figure 3B In response to one of the following (not shown) reaching a threshold time, one or more function indicators may be displayed. For example, an indicator for executing a voice broadcast function may be displayed. In response to a user selecting an indicator for executing a voice broadcast function, the human-computer dialogue application may broadcast the corresponding content. For another example, an indicator for executing a copy function may be displayed. In response to a user selecting an indicator for executing a copy function, the human-computer dialogue application may copy the corresponding content. However, the present disclosure is not limited thereto, and more or fewer functions may be displayed in response to a user continuously selecting one of the recommended prompt information, the user input, and the human-computer dialogue application's reply reaching a threshold time.

[0063] like Figure 3B As shown, function indicators 320-324 are displayed in the human-computer dialogue interface. Function indicator 320 may be an indicator for voice calls. In response to the user selecting function indicator 320, the human-computer dialogue application may perform a voice call with the user. Function indicator 322 may be an indicator for capturing images. In response to the user selecting function indicator 322, the human-computer dialogue application may call the camera of the electronic device to perform a capture function. For example, the user may use the camera to capture the user's health test results or the packaging box of the medicine so that the human-computer dialogue application may analyze the user's health test results or the packaging box of the medicine. Function indicator 324 may be an indicator for uploading files. In response to the user selecting function indicator 324, the human-computer dialogue application may assist the user in uploading files. For example, the user may upload his health check results.

[0064] Figure 3BThe first access method may include accessing the human-computer dialogue application based on an identifier associated with the user's health check result.

[0065] like Figure 3B As shown, the human-machine dialogue application can display one or more recommendation prompt information 310-314 that are compatible with the first access method among the multiple access methods in the human-machine dialogue interface. Figure 3B Three recommended prompts are shown in Figure 3B The human-computer dialogue interface may include more or less recommendation prompt information.

[0066] The recommended prompt information 310 may be a recommended prompt information about an inquiry associated with the overall health check result. The recommended prompt information 310 may include the content of "Please help me see what this report means?" For example, part of the user's health check results may be normal, and another part of the user's health check results may be abnormal. The user may want to obtain an overall interpretation of such health check results. The recommended prompt information 310 may instruct the human-computer dialogue program to interpret the overall health check results (e.g., report) of the user. In response to the user selecting the recommended prompt information 310, the human-computer dialogue program may display a reply to the user including an answer to the recommended prompt information 310. For example, the human-computer dialogue application may display an overall interpretation result of the user's health check results, such as health risk assessment, medical advice, lifestyle advice, etc.

[0067] The recommended prompt information 312 may be recommended prompt information about inquiries associated with abnormal items in one or more items in the health check results. The above-mentioned recommended prompt information may be generated by prompt engineering (PE). Prompt engineering aims to input more targeted and inspiring prompt information by adjusting the prompt information, so that the output of the large model is more in line with the expected answer. For example, reasonable system-level prompt information may be input to the large model included in the human-computer dialogue program through prompt engineering to instruct the large model to prompt the user's health check results. For example, system-level prompt information such as "If you are a senior medical consultant, please give at least 3 medical problems that are highly related to the health check results input by the user" may be input to the large model included in the human-computer dialogue program. However, those skilled in the art will appreciate that the above-mentioned system-level prompt information is only used as an example, and other suitable system-level prompt information is also possible.

[0068] For example, the recommended prompt information 310 may include the content of "What is the matter with high aspartate aminotransferase?" For example, the aspartate aminotransferase in the user's health check results may be higher than the normal value. The user may want to obtain an interpretation of the high aspartate aminotransferase in the health check results. The recommended prompt information 312 can instruct the human-computer dialogue program to interpret the abnormal items (e.g., high aspartate aminotransferase) in the user's health check results. In response to the user selecting the recommended prompt information 312, the human-computer dialogue program can display a reply to the user including an answer to the recommended prompt information 312. For example, the human-computer dialogue application can display the interpretation results of the high aspartate aminotransferase in the user's health check results, such as what causes high aspartate aminotransferase, what disease risks are associated with high aspartate aminotransferase, an assessment of the degree of high aspartate aminotransferase, medical advice, lifestyle advice, etc.

[0069] The recommended prompt information 314 may be a recommended prompt information about an inquiry associated with a portion of one or more items in the health check result. The recommended prompt information 314 may include the content of "What do low-density lipoprotein cholesterol, triglycerides, aspartate aminotransferase, alanine aminotransferase, blood sugar, and glycosylated hemoglobin represent?" For example, the user's health check result may include some key items, which may be highly related to the user's health status. The user may want to obtain an interpretation of the key items in the health check result. The recommended prompt information 314 may instruct the human-computer dialogue program to interpret a portion of one or more items in the user's health check result (e.g., key items). In response to the user selecting the recommended prompt information 314, the human-computer dialogue program may display a reply to the user including an answer to the recommended prompt information 314. For example, the human-computer dialogue application may display a medical interpretation of "low-density lipoprotein cholesterol", "triglycerides", "aspartate aminotransferase", "alanine aminotransferase", "blood sugar", and "glycosylated hemoglobin" in the user's health check result.

[0070] When a user accesses the human-computer dialogue program through the health check result, the query that the user may wish to make generally depends on the health check result. Figure 3B The one or more recommended prompt information displayed in the manner shown may include recommended prompt information that the user is more interested in. In this way, the user can select the recommended prompt information more conveniently and efficiently, which enhances the user's willingness to use the human-computer dialogue application, thereby improving the user experience.

[0071] Figure 4A is a schematic diagram showing a historical human-computer dialogue according to an embodiment of the present disclosure, Figure 4B is a schematic diagram showing a second access method according to an embodiment of the present disclosure. Figure 4BIt may be a human-machine dialogue interface displayed by the human-machine dialogue application when the user accesses the human-machine dialogue application through the second access method among the multiple access methods for accessing the human-machine dialogue application.

[0072] like Figure 4A As shown, the historical human-computer dialogue between the user and the human-computer dialogue application may include the following dialogue records:

[0073] "User: What causes stomach pain?

[0074] Human-computer dialogue program: How severe is the pain? How long has this condition lasted? Has it gotten better or worse over time?

[0075] User: The pain is very severe. It lasted for three days. It keeps getting worse.

[0076] Human-computer dialogue program: Are there any other symptoms associated with it?

[0077] User: Accompanied by nausea, vomiting, fever, and black stools.

[0078] Human-computer dialogue program: You may have gastric ulcer or other serious digestive tract diseases. Please seek medical treatment offline as soon as possible. "

[0079] exist Figure 4A In the historical human-computer dialogues, the user may have entered information indicating that the user is in an unhealthy state, such as "What is the cause of the stomach pain?", "The pain is very severe. It lasted for three days. It has been getting worse" and "Accompanied by nausea, vomiting, fever and black stools." In addition, the human-computer dialogue program may answer operations to alleviate the unhealthy state. For example, the human-computer dialogue program may answer a response such as "You may have gastric ulcers or other serious digestive tract diseases. Please seek medical attention offline as soon as possible." It advises the user to seek medical attention offline. Although Figure 4A An example of a historical human-computer dialogue for a serious disease such as a gastric ulcer is shown. However, the historical human-computer dialogue is not limited to this. For example, the historical human-computer dialogue may include information input by the user that the user is in various degrees of unhealthy state. That is, the unhealthy state may indicate that the user is in a diseased state or in an uncomfortable state. For example, in the historical human-computer dialogue, the user may input information about the user having a cold, and the human-computer dialogue application may answer a reply including medication suggestions for the user and a lifestyle adjustment plan. For another example, the user may input information about the user just staying up all night and therefore not feeling well, and the human-computer dialogue application may answer a reply including rest suggestions for the user and a lifestyle adjustment plan. For another example, the user may input information about the user's specific health status items (e.g., height, weight, etc.), and the human-computer dialogue application may answer a reply indicating that the user is currently in an overweight state and a lifestyle adjustment plan.

[0080] Figure 4B The second access method in may include in the presence of Figure 4A In the case of the historical human-computer dialogue shown in the figure, access the human-computer dialogue application. For example, in the case of a user such as Figure 4B When accessing a human-computer dialogue application, the human-computer dialogue application may contain historical human-computer dialogues that the user previously had with the human-computer dialogue application (such as Figure 4A That is, the second access mode can be triggered by the historical human-computer dialogue between the human-computer dialogue application and the user. Figure 4A In the historical human-computer dialogue shown, the user inputs information indicating that the user is in an unhealthy state.

[0081] For example, in response to the user exiting the human-machine dialogue application for a period of time not exceeding a threshold time period (for example, five minutes or ten minutes, the present disclosure is not limited thereto), when accessing the human-machine dialogue application again, the human-machine dialogue application may not generate or create a new human-machine dialogue, but continue the current human-machine dialogue. In response to the user exiting the human-machine dialogue application for a period of time exceeding the threshold time period, when accessing the human-machine dialogue application again, a new human-machine dialogue may be created.

[0082] like Figure 4B As shown, a human-computer dialogue history indicator 420 may be displayed in the human-computer dialogue interface. For example, the human-computer dialogue application may create a human-computer dialogue history for a previously occurring human-computer dialogue. In response to a user selecting the human-computer dialogue history indicator, the human-computer dialogue application may display one or more created human-computer dialogue histories to the user. For example, in response to a user selecting a created human-computer dialogue history, a human-computer dialogue example display area may be displayed in the human-computer dialogue interface, and the content (e.g., a portion thereof) included in the human-computer dialogue corresponding to the human-computer dialogue history and the time when the human-computer dialogue corresponding to the human-computer dialogue history occurred may be displayed in the human-computer dialogue example display area.

[0083] like Figure 4B As shown, the one or more recommended prompt information adapted to the second access mode may include recommended prompt information regarding an inquiry for information indicating that the user is in an unhealthy state. Figure 4A As shown, the information indicating that the user is in an unhealthy state is input, and when the user accesses the human-machine dialogue application again, the human-machine dialogue application can display the recommended prompt information 410. Figure 4BOne recommendation prompt information 410 is shown, but the recommendation prompt information may include more recommendation prompt information. The recommendation prompt information may include the content of "Is the stomachache better?" to inquire about the information indicating that the user is in an unhealthy state. In addition, one or more recommendation prompt information adapted to the second access mode may include recommendation prompt information about the execution status of the operation to alleviate the unhealthy state. For example, the human-computer dialogue program in such Figure 4A The operation to alleviate the unhealthy state is answered or suggested as shown, and when the user visits the human-machine dialogue application again, the human-machine dialogue application can display the recommended prompt information 410. The recommended prompt information may include the content of "Did you go to the hospital for the stomachache problem last time?" to inquire about the execution of the operation to alleviate the unhealthy state.

[0084] The above-mentioned recommendation prompt information can be generated through prompt engineering. For example, system-level prompt information such as "If you are a senior medical consultant, please give at least 3 medical problems that care for the user's previous non-healthy state based on the user's previous human-computer dialogue content" can be input into the large model included in the human-computer dialogue program. However, those skilled in the art will understand that the above-mentioned system-level prompt information is only used as an example, and other suitable system-level prompt information is also possible.

[0085] In one embodiment, Figure 4A The historical human-computer dialogue shown can be Figure 4B The access process shown in follows the previous historical human-computer dialogue. That is, Figure 4A The historical human-computer dialogue shown can be Figure 4B In another embodiment, Figure 4A The historical human-computer dialogue shown can be Figure 4B The historical human-computer dialogue within the threshold number of times before the access process shown in . For example, the threshold number of times can be 5 times. That is, Figure 4B The access process shown in may be preceded by, for example, 10 or more historical human-computer dialogues, and Figure 4A The historical human-computer dialogue shown may be a Figure 4B 1 historical human-computer dialogue out of the 5 historical human-computer dialogues of the access process shown in . In another embodiment, Figure 4A The historical human-computer dialogue shown can be Figure 4B The historical human-computer dialogue within the threshold time before the access process shown in . For example, the threshold time can be 5 days. That is, Figure 4B The access process shown in FIG. 1 may have occurred in a historical human-computer dialogue for, for example, 10 days or more, and Figure 4A The historical human-computer dialogue shown may be a Figure 4BIn yet another embodiment, Figure 4B The access process shown in may be preceded by multiple historical human-computer dialogues in which the user inputs information indicating that the user is in an unhealthy state, and Figure 4B In one example, one or more recommendation prompts can display multiple recommendation prompts to inquire about each piece of information indicating that the user is in an unhealthy state or the execution of mitigation operations in the information input by the user in multiple historical human-computer dialogues indicating that the user is in an unhealthy state. In another example, the information can be based on the severity of the information input by the user in multiple historical human-computer dialogues indicating that the user is in an unhealthy state and the multiple historical human-computer dialogues. Figure 4B A combination of the proximity of the access process shown is used to select a historical human-computer dialogue. A recommended prompt information is displayed based on the selected historical human-computer dialogue for inquiry.

[0086] When the user accesses the human-computer dialogue program again after inputting information indicating that the user is in an unhealthy state, the human-computer dialogue program displays recommended prompt information for inquiring about the user's unhealthy state, which can show care for the user and a high degree of trustworthiness. Therefore, in this way, the user can select the recommended prompt information more conveniently and efficiently, enhance the user's trust in the human-computer dialogue application, and thus improve the user experience.

[0087] Figure 5 is a schematic diagram showing a third access method according to an embodiment of the present disclosure. Figure 5 It may be a human-machine dialogue interface displayed by the human-machine dialogue application when the user accesses the human-machine dialogue application through a third access method among multiple access methods for accessing the human-machine dialogue application.

[0088] Figure 5 The third access method in the method may include accessing the human-machine dialogue application based on a network search of the human-machine dialogue application by the user. For example, the user may search for the human-machine dialogue application on a network such as the Internet, and access the human-machine dialogue application through a web page or through a web page jump application. For another example, the user may search for the human-machine dialogue application in other social applications, and access the human-machine dialogue application configured in the social application. In addition, Figure 5 The third access method may include accessing the human-machine dialogue application based on the user creating a new human-machine dialogue application in the human-machine dialogue application. As an example only, there may be no historical human-machine dialogue with the user in the human-machine dialogue application, and the user can access the human-machine dialogue application by creating a new human-machine dialogue in the human-machine dialogue application, but the present disclosure is not limited thereto.

[0089] like Figure 5As shown, the human-computer dialogue application can display one or more recommendation prompt information 510-530 that is compatible with the third access method among the multiple access methods in the human-computer dialogue interface. Figure 5 Three recommended prompts are shown in Figure 5 The human-computer dialogue interface may include more or less recommendation prompt information.

[0090] One or more recommendation prompt information 510-530 may include random recommendation prompt information. For example, one or more recommendation prompt information 510-530 may be recommendation prompt information randomly selected from a set of recommendation prompt information or randomly generated by a human-computer dialogue program. One or more recommendation prompt information 510-530 may include recommendation prompt information associated with the current season. For example, one or more recommendation prompt information 510-530 may be recommendation prompt information about medical scenarios associated with the season. Figure 5 As shown, one or more recommendation prompt information 510-530 may include "What are the benefits of Sanfutie", "What kind of people are suitable for Sanfutie?", and "What are the ingredients of Sanfutie?", etc. One or more recommendation prompt information 510-530 may include recommendation prompt information with high selection frequency determined based on big data. For example, one or more recommendation prompt information with high selection frequency by users in a time period (e.g., the previous day, week, month, or larger or smaller time granularity) before the time when the user accesses the human-computer dialogue program may be determined based on big data.

[0091] The above-mentioned recommendation prompt information can be generated through prompt engineering. For example, system-level prompt information such as "If you are a senior medical consultant and proficient in big data technology, please give at least 3 medical questions with high selection frequency determined based on big data" can be input into the big model included in the human-computer dialogue program. However, those skilled in the art will understand that the above-mentioned system-level prompt information is only used as an example, and other suitable system-level prompt information is also possible.

[0092] Therefore, Figure 5 The one or more recommended prompt information displayed in the manner shown may include recommended prompt information that the user is more interested in. In this way, the user can select the recommended prompt information more conveniently and efficiently, which enhances the user's willingness to use the human-computer dialogue application, thereby improving the user experience.

[0093] As mentioned above Figure 3A-Figure 5 As described, one or more recommendation prompt information may correspond to an access mode. For example, recommendation prompt information 310-314 may correspond to a first access mode, recommendation prompt information 410 may correspond to a second access mode, and recommendation prompt information 510-530 may correspond to a third access mode.

[0094] Figure 6 is another flow chart illustrating an intelligent medical consultation method according to an embodiment of the present disclosure.

[0095] like Figure 6 The method shown may include steps S610 - S650 .

[0096] In S610, a candidate access method for a user to access a human-computer dialogue application is determined and a human-computer dialogue interface is presented. The candidate access method may be similar to FIG. Figure 5 The access method described in .

[0097] In S620, the number of candidate access methods used by the user to access the human-computer dialogue application can be determined. Figure 5 The user can access the human-computer dialogue application program through a candidate access method described in the description. The user can access the human-computer dialogue application program through only one candidate access method. The user can also access the human-computer dialogue application program through multiple candidate access methods. For example, the user can access the human-computer dialogue application program through the first access method and the second access method as candidate access methods at the same time.

[0098] In S630, it can be determined whether the number of candidate access methods used by the user is greater than 1. If so, the process proceeds to S640, and the candidate access method used by the user can be determined as the access method used by the user. If not, the process proceeds to S650, and based on the priority corresponding to the candidate access method used by the user, the candidate access method with the highest priority can be determined as the access method used by the user. The priority corresponding to the candidate access method used by the user can be predetermined or generated based on the specific information of the candidate access method. As an example only, among the priorities of the candidate access methods, the priority of the third access method may be lower than the first access method and the second access method, and the priority of the first access method may be higher than the second access method, but the present disclosure is not limited to this.

[0099] At S660, one or more recommendation prompt information adapted to the access mode used by the user may be displayed in the human-computer dialogue interface.

[0100] Figure 7 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure.

[0101] like Figure 7 The human-machine dialogue device shown can execute a human-machine dialogue application program. Figure 7 As shown, the human-machine dialogue device 700 may include a human-machine dialogue presentation module 710 and a recommendation prompt information display module 720 .

[0102] The human-machine dialogue presentation module 710 may be configured to present a human-machine dialogue interface in response to a user accessing the human-machine dialogue application through one of a plurality of access methods for accessing the human-machine dialogue application;

[0103] The recommendation prompt information display module 720 can be configured to display one or more recommendation prompt information in the human-computer dialogue interface, and the one or more recommendation prompt information is used to trigger the human-computer dialogue application to output a response associated with the medical scenario. The one or more recommendation prompt information is adapted to one of the one or more access modes.

[0104] According to yet another aspect of the present disclosure, a human-computer dialogue device is also provided. Figure 8 A schematic diagram of a human-machine dialogue device 800 according to an embodiment of the present disclosure is shown.

[0105] like Figure 8 As shown, the human-computer dialogue device 800 may include one or more processors 810 and one or more memories 820. The memory 820 stores a computer-readable code, and when the computer-readable code is run by the one or more processors 810, the human-computer dialogue method described above may be executed.

[0106] The processor in the embodiments of the present disclosure may be an integrated circuit chip having signal processing capabilities. The above processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., which may be an X88 architecture or an ARM architecture.

[0107] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0108] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Fig. 9 The architecture of the computing device 900 shown in FIG. Fig. 9 As shown, the computing device 900 may include a bus 910, one or more CPUs 920, a read-only memory (ROM) 930, a random access memory (RAM) 940, a communication port 950 connected to a network, an input / output component 980, a hard disk 990, etc. The storage device in the computing device 900, such as the ROM 990 or the hard disk 990, may store various data or files used for processing and / or communication of the human-computer dialogue method provided by the present disclosure and program instructions executed by the CPU. The computing device 900 may also include a user interface 980. Of course, Fig. 9 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Fig. 9 One or more components of a computing device are shown.

[0109] According to another aspect of the present disclosure, a computer-readable storage medium is also provided. Computer-readable instructions are stored on the computer storage medium. When the computer-readable instructions are executed by the processor, the human-computer dialogue method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous connection dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM). It should be noted that memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0110] The embodiments of the present disclosure also provide a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the human-computer dialogue method according to the embodiments of the present disclosure.

[0111] Embodiments of the present disclosure provide a human-computer dialogue method, apparatus, device, and computer-readable storage medium.

[0112] The method provided by the embodiments of the present disclosure generates and displays to the user recommendation prompt information that is compatible with the user's access method to the human-computer dialogue application based on the user's access method to the human-computer dialogue application, so that the user can conveniently and efficiently select the recommendation prompt information, enhance the user's trust in the human-computer dialogue application and willingness to use it, thereby greatly improving the user experience.

[0113] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains at least one executable instruction for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0115] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. An intelligent medical consultation method, applied to a human-computer dialogue application, the method comprising: In response to a user accessing the human-machine dialogue application through one of a plurality of access methods for accessing the human-machine dialogue application, presenting a human-machine dialogue interface; as well as Displaying one or more recommendation prompts in the human-computer dialogue interface, wherein the one or more recommendation prompts are used to trigger the human-computer dialogue application to output a response associated with the medical scenario, The one or more recommendation prompt information is adapted to the one access method among the multiple access methods.

2. The method according to claim 1, wherein: The multiple access modes include a first access mode, which includes accessing the human-computer dialogue application based on an identifier associated with a health check result of the user.

3. The method according to claim 2, wherein: The identifier associated with the user's health check result is obtained by one or more of the following operations: Image recognition; Near Field Communication; and Radio Frequency Identification.

4. The method according to claim 2, wherein: The one or more recommendation prompt information adapted to the first access mode includes one or more of the following: the recommended prompt information regarding the query associated with the entirety of the health checkup result; the recommended prompt information regarding an inquiry associated with an abnormal item in one or more items in the health check result; as well as The recommendation prompt information about the query associated with a portion of the one or more items in the health check result.

5. The method according to claim 1, wherein: The multiple access modes include a second access mode, wherein the second access mode includes accessing the human-computer dialogue application program when there is a historical human-computer dialogue, Wherein, in the historical human-computer dialogue, the user inputs information indicating that the user is in an unhealthy state.

6. The method according to claim 5, wherein: The one or more recommendation prompt information adapted to the second access mode includes one or more of the following: Recommended prompt information regarding the inquiry for the information indicating that the user is in an unhealthy state; as well as Recommendation prompt information regarding an inquiry about the execution status of an operation to alleviate the unhealthy state, wherein the operation to alleviate the unhealthy state is included in a reply of the human-machine dialogue application in the historical human-machine dialogue.

7. The method according to claim 1, wherein: The multiple access modes include a third access mode, and the third access mode includes one or more of the following: Accessing the human-machine dialogue application based on a network search of the human-machine dialogue application by a user; The human-machine dialogue application is accessed based on a user creating a new human-machine dialogue application within the human-machine dialogue application.

8. The method according to claim 7, wherein: The one or more recommendation prompt information adapted to the third access mode includes one or more of the following: Random recommendation tips; Recommended tips related to the current season; as well as Recommended prompt information with high selection frequency determined based on big data.

9. The method according to claim 1, further comprising displaying one or more of the following function indicators in the human-machine dialogue interface: Indicator for voice calls; an indicator for capturing an image; and Indicator for uploading files.

10. The method according to claim 1, further comprising: In response to the user accessing the human-computer dialogue application again within a time period not exceeding a first threshold after exiting the human-computer dialogue application, continuing the human-computer dialogue; as well as In response to the user accessing the human-machine dialogue application again after exiting the human-machine dialogue application for more than a first threshold time period, a new human-machine dialogue is created.

11. The method according to claim 1, further comprising: Create historical human-computer dialogues for human-computer dialogues, Displaying a historical human-computer dialogue indicator in the human-computer dialogue interface, In response to the user selecting the historical human-machine dialogue indicator, one or more created historical human-machine dialogues are displayed to the user.

12. The method according to claim 10 further includes, in response to the historical human-computer dialogue created by the user's choice, displaying the content included in the human-computer dialogue corresponding to the historical human-computer dialogue and the time when the human-computer dialogue corresponding to the historical human-computer dialogue occurred in the human-computer dialogue interface.

13. The method according to claim 1, wherein: The human-computer dialogue interface includes a first area and a second area. The second area is configured to receive user input, wherein the user input includes text input and voice input, The first area is configured to display the one or more recommendation prompt information and the response of the human-computer dialogue application to the user input and the one or more recommendation prompt information.

14. The method according to claim 13, further comprising: In response to the user continuously selecting one of the recommendation prompt information, the user input, and the response of the human-machine dialogue application for a second threshold time, displaying one or more of the following function indicators: Indicator for executing voice announcement function; Indicator used to perform the copy function.

15. An intelligent medical consultation device, configured to execute a human-computer dialogue application, the device comprising: a human-computer dialogue presentation module configured to present a human-computer dialogue interface in response to a user accessing the human-computer dialogue application through one of a plurality of access modes for accessing the human-computer dialogue application; A recommendation prompt information display module, configured to display one or more recommendation prompt information in the human-computer dialogue interface, wherein the one or more recommendation prompt information is used to trigger the human-computer dialogue application to output a reply associated with the medical scenario; The one or more recommendation prompt information is adapted to the one access method among the one or more access methods.

16. An intelligent medical consultation device, comprising: one or more processors; as well as One or more memories, wherein a computer executable program is stored, and when the computer executable program is executed by the processor, the method of any one of claims 1-14 is performed.

17. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the instructions are used to implement the method according to any one of claims 1 to 14 when executed by a processor.

Images