Method for providing medical question and answer service, related device and computer program product

Abstract

The invention provides a method and device for providing a medical question and answer service, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of artificial intelligence such as text generation, data processing, intelligent recommendation and intelligent medical treatment. A specific embodiment of the method comprises the steps of determining candidate medical entities based on historical search data of a user; determining a target medical entity based on the historical case information of the user and the candidate medical entities; generating question information at least based on the target medical entity and the language style configuration of the user; and providing feedback information corresponding to the question information selected by the user for the user. In this way, the consultation point of the user can be mined based on the historical search data and the historical cases of the user, and the user is assisted to propose medical problems more efficiently and qualitatively. Therefore, the interaction cost when the user performs medical consultation based on the question and answer mode can be reduced, the user can use the medical question and answer service more efficiently and qualitatively, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence technology such as text generation, data processing, intelligent recommendation and smart medicine, and especially to methods, devices, electronic devices, computer-readable storage media and computer program products for providing medical question-and-answer services. Background Art

[0002] With the development of society and computer technology, online medical Q&A, medical intelligence and other related technologies have emerged to facilitate people and users to obtain medical knowledge. Online medical Q&A assistants and medical intelligence are innovative applications that have rapidly emerged in recent years with the development of technologies such as "artificial intelligence", "big data", "Internet of Things" and "cloud computing".

[0003] Online medical question-and-answer assistants and medical agents are a technical aspect that can provide medical knowledge and medical services, and are gradually being recognized and welcomed by people. Based on online medical question-and-answer assistants and medical agents, users can conveniently obtain medical-related knowledge through their interaction.

[0004] Accordingly, the development of technologies such as online medical Q&A assistants and medical intelligent agents can bring more efficient, smarter, and more inclusive medical services to the medical industry. Therefore, how to more effectively use technologies such as online medical Q&A assistants and medical intelligent agents to provide users with more efficient and higher-quality services is worthy of attention and urgent need. Summary of the invention

[0005] The embodiments of the present disclosure provide a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for providing a medical question-and-answer service.

[0006] In a first aspect, an embodiment of the present disclosure proposes a method for providing a medical question-and-answer service, comprising: determining candidate medical entities based on a user's historical search data; determining a target medical entity based on the user's historical case information and the candidate medical entities; generating question information based at least on the target medical entity and the user's language style configuration; and providing the user with feedback information corresponding to the question information selected by the user.

[0007] In the second aspect, an embodiment of the present disclosure proposes a device for providing medical question and answer services, comprising: a candidate medical entity determination unit, configured to determine candidate medical entities based on a user's historical search data; a target medical entity determination unit, configured to determine a target medical entity based on the user's historical case information and the candidate medical entities; a question information generation unit, configured to generate question information based at least on the target medical entity and the user's language style configuration; and a feedback information providing unit, configured to provide the user with feedback information corresponding to the question information selected by the user.

[0008] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that when the at least one processor executes, it is able to implement the method for providing medical question and answer services as described in any implementation method in the first aspect.

[0009] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the method of providing medical question-and-answer services as described in any implementation method of the first aspect when executed.

[0010] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the method for providing medical question and answer services as described in any implementation manner in the first aspect.

[0011] The method, device, electronic device, computer-readable storage medium, and computer program product for providing medical question-and-answer services provided by the embodiments of the present disclosure determine candidate medical entities based on the user's historical search data. Then, based on the user's historical case information and the candidate medical entities, a target medical entity is determined. Then, question information is generated based at least on the target medical entity and the user's language style configuration. Finally, based on the user's selection of the question information, feedback information corresponding to the question information selected by the user is provided to the user.

[0012] The present disclosure can mine the user's consultation points based on the user's historical search data and historical cases, and assist the user to raise medical questions more efficiently and with quality. Thus, it can reduce the interaction cost of the user when conducting medical consultation based on the question-and-answer method, facilitate the user to use the medical question-and-answer service more efficiently and with quality, and improve the user experience.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0015] Figure 1 is an exemplary system architecture in which the present disclosure may be applied;

[0016] Figure 2A flowchart of a process for providing a medical question-and-answer service provided by an embodiment of the present disclosure;

[0017] Figure 3 A flowchart of a process of providing feedback information to a user provided by an embodiment of the present disclosure;

[0018] Figure 4 A flowchart of a process of providing a medical question-and-answer service in an application scenario provided by an embodiment of the present disclosure;

[0019] Figure 5 A structural block diagram of a device for providing medical question-and-answer services provided in an embodiment of the present disclosure;

[0020] Figure 6 A schematic diagram of the structure of an electronic device suitable for executing a method for providing medical question-and-answer services provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments may be combined with each other without conflict.

[0022] In addition, in the technical solutions involved in this disclosure, the acquisition, storage, use, processing, transportation, provision and disclosure of user personal information involved (such as the user's historical search data, historical case information, etc. involved in this disclosure later) are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0023] For example, the user can be requested to authorize the processing of the relevant content of his / her personal information, such as acquisition, storage, use, processing, transportation, provision and disclosure, by interacting with the user in advance. Accordingly, after the user's authorization, the user's personal information can be used in accordance with the user's authorization based on the type and corresponding scope of the specific behavior authorized by the user.

[0024] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the method, apparatus, electronic device, and computer-readable storage medium for providing a medical question-and-answer service of the present disclosure can be applied.

[0025] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0026] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various applications for realizing information communication between the terminal devices 101, 102, 103 and the server 105 can be installed, such as online medical question-and-answer applications, information retrieval applications, instant messaging applications, etc.

[0027] Terminal devices 101, 102, 103 and server 105 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc.; when terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above, which can be implemented as multiple software or software modules, or as a single software or software module, and no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server; when the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, and no specific limitation is made here.

[0028] The server 105 can provide various services through various built-in applications. Taking an online medical question-and-answer application that can provide online questions and answers and online acquisition of medical knowledge as an example, the server 105 can achieve the following effects when running the online medical question-and-answer application: first, the server 105 determines the candidate medical entity based on the user's historical search data (for example, the user's historical search data stored locally on the server 105, or the user's historical search data obtained by the network 104 from the terminal devices 101, 102, 103); then, the server 105 determines the target medical entity based on the user's historical case information (for example, the historical case information stored locally on the server 105, or the historical case information obtained by the network 104 from the terminal devices 101, 102, 103) and the candidate medical entities; then, the server 105 generates question information based at least on the target medical entity and the user's language style configuration; finally, the server 105 provides the user with feedback information corresponding to the question information selected by the user.

[0029] Since storing historical search data, case information, etc. may require more storage resources, and determining candidate medical entities and target medical entities may require more computing resources and require stronger computing power, the methods for providing medical Q&A services provided in the subsequent embodiments of the present disclosure are generally performed by the server 105 with stronger computing power and more computing resources, and accordingly, the device for providing medical Q&A services is generally also set in the server 105. However, it should also be pointed out that when the terminal devices 101, 102, and 103 also have computing power and computing resources that meet the requirements, the terminal devices 101, 102, and 103 can also complete the above-mentioned various operations handed over to the server 105 through the online medical Q&A applications installed thereon, and then output the same results as the server 105. Especially when there are multiple terminal devices with different computing capabilities, but the online medical question-and-answer application determines that the terminal device has strong computing capabilities and more remaining computing resources, the terminal device can be allowed to perform the above-mentioned operations, thereby appropriately reducing the computing pressure of the server 105. Accordingly, the device providing medical question-and-answer services can also be set in the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104.

[0030] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0031] Please refer to Figure 2 , Figure 2 A flowchart of a process 200 for providing a medical question-and-answer service provided in an embodiment of the present disclosure, wherein the process 200 includes the following steps:

[0032] Step 201: Determine candidate medical entities based on the user's historical search data;

[0033] In the embodiments of the present disclosure, for example Figure 1 The server 105 shown is used as the execution subject of the method for providing medical question and answer service. For example, the server 105 may be a server used by a service platform capable of providing "medical question and answer service".

[0034] Accordingly, in the process of providing "medical question-and-answer services", the execution entity may first obtain the user's historical search data. For example, the historical search data may be the data determined based on the specific search content and search questions pointed to by the historical search behavior, after the user's authorization is collected on various search engines and medical platforms.

[0035] For example, after being authorized by the user, the execution entity can access the above-mentioned search engines and medical platforms through the authorized application programming interface (API) to collect the user's health-related search history (behavior) data and interaction data on these medical platforms and search engines.

[0036] Then, the execution subject can determine, based on the search behavior data and interaction data, the following field information, for example, as historical search data:

[0037] Search keywords: keywords entered by users on search engines, medical platforms, etc.

[0038] Browsing history: visited medical articles, disease introductions, drug information, etc.;

[0039] Data that can reflect the user's interests and concerns, such as interactive behaviors such as likes, comments, and favorites;

[0040] Historical questions: questions that users have previously asked doctors, medical agents, etc.

[0041] In some optional implementations of this embodiment, after obtaining the historical search data, the execution entity may also choose to filter missing or incomplete data, convert data from different sources into a unified format, and decrypt the historical search data to further improve the quality of the historical search data.

[0042] Then, after acquiring the historical search data, the execution entity may determine (a group of) candidate medical entities based on the user's historical search data.

[0043] The candidate medical entity may be a "medical entity" directly included in the search keyword at the text level, or may be a "medical entity" analyzed and identified after semantic analysis and content analysis of medical articles, disease introductions, drug information, etc. that the user has visited.

[0044] For example, the candidate medical entity may be a specific “disease name”, “drug name”, “treatment method”, “symptom name”, etc.

[0045] In some optional implementations of this embodiment, in order to more effectively determine candidate medical entities, the execution entity may process historical search data through, for example, a Latent Dirichlet Allocation (LDA) model to mine out "topics" that users are concerned about.

[0046] Alternatively, a word frequency-inverse document frequency algorithm is used to extract high-frequency keywords that may better reflect the user's interests.

[0047] Alternatively, algorithms such as Random Forest, support vector machine or convolutional neural network are used to train the user's interests and form an interest model, and the interest model is used to mine the "user interests" in historical search data.

[0048] Then, based on these "topics", "high-frequency keywords" and "user interests", candidate medical entities are determined, and the quality of determination of candidate medical entities is improved by "streamlining" and "refining" the information. For example, "topics" and "user interests" are used as processing samples, and "candidate medical entities" are determined by, for example, semantic analysis, natural language processing, etc.

[0049] Step 202: Determine a target medical entity based on the user's historical case information and candidate medical entities;

[0050] In an embodiment of the present disclosure, after the execution subject determines the candidate medical entity based on the above step 201, the execution subject may determine the target medical entity based on the user's historical case information and the candidate medical entity.

[0051] As discussed above, historical case information may also be obtained from, for example, a medical institution after authorization by the user, or uploaded by the user to the execution entity.

[0052] Then, the execution entity may determine the target medical entity from the candidate medical entities by analyzing the historical case information or taking the historical case information as a reference.

[0053] Generally, the execution subject can process the historical case information in a similar manner to determine the candidate medical entities hit therein. For example, the execution subject can also identify medical entities in the form of disease names, drug names, etc. recorded in the case information. Then, if the same medical entity is hit from both the historical search data and the historical case information, the medical entity can be determined as the target medical entity.

[0054] In some optional implementations of this embodiment, the execution subject can use the candidate medical entity as the "basis" and the historical case information as a reference to determine whether the corresponding candidate medical entity can be determined and hit through the records in the "historical case information". If it can be hit, the candidate medical entity is determined as the target medical entity.

[0055] For example, for a candidate medical entity with a disease name "X", the executing entity can determine whether it can be verified that the user has disease "X" or is at risk of having "X" based on the information recorded in the historical case information (generally, a situation where the risk of having "X" is greater than or equal to a preset threshold can be considered as "having a risk of having X").

[0056] Exemplarily, the execution entity may determine that there is a risk of "X" based on the disease name in the "diagnosis information" recorded in the historical case information.

[0057] Alternatively, in some optional implementations of this embodiment, the execution entity may also "infer" the above-mentioned "risk level" by analyzing and processing historical case information.

[0058] For example, for a medical entity in the form of "disease name", the executing entity can determine whether the user has the "disease" or whether the "disease" is "highly risky" for the user (i.e., the risk level is greater than or equal to a preset threshold) by matching the medical history, medication, biochemical indicators, and blood test results recorded in the historical case information with a predetermined disease model (e.g., the disease model corresponding to the "disease name").

[0059] Accordingly, if it exists, or is "high risk", the execution entity may determine the "candidate medical entity" as a "target medical entity".

[0060] Similarly, for the "risk level", the executing entity can also use algorithms such as random forest, support vector machine or convolutional neural network to determine the "risk level", which will not be repeated here.

[0061] Step 203: Generate question information based at least on the target medical entity and the user's language style configuration;

[0062] In an embodiment of the present disclosure, after determining the target medical entity based on the above step 202, the execution subject may generate question information directed to and associated with the target medical entity based at least on the target medical entity and the user's language style configuration.

[0063] For language style configuration, the execution subject can usually read the language style reference package provided by the user. For example, the user can provide the execution subject with a reference text provided in a natural language style so that the execution subject can learn its language style.

[0064] For example, for a reference text, the execution subject may analyze the “language style” included therein by using a sentiment analysis method (eg, Bi-LSTM).

[0065] In some optional implementations of this embodiment, the execution subject may also learn the user's language style in a similar manner by collecting expression texts in the user's historical search data to determine the corresponding language style configuration.

[0066] Accordingly, based on the language style configuration, when the execution subject generates the corresponding text information and voice information, the generated and output content can be "close to" the user's expression habits. For example, the execution subject can generate question information for the target medical entity based on the user's language style configuration by calling BERT (Bidirectional Encoder Representations from Transformers).

[0067] In some embodiments, in the process of generating question information, Top-k sampling or Nucleus Sampling may be introduced to increase the diversity of generated question information and avoid duplication.

[0068] In some embodiments, a question template may be preset corresponding to the question information, for example, a question template with a preset conjunction may be split based on the grammatical result. Subsequently, the question information may be generated by adding grammatical components such as a subject (for example, a target medical entity of a disease name) and a predicate to the template.

[0069] Accordingly, in some embodiments, the execution entity may also utilize a grammatical error correction model (eg, Transformer-based) to perform “grammatical correction” on the question information to avoid grammatical errors.

[0070] In some optional implementations of this embodiment, in order to more specifically define the inquiry requirements, the execution subject may also introduce "intention" in the process of generating question information to make the question information more specific and targeted.

[0071] In some optional implementations of this embodiment, the execution entity may choose to detect whether the user's search intention for the target medical entity can be determined based on the historical search data.

[0072] Subsequently, if the executing entity can determine the user's search intent for the target medical entity based on historical search data, when generating question information, the executing entity can choose to generate question information based on the target medical entity, search intent and user's language style configuration.

[0073] Specifically, the execution subject can determine the part that can be used to determine and hit the target medical entity from the historical search data. Then, based on the record of this part, try to read the user's search intention for the target medical entity to determine whether the user's search intention for the target medical entity can be determined based on the historical search data.

[0074] Taking "disease name" as an example, if the record used to determine the "disease name" in the historical search data is "how to prevent Y", the executing entity can determine based on the content that the "search intention" is "how to prevent (target medical entity)".

[0075] Therefore, when generating problem information, the executing entity can directly incorporate the intention of "how to prevent" into it, so as to adjust the inquiry direction of the "problem information" and improve the quality of the "problem information".

[0076] In some optional implementations of this embodiment, if the executing entity cannot determine the user's search intent for the target medical entity based on historical search data, the executing entity may respond to this and, in the process of generating question information, choose to generate question information based on the target medical entity, default search intent and user's language style configuration.

[0077] Default search intent can usually be preset, for example, "what is (target medical entity)", "the meaning of (target medical entity)".

[0078] In some optional implementations of this embodiment, the execution entity may also pre-set and default the search intent based on historical user search and inquiry intentions for the target medical entity.

[0079] For example, the execution entity can analyze the popularity of multiple historical users' search and query intentions for the target medical entity based on big data analysis, and select those "intents" whose popularity results meet the requirements (i.e., greater than or equal to the popularity threshold) as the default search intention, or select the "intention" with the highest popularity result as the "default".

[0080] Therefore, the executing entity can use "big data" to determine the "intentions" that are more likely to be of concern to users to generate question information and improve the value of the question information.

[0081] Similarly, for the "default search intent", the execution subject can also make a default based on the user configuration provided by the user to the execution subject, or the "search intent" that most frequently appears in the user's historical search data. In this way, the personalized habits and needs of users are met, and the value of question information is improved.

[0082] In some embodiments, the question information generated by the execution subject may at least include target information in the historical case information for determining the target medical entity.

[0083] For example, the form of "problem information" generated by the execution subject may be "based on (target information used to determine the target medical entity in historical case information), it is necessary to understand the control method of (target medical entity)".

[0084] Therefore, through this form of question information, users can directly understand the basis for determining the "target medical entity" and the basis for asking the question information based on the textual expression of the question information (or, allow users to use this as a reference) to better select the "question information" used for subsequent questions to the executing entity.

[0085] Next, the execution entity may provide (these) question information to the user, so that the user may "ask questions" to the execution entity by directly selecting the question information or referring to it.

[0086] For example, the execution subject may be directly presented to the user, or the terminal device used by the user may be used to present the problem information to the user for selection and reference.

[0087] Next, if the user selects (one piece of) question information, the execution entity may continue to execute step 204 .

[0088] Step 204: providing the user with feedback information corresponding to the question information selected by the user.

[0089] In the embodiment of the present disclosure, if the user selects (one of) the question information generated in the above step 203, the execution subject can obtain feedback information corresponding to the question information and provide it to the user. Thus, the "medical question and answer service" is provided to the user.

[0090] For feedback information, you can choose to use existing knowledge such as expert knowledge for matching and selection, or you can choose to provide it to a third party who has been pre-reviewed and certified and has (medical) question-and-answer capabilities for processing (for example, a doctor).

[0091] Accordingly, in order to improve the quality and efficiency of determining feedback information, the executing entity can choose to classify the "problem information" to determine a more "suitable" "feedback information determination strategy", or in other words, choose whether to use expert knowledge to respond or provide feedback, or provide it to a third party for processing by the third party.

[0092] Accordingly, the execution subject can implement classification based on the "search intent" of the question information. For example, for question information under the first question type, the execution subject can choose to use the pre-maintained medical knowledge base to match it with feedback information as an "answer".

[0093] For example, such "search intent" may generally correspond to, for example, "defining the name of a specific disease" and providing symptom description information for the disease.

[0094] Accordingly, for those question information that rely more on "inherent, known, and clear" expert knowledge, the executing entity can choose to use a pre-maintained medical knowledge base (as discussed above, which may include various types of expert knowledge, prior knowledge, etc. related to medical entities) to match the feedback information corresponding to the question information selected by the user.

[0095] Accordingly, in the process of providing the user with feedback information corresponding to the question information selected by the user, if the question information selected by the user is of the first question type, the executing entity may respond to this and further, as an alternative or alternative, utilize a pre-maintained medical knowledge base to match the feedback information corresponding to the question information selected by the user.

[0096] This feedback information is then provided to the user.

[0097] The method for providing medical Q&A services provided by the embodiments of the present disclosure can mine the user's consultation points based on the user's historical search data and historical cases, and assist the user to raise medical questions more efficiently and with quality. Thus, the interaction cost of the user when conducting medical consultation based on the Q&A method can be reduced, which facilitates the user to use the medical Q&A service more efficiently and with quality, and improves the user experience.

[0098] In some embodiments, when utilizing a pre-maintained medical knowledge base, the content provided by expert knowledge may be highly professional (for example, including some professional terms that are not easy to understand directly), making it inconvenient for users to read it completely at one time.

[0099] Therefore, the execution entity can also detect the feedback information to determine whether it hits other candidate medical entities besides the target medical entity.

[0100] Accordingly, if the execution subject determines that the feedback information hits other candidate medical entities besides the target medical entity, the execution subject may respond thereto and similarly generate follow-up question information based at least on the other hit candidate medical entities and the user's language style configuration.

[0101] Then, the execution subject can similarly provide these follow-up question information for the user to select and refer to. Accordingly, the user can similarly ask questions about the medical entities in the previous feedback information through the follow-up question information, in the hope of obtaining more comprehensive and complete information.

[0102] Correspondingly, if the user selects a follow-up question information, the execution entity can similarly provide the user with follow-up question feedback information corresponding to the selected follow-up question information, thereby providing the user with more comprehensive and in-depth information.

[0103] In some embodiments, as discussed above, different “feedback information determination strategies” may be selected based on the classification of the problem information.

[0104] For example, compared to the first question type mentioned above, for question information classified as the second question type, the executor can choose to communicate with the target device used by an audited, certified, and question-and-answer capable third party based on a pre-configured communication path to request the third party to provide feedback information.

[0105] Therefore, by connecting to a third party, we can meet the medical question and answer needs of different users in a higher quality and more personalized manner.

[0106] For this, please refer to Figure 3 , Figure 3 The flowchart of a process 300 of providing feedback information to a user provided in an embodiment of the present disclosure is shown. The process 300 can be used as an alternative or alternative implementation of the above step 204 to provide feedback information to the user. The process 300 specifically includes the following steps:

[0107] Step 301: In response to the question information selected by the user being the second question type, requesting the user to provide user reference information associated with a target medical entity;

[0108] Specifically, if the question information selected by the user is the second question type, the execution subject may respond to this to request the user to provide user reference information associated with the target medical entity. For example, the execution subject may provide "request information" to the terminal device used by the user to request the user reference information.

[0109] The user reference information associated with the target medical entity usually corresponds to the form of the specific target medical entity. For example, in the case where the target medical entity is a disease name, if the question information is, "Do you suffer from the disease (disease name)?", then the user reference information can be various (physiological indicators) required for determining and diagnosing the disease (disease name).

[0110] For another example, if the question information is "How to treat (disease name) in the current state", the user reference information may be related to the (disease name) disease and may reflect various (physiological indicators) of the development stage and state of the disease.

[0111] In some optional implementations of this embodiment, for the convenience of the user, the user can provide "user reference information" to the execution subject by specifying part of the content in the historical case information. For example, the user can provide "user reference information" by indicating the case number and part of the content recorded in the case.

[0112] If the user returns the user reference information, the execution entity may respond thereto and continue to execute step 302 .

[0113] Step 302: Determine the completeness of the user reference information based on the comparison between the user reference information and the standard reference information;

[0114] Specifically, if the user feeds back the user reference information, the execution entity may respond thereto and determine the completeness of the user reference information based on a comparison between the user reference information and the standard reference information.

[0115] The standard reference information is set corresponding to the target medical entity and the question information, and can be a standard template of the reference information required to answer the question information. For example, the standard reference information can record the specific items (physiological indicators) that need to be obtained.

[0116] Therefore, the executing entity can determine the completeness of the user reference information by comparing the user reference information with the standard reference information, so as to determine whether the "completeness" meets the standard and whether it can meet the usage requirements of the third party.

[0117] If the completeness of the user reference information is greater than or equal to the completeness threshold (or in other words, it meets the usage requirements of a third party), the execution entity may further execute step 303 to send the question information selected by the user and the user reference information to the target device to request the third party to process it.

[0118] Step 303: Send the question information and user reference information selected by the user to the target device;

[0119] If the target device returns feedback information, the execution subject may respond thereto and continue to execute step 304 .

[0120] Step 304: Provide feedback information to the user.

[0121] In some optional implementations of this embodiment, the completeness of the user reference information provided by the user may not meet the usage requirements in the current state, that is, the completeness is less than the above-mentioned completeness threshold. In this case, the execution subject can respond to this and request the user to further provide user reference information to enrich and improve the quality of user reference information, so as to fully and effectively utilize the question-and-answer service provided by the third party.

[0122] Specifically, in the above process 300, step 305 may also be included, and step 305 may be executed when the execution subject determines that the completeness of the user reference information is less than the completeness threshold. That is, if the execution subject determines that the completeness of the user reference information is less than the completeness threshold, the execution subject may respond to this and execute step 305.

[0123] Step 305: Request the user to provide updated reference information to supplement the missing parts of the user reference information compared to the standard reference information;

[0124] Specifically, the execution subject may determine the missing part of the user reference information compared with the standard reference information based on the comparison between the user reference information and the standard reference information. Then, the execution subject may generate prompt information based on the missing part, and based on the prompt information, request the user to provide updated reference information to supplement the missing part of the user reference information compared with the standard reference information.

[0125] If the user returns to update the user reference information, the execution entity may respond to this and continue to execute step 306 .

[0126] Step 306: Update the user reference information based on the update return to update the completeness of the user reference information.

[0127] Specifically, after the above step 305, if the user returns the updated user reference information, the execution subject may respond to this and update the completeness of the user reference information based on the updated user reference information returned.

[0128] Then, the execution subject may further determine whether to continue requesting the user to perform an "update" or to provide the target device with the question information selected by the user and the (updated) user reference information based on the comparison result between the updated completeness and the completeness threshold.

[0129] It should be understood that, with respect to the method of determining feedback information, the execution subject may also meet the user's personalized needs in a manner configured by the user in advance. For example, if the user prefers to use a third party to reply, the user may instruct the execution subject to adopt the method of determining and providing feedback information, such as that shown in the above process 300, in a manner set by the user.

[0130] In some embodiments, the user may also directly issue instructions to the execution subject to determine the way to determine and provide feedback information. For example, based on the text instruction of "machine answer", the execution subject is instructed to use the medical knowledge base to provide feedback information (for example, for the question information including the instruction, the execution subject can directly classify the question information as the first question type, so as to use "expert knowledge" to answer it).

[0131] For another example, based on the text instructions of "doctor answer" and "manual answer", the execution subject is instructed to provide feedback information by accessing a third party. (For example, for the question information including the instruction, the execution subject can directly classify the question information as the second question type, so as to use a third party to answer it).

[0132] In some optional implementations of this embodiment, if a third party is used to provide feedback information, the executing entity, in the process of generating question information based on (at least) the language style configuration of the target medical entity and the user, may further choose to generate question information based on the language style configuration of the target medical entity, the user, and the language style configuration corresponding to the target device.

[0133] Specifically, the execution subject can determine the combined language style configuration by fusing the user's language style configuration and the language style configuration corresponding to the target device (for example, it can be determined based on the user's language style configuration in a similar manner to the language style of the user of the target device) (for example, in each channel, the parameters recorded by the two language styles in the channel are averaged). Then, the execution subject generates question information based on the target medical entity and the combined language style configuration.

[0134] Therefore, by incorporating the language style configuration corresponding to the target device into the process of generating question information, the question information is made more readable for a third party such as a "doctor", so that the third party can understand the question more accurately and effectively, and make responses and feedback information.

[0135] Based on any of the above embodiments, because the historical case information may include multiple "cases", or the "cases" may include "invalid" or "low-value information" due to expiration of time, etc., the user can request adjustment of the historical case information by sending a historical case information adjustment request to the execution entity to indicate the "valuable information" that can be used and used as a reference by the execution entity.

[0136] Accordingly, if the executing entity receives a historical case information adjustment request sent by a user, it may respond thereto and provide the historical case information to the user.

[0137] Then, (if the user returns a range selection result for the historical case information), the execution entity may determine the target historical case information that can be used in the historical case information based on the user's range selection result for the historical case information.

[0138] Accordingly, in the process of executing the above step 202, for example, the execution subject may further select and determine the target medical entity based on the target historical case information and the candidate medical entities.

[0139] Therefore, the execution entity can determine the "valuable information" based on the user's selection and instruction of the content in the historical case information to more accurately determine the target medical entity.

[0140] Similarly, the executing entity may also "actively provide the user" with the historical case information that it wishes to use before actually using the historical case information, so that the user can make adjustments and improve the information quality of the historical case information.

[0141] To deepen understanding, the present disclosure also provides a specific implementation solution in combination with a specific application scenario.

[0142] For this, see Figure 4 . Figure 4 A flowchart of a process 400 for providing a medical question-and-answer service in an application scenario provided by an embodiment of the present disclosure.

[0143] For ease of understanding, it can be exemplified by combining Figure 1 The system architecture 100 is shown for illustration. For example, the server 100 shown in the system architecture is used as the execution subject of providing the medical question-and-answer service in the process 400.

[0144] In process 400, user 401 may interact with server 105 through S401 to initiate a "medical question and answer service". For example, user 401 may execute S401 through a terminal device (not shown) to request server 105 to provide a medical question and answer service.

[0145] Accordingly, after receiving the medical question-and-answer service request from the user 401, the server 105 may execute S402 to determine candidate medical entities based on the historical search data 403 of the user 401. Exemplarily, the server 105 may determine the candidate medical entities 411-41N hit or included therein based on the historical search data 403 of the user 401, where N is a positive integer.

[0146] Then, the server 105 may execute S403 to determine a target medical entity (eg, determine the target medical entity 421 ) based on the historical case information 405 of the user 401 and the candidate medical entities (eg, the candidate medical entities 411 - 41N).

[0147] It should be understood that the target medical entity 421 is actually one of the candidate medical entities 411 - 41 N. For example, the target medical entity 421 may be in an exemplary text form, which may be "XX" which is a disease name.

[0148] Then, the server 105 may execute S404 to generate question information (eg, generate question information 431 and 432 ) based on the target medical entity 421 and the language style configuration of the user 401 .

[0149] Then, the server 105 may execute S405 to provide the user 401 with question information 431 and 432 for the user 401 to refer to and select.

[0150] Exemplarily, the user 401 selected the question information 431 , that is, the user 401 actually expects to obtain the “medical question and answer service” by using the question information 431 .

[0151] Accordingly, the user 401 may interact with the server 105 through S406 and select question information 431 in order to obtain corresponding feedback information.

[0152] Next, the server 105 may execute S407 to determine the feedback information 441 corresponding to the question information 431 .

[0153] Then, the server 105 may continue to execute S408 to return feedback information 441 to the user 401 to provide and implement the "medical question and answer service".

[0154] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for providing medical question-and-answer services. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0155] like Figure 5As shown, the apparatus 500 for providing medical question-and-answer service in this embodiment may include: a candidate medical entity determination unit 501, a target medical entity determination unit 502, a question information generation unit 503, and a feedback information providing unit 504. The candidate medical entity determination unit 501 is configured to determine the candidate medical entity based on the user's historical search data; the target medical entity determination unit 502 is configured to determine the target medical entity based on the user's historical case information and the candidate medical entity; the question information generation unit 503 is configured to generate question information based on at least the target medical entity and the user's language style configuration; the feedback information providing unit 504 is configured to provide the user with feedback information corresponding to the question information selected by the user.

[0156] In this embodiment, in the device 500 for providing medical question-and-answer services, the specific processing of the candidate medical entity determination unit 501, the target medical entity determination unit 502, the question information generation unit 503, and the feedback information providing unit 504 and the technical effects thereof can be referred to in detail. Figure 2 The relevant descriptions of steps 201 - 204 in the corresponding embodiment are not repeated here.

[0157] In some optional implementations of this embodiment, the device 500 also includes: a search intention detection unit, configured to detect whether the user's search intention for the target medical entity can be determined based on historical search data; and a question information generation unit 503, including: a first question information generation subunit, configured to generate question information based on the target medical entity, the search intention and the user's language style configuration in response to being able to determine the user's search intention for the target medical entity based on historical search data.

[0158] In some optional implementations of this embodiment, the device 500 also includes: a second question information generating subunit, configured to, in response to an inability to determine the user's search intention for the target medical entity based on historical search data, the question information generating unit, further configured to generate question information based on the target medical entity, the default search intention and the user's language style configuration.

[0159] In some optional implementations of this embodiment, the feedback information providing unit 504 includes: a first feedback information determination subunit, configured to, in response to the question information selected by the user being a first question type, match the feedback information corresponding to the question information selected by the user using a pre-maintained medical knowledge base; and a first feedback information providing subunit, configured to provide feedback information to the user.

[0160] In some optional implementations of this embodiment, the device 500 also includes: a follow-up question information generating unit, configured to generate follow-up question information in response to other candidate medical entities other than the target medical entity hit in the feedback information, at least based on the other candidate medical entities hit and the user's language style configuration; a follow-up question feedback information providing unit, configured to provide the user with follow-up question feedback information corresponding to the selected follow-up question information.

[0161] In some optional implementations of the present embodiment, the feedback information providing unit 504 includes: a reference information requesting subunit, configured to request the user to provide user reference information associated with the target medical entity in response to the question information selected by the user being the second question type; an information completeness determining subunit, configured to determine the completeness of the user reference information based on a comparison between the user reference information and the standard reference information in response to the user returning the user reference information; a question information and reference information forwarding subunit, configured to send the question information and user reference information selected by the user to the target device in response to the completeness of the user reference information being greater than or equal to a completeness threshold; and a third feedback information providing subunit, configured to provide feedback information to the user in response to the target device returning feedback information.

[0162] In some optional implementations of the present embodiment, the device 500 also includes: an updated reference information request unit, configured to request the user to provide updated reference information in response to the completeness of the user reference information being less than a completeness threshold, so as to supplement the missing part of the user reference information compared to the standard reference information; an information completeness update unit, configured to update the user reference information in response to the user returning the updated user reference information, and update the completeness of the user reference information based on the updated returned user reference information.

[0163] In some optional implementations of this embodiment, the question information generating unit 503 is further configured to generate question information based on the target medical entity, the user's language style configuration and the language style configuration corresponding to the target device.

[0164] In some optional implementations of this embodiment, the question information includes at least target information in the historical case information for determining the target medical entity.

[0165] In some optional implementations of this embodiment, the device 500 also includes: a historical case information providing unit, configured to provide historical case information to the user in response to receiving a historical case information adjustment request sent by the user; a case usage range determination unit, configured to determine the target historical case information that can be used in the historical case information based on the user's range selection result of the historical case information; and a target medical entity determination unit 502, further configured to determine the target medical entity based on the target historical case information and the candidate medical entities.

[0166] This embodiment exists as a device embodiment corresponding to the above method embodiment. The device for providing medical Q&A services provided by this embodiment can mine the user's consultation points based on the user's historical search data and historical cases, and assist the user to raise medical questions more efficiently and with quality. In this way, the interaction cost of the user when conducting medical consultation based on the question-and-answer method can be reduced, which facilitates the user to use the medical Q&A service more efficiently and with quality, and improves the user experience.

[0167] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0168] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0169] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0170] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0171] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a method for providing a medical question-and-answer service. For example, in some embodiments, the method for providing a medical question-and-answer service may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for providing a medical question-and-answer service described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform a method for providing a medical question-and-answer service in any other appropriate manner (e.g., by means of firmware).

[0172] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0174] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0176] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0177] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services. The server can also be divided into a server of a distributed system, or a server combined with a blockchain.

[0178] According to the technical solution of the embodiment of the present disclosure, it is possible to mine the user's consultation points based on the user's historical search data and historical cases, and assist the user to raise medical questions more efficiently and with quality. As a result, it is possible to reduce the interaction cost of the user when conducting medical consultation based on the question-and-answer method, facilitate the user to use the medical question-and-answer service more efficiently and with quality, and improve the user experience.

[0179] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution provided by this disclosure can be achieved, and this document is not limited here.

[0180] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for providing medical question-and-answer services, comprising: Determine candidate medical entities based on the user's historical search data; Determining a target medical entity based on the user's historical case information and candidate medical entities; generating question information based at least on the target medical entity and the language style configuration of the user; Feedback information corresponding to the question information selected by the user is provided to the user.

2. The method according to claim 1, further comprising: detecting whether the user's search intention for the target medical entity can be determined based on the historical search data; as well as The generating question information based at least on the target medical entity and the language style configuration of the user comprises: In response to being able to determine the user's search intent for the target medical entity based on the historical search data, question information is generated based on the target medical entity, the search intent, and the user's language style configuration.

3. The method according to claim 1, further comprising: In response to failure to determine the user's search intent for the target medical entity based on the historical search data, question information is generated based on the target medical entity, a default search intent, and a language style configuration of the user.

4. The method according to claim 1, wherein: The providing the user with feedback information corresponding to the question information selected by the user includes: In response to the question information selected by the user being a first question type, matching feedback information corresponding to the question information selected by the user using a pre-maintained medical knowledge base; The feedback information is provided to the user.

5. The method according to claim 4, further comprising: In response to the feedback information hitting other candidate medical entities other than the target medical entity, generating follow-up question information based at least on the other candidate medical entities hit and the language style configuration of the user; The user is provided with follow-up question feedback information corresponding to the selected follow-up question information.

6. The method according to claim 1, wherein: The providing the user with feedback information corresponding to the question information selected by the user includes: In response to the question information selected by the user being a second question type, requesting the user to provide user reference information associated with the target medical entity; In response to the user returning the user reference information, determining the completeness of the user reference information based on a comparison between the user reference information and standard reference information; In response to the completeness of the user reference information being greater than or equal to a completeness threshold, sending the question information selected by the user and the user reference information to a target device; In response to the target device returning feedback information, the feedback information is provided to the user.

7. The method according to claim 6, further comprising: In response to the completeness of the user reference information being less than the completeness threshold, requesting the user to provide updated reference information to supplement the missing portion of the user reference information compared to the standard reference information; In response to the user returning updated user reference information, the completeness of the user reference information is updated based on the updated returned updated user reference information.

8. The method according to claim 6, wherein: The generating question information based at least on the target medical entity and the language style configuration of the user comprises: Question information is generated based on the target medical entity, the user's language style configuration, and the language style configuration corresponding to the target device.

9. The method according to claim 1, wherein: The question information at least includes target information in the historical case information for determining the target medical entity.

10. The method according to any one of claims 1 to 9, further comprising: In response to receiving a historical case information adjustment request sent by the user, providing the historical case information to the user; Based on the user's selection result of the range of the historical case information, determining target historical case information that can be used in the historical case information; as well as The determining of a target medical entity based on the historical case information of the user and the candidate medical entities includes: Based on the target historical case information and the candidate medical entities, a target medical entity is determined.

11. A device for providing medical question-and-answer services, comprising: a candidate medical entity determination unit, configured to determine a candidate medical entity based on historical search data of a user; a target medical entity determination unit, configured to determine a target medical entity based on the historical case information of the user and the candidate medical entities; a question information generating unit configured to generate question information based at least on the target medical entity and the language style configuration of the user; The feedback information providing unit is configured to provide the user with feedback information corresponding to the question information selected by the user.

12. The apparatus according to claim 11, further comprising: A search intention detection unit, configured to detect whether the user's search intention for the target medical entity can be determined based on the historical search data; as well as The question information generating unit comprises: a first question information generating sub-unit, configured to generate question information based on the target medical entity, the search intention and the user's language style configuration in response to being able to determine the user's search intention for the target medical entity based on the historical search data.

13. The apparatus according to claim 11, further comprising: The second question information generating subunit is configured to generate question information based on the target medical entity, the default search intent and the user's language style configuration in response to the inability to determine the user's search intent for the target medical entity based on the historical search data.

14. The device according to claim 11, wherein: The feedback information providing unit includes: a first feedback information determination subunit, configured to match feedback information corresponding to the question information selected by the user using a pre-maintained medical knowledge base in response to the question information selected by the user being of a first question type; The first feedback information providing subunit is configured to provide the feedback information to the user.

15. The apparatus according to claim 14, further comprising: A follow-up question information generating unit is configured to generate follow-up question information in response to the other candidate medical entities other than the target medical entity being hit in the feedback information, based at least on the other candidate medical entities being hit and the language style configuration of the user; The follow-up question feedback information providing unit is configured to provide the user with follow-up question feedback information corresponding to the selected follow-up question information.

16. The device according to claim 11, wherein The feedback information providing unit includes: a reference information requesting subunit, configured to request the user to provide user reference information associated with the target medical entity in response to the question information selected by the user being a second question type; an information completeness determination subunit, configured to determine the completeness of the user reference information based on a comparison between the user reference information and standard reference information in response to the user returning the user reference information; a question information and reference information forwarding subunit, configured to send the question information selected by the user and the user reference information to a target device in response to the completeness of the user reference information being greater than or equal to a completeness threshold; The third feedback information providing subunit is configured to provide the feedback information to the user in response to the target device returning the feedback information.

17. The apparatus according to claim 16, further comprising: an updated reference information requesting unit, configured to, in response to the completeness of the user reference information being less than the completeness threshold, request the user to provide updated reference information for supplementing a missing portion of the user reference information compared to the standard reference information; The information integrity updating unit is configured to update the user reference information in response to the user return, and update the integrity of the user reference information based on the updated user reference information.

18. The device according to claim 16, wherein: The question information generating unit is further configured to generate question information based on the target medical entity, the user's language style configuration and the language style configuration corresponding to the target device.

19. The device according to claim 11, wherein: The question information at least includes target information in the historical case information for determining the target medical entity.

20. The apparatus according to any one of claims 11 to 19, further comprising: a historical case information providing unit, configured to provide the historical case information to the user in response to receiving a historical case information adjustment request sent by the user; A case use range determination unit, configured to determine target historical case information that can be used in the historical case information based on the range selection result of the user on the historical case information; as well as The target medical entity determination unit is further configured to determine a target medical entity based on the target historical case information and the candidate medical entities.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for providing medical question and answer service according to any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method for providing medical question-and-answer services according to any one of claims 1 to 10.

23. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for providing medical question-and-answer service according to any one of claims 1 to 10.

Images