Intelligent agent-based expert and doctor recommendation method and system

Abstract

The invention belongs to the technical field of doctor recommendation. The invention provides an agent-based expert and doctor recommendation method and system. The method comprises the following steps: outputting a group of prompt questions to a patient, and receiving a first response voice input by the patient for the group of prompt questions; using a semantic analysis plug-in to extract a plurality of groups of first response semantic contents from the first response voice, and if a first quantity of the first response semantic contents is higher than a preset value, determining that the patient is a target patient; generating and outputting a group of inquiry questions to the target patient according to each first response semantic content, and receiving a second response voice input by the target patient for the group of inquiry questions; and extracting a plurality of groups of second response semantic contents from the second response voice, screening a second number of expert doctors based on each group of second response semantic contents, and outputting the second number of expert doctors to the target patient. The technical problem that it is difficult to recommend experts and doctors when the patient cannot accurately describe the illness state of the patient can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of doctor recommendation, and in particular to an agent-based expert doctor recommendation method and system. Background Art

[0002] In order to improve the level of medical services for patients, there are now some products that can recommend expert doctors suitable for their conditions to patients to assist them in choosing appropriate expert doctors. These products generally require patients to input their own conditions, and then select expert doctors suitable for their conditions through preset matching screening rules.

[0003] However, the above products require patients to be able to accurately describe their own conditions, which is difficult for some patients, especially those who are not good at language summary or do not have enough understanding of their own conditions. Therefore, how to improve the convenience of using expert doctor recommendations is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In this regard, the present invention provides an agent-based expert doctor recommendation method, system, electronic device, computer storage medium and computer program product to solve the above-mentioned technical problems.

[0005] The present invention discloses an expert doctor recommendation method based on an intelligent agent, which is applied to an intelligent agent. The method comprises the following steps: Outputting a set of prompt questions to the patient, and receiving a first response voice input by the patient in response to the set of prompt questions; Extracting a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and determining that the patient is a target patient if a first number of the first response semantic contents is higher than a preset value; wherein the semantic similarity between the groups of the first response semantic contents is lower than a similarity threshold; generating a group of inquiry questions according to each of the first response semantic contents and outputting them to the target patient, and receiving a second response speech input by the target patient in response to the group of inquiry questions; A semantic analysis plug-in is used to extract several groups of second response semantic contents from the second response speech, and a second number of expert doctors are screened based on each group of second response semantic contents and output to the target patient.

[0006] In some embodiments, the step of outputting a set of prompt questions to the patient and receiving a first response voice input by the patient in response to the set of prompt questions includes: Determine whether the patient's operation selection information is received, if not, execute the following step S0; If yes, determine whether the operation selection information is a prompt mode, if yes, execute the following step S0; if no, do not execute the following step S0; S0: Output a set of prompt questions to the patient, and receive a first response voice input by the patient in response to the set of prompt questions.

[0007] In some embodiments, the extracting several groups of first answer semantic contents from the first answer speech using a semantic analysis plug-in includes: A semantic analysis plug-in is used to extract a plurality of response sentences from the first response speech, and each of the response sentences is input into a semantic aggregation model based on a large model, and the semantic aggregation model outputs a plurality of groups of the first response semantic contents; wherein each group of the first response semantic contents contains a plurality of the response sentences; Among them, the semantic aggregation model based on the big model is embedded with the comparison relationship data between disease types and disease symptoms.

[0008] In some embodiments, determining that the patient is a target patient comprises: Extracting a plurality of voice interruption node segments from the first answer voice content, calculating a third number and a total duration of each voice interruption node segment, and evaluating the voice input continuity according to the third number and the total duration; Determine an adjustment coefficient value according to the continuity of the speech input; Calculating the first quantity of the first response semantic content output by the semantic aggregation model, and multiplying the first quantity by the adjustment coefficient value to obtain an adjusted second quantity; If the second number of the patient is higher than a preset value, the patient is determined to be a target patient.

[0009] In some embodiments, generating and outputting a set of inquiry questions to the target patient according to each of the first response semantic contents includes: The disease type corresponding to each of the first response semantic contents is determined based on the comparison relationship data between the disease type and the disease symptoms, and a set of inquiry questions is generated based on other disease symptoms corresponding to the disease type and output to the target patient.

[0010] In some embodiments, the step of obtaining a second number of expert doctors based on the semantic content of each group of the second responses includes: A semantic similarity calculation is performed between the semantic content of the second response of each group and the medical skill description information corresponding to each expert doctor, and a second number of expert doctors whose semantic similarity is higher than a semantic similarity threshold are screened out.

[0011] The present invention also discloses an agent-based expert doctor recommendation system, which is applied to the agent, and the system includes a prompt module, a first analysis module, an inquiry module, and a second analysis module; The prompt module is used to output a set of prompt questions to the patient and receive a first answer voice input by the patient in response to the set of prompt questions; The first analysis module is used to extract a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and if a first number of the first response semantic contents is higher than a preset value, the patient is determined to be a target patient; wherein the semantic similarity between the first response semantic contents of each group is lower than a similarity threshold; The inquiry module is used to generate and output a set of inquiry questions to the target patient according to each of the first response semantic contents, and receive a second response voice input by the target patient in response to the set of inquiry questions; The second analysis module uses a semantic analysis plug-in to extract several groups of second response semantic contents from the second response voice, screens a second number of expert doctors based on each group of second response semantic contents, and outputs them to the target patient.

[0012] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0013] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present invention also discloses a computer program product, which implements any of the above methods when the computer program product is run on a terminal.

[0015] The present invention dynamically decides whether to guide the patient to describe his or her condition by asking questions based on the patient's accurate description of his or her own condition. This can solve the technical problem that it is difficult to obtain expert doctor recommendations when the patient is unable to accurately describe his or her own condition, thereby providing patients with a better medical experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of an agent-based expert doctor recommendation method disclosed in an embodiment of the present invention; Figure 2 is a flow chart of an implementation scheme for determining that the patient is a target patient disclosed in an embodiment of the present invention; Figure 3 It is a structural diagram of an agent-based expert doctor recommendation system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0019] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0020] like Figure 1 As shown, an embodiment of the present invention discloses an agent-based expert doctor recommendation method, which is applied to an agent. The method comprises the following steps: Outputting a set of prompt questions to the patient, and receiving a first response voice input by the patient in response to the set of prompt questions; Extracting a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and determining that the patient is a target patient if a first number of the first response semantic contents is higher than a preset value; wherein the semantic similarity between the groups of the first response semantic contents is lower than a similarity threshold; generating a group of inquiry questions according to each of the first response semantic contents and outputting them to the target patient, and receiving a second response speech input by the target patient in response to the group of inquiry questions; A semantic analysis plug-in is used to extract several groups of second response semantic contents from the second response speech, and a second number of expert doctors are screened based on each group of second response semantic contents and output to the target patient.

[0021] In the solution of the present invention, the intelligent agent first outputs a set of prompt questions to the patient, and these prompt questions are used to prompt the patient to describe his or her condition from at least one of the following aspects, for example, the name of the disease, symptoms, duration of symptoms, degree of symptoms, etc. Based on this, the patient inputs a first response voice to the intelligent agent by voice input.

[0022] Then, the agent uses the semantic analysis plug-in to extract several groups of first response semantic contents from the first response speech, and the semantic similarity between the first response semantic contents is lower than the similarity threshold. If the first number of first response semantic contents is higher than the preset value, it indicates that the patient cannot accurately describe his condition. At this time, the patient is determined to be a target patient and the strategy needs to be changed.

[0023] Next, the intelligent agent generates and outputs a set of questions to the target patient based on the semantic content of each first response. The intelligent agent directly asks the patient whether he or she has certain symptoms. The patient then answers the set of questions one by one through the second response voice, which is conducive to accurately determining the patient's true disease type.

[0024] Finally, the intelligent agent uses the semantic analysis plug-in to extract several groups of second answer semantic content from the second answer voice, screens a second number of expert doctors based on the semantic content of each group of answers, and outputs them to the target patient for screening.

[0025] It can be seen that the present invention dynamically decides whether to guide the patient to describe his or her condition by asking questions based on the patient's accurate description of his or her own condition. This can solve the technical problem that it is difficult to obtain expert doctor recommendations when the patient is unable to accurately describe his or her own condition, thereby providing patients with a better medical experience.

[0026] It should be noted that the agent in the present invention can be embedded and installed in a web page or in various mobile or fixed devices. Among them, mobile devices refer to smart phones, tablet computers, wearable devices, smart glasses, etc., and fixed devices refer to desktop computers, laptops, etc.

[0027] In some embodiments, the step of outputting a set of prompt questions to the patient and receiving a first response voice input by the patient in response to the set of prompt questions includes: Determine whether the patient's operation selection information is received, if not, execute the following step S0; If yes, determine whether the operation selection information is a prompt mode, if yes, execute the following step S0; if no, do not execute the following step S0; S0: Output a set of prompt questions to the patient, and receive a first response voice input by the patient in response to the set of prompt questions.

[0028] In this embodiment, the present invention sets a variety of disease condition input modes, namely, the normal mode and the prompt mode. In the normal mode, the intelligent agent does not output prompt questions or ask questions to the patient, but the patient directly inputs a voice description of his own disease condition to the intelligent agent. This mode is suitable for patients who have a high degree of understanding of their own disease condition. In the prompt mode, the intelligent agent is required to output prompt questions or ask questions to the patient to guide the patient to describe his own disease condition clearly. This mode is suitable for patients who have a low degree of understanding of their own disease condition, such as patients who have not yet been diagnosed.

[0029] Among them, the web page or mobile device or fixed device in which the intelligent body is embedded is configured with a mode selection button. By detecting which button is selected, it can be determined whether the operation selection information is a prompt mode or a normal mode.

[0030] In some embodiments, the extracting several groups of first answer semantic contents from the first answer speech using a semantic analysis plug-in includes: A semantic analysis plug-in is used to extract a plurality of response sentences from the first response speech, and each of the response sentences is input into a semantic aggregation model based on a large model, and the semantic aggregation model outputs a plurality of groups of the first response semantic contents; wherein each group of the first response semantic contents contains a plurality of the response sentences; Among them, the semantic aggregation model based on the big model is embedded with the comparison relationship data between disease types and disease symptoms.

[0031] In this embodiment, after receiving the first response voice input by the patient, the intelligent agent first uses the semantic analysis plug-in to extract several response sentences from the first response voice. At the same time, a semantic aggregation model based on a large model is pre-built and trained, and a set of small sample training data is used for fine-tuning training. The semantic aggregation model can cluster the multiple response sentences obtained by the above analysis with the assistance of the embedded disease type and disease symptom comparison relationship data, that is, attribute them to the corresponding disease type, thereby obtaining multiple groups of first response semantic content. The first number of these groups of first response semantic content represents the number of disease types described by the patient in the first response voice. Obviously, the more the first number, the more disease types are involved, which means that the patient's description of his own condition is less accurate, and vice versa, the description is more accurate.

[0032] It should be noted that the large models mentioned above refer to general large models based on advanced neural networks such as Transformer, such as GPT model, BERT model, etc. These models far exceed conventional machine learning models in terms of training data, model parameter volume, and computing resources, and can handle data from multiple tasks and fields, with good adaptability and flexibility.

[0033] In some embodiments, determining that the patient is a target patient comprises: Extracting a plurality of voice interruption node segments from the first answer voice content, calculating a third number and a total duration of each voice interruption node segment, and evaluating the voice input continuity according to the third number and the total duration; Determine an adjustment coefficient value according to the continuity of the speech input; Calculating the first quantity of the first response semantic content output by the semantic aggregation model, and multiplying the first quantity by the adjustment coefficient value to obtain an adjusted second quantity; If the second number of the patient is higher than a preset value, the patient is determined to be a target patient.

[0034] In this embodiment, according to the aforementioned scheme, when the number of groups of the first response semantic content in the patient's first response speech, i.e., the first quantity, is higher than a preset value, it can be determined that the patient cannot accurately describe his or her condition, and at this time, the patient is determined to be a target patient who needs to be induced to describe his or her condition by asking questions. However, some patients may need to be diagnosed and treated for multiple diseases at a time, or their diseases do involve more symptoms, and these symptoms are similar to other types of diseases. In this case, the aforementioned scheme is likely to mistakenly determine the patient as a target patient.

[0035] In view of the above situation, if Figure 2 As shown, the present invention is set to extract multiple speech interruption node segments (i.e., node segments without inputting content with actual meaning, such as silent node segments, node segments similar to "uh...uh...") from the first response speech content, and calculate the third number and total duration of each speech interruption node segment, and evaluate the speech input continuity according to the third number and the total duration. Obviously, the speech input continuity can characterize the proficiency of the patient in inputting the description information of the condition. If the patient's speech input continuity is high, it means that the patient has a high degree of understanding of his own condition, and the probability that he belongs to the target patient is lower. At this time, the adjustment coefficient value is set to a smaller value (for example, 0.8, 0.9, 1.0), and the first number of the first response semantic content output by the aforementioned semantic aggregation model is adjusted to a smaller second number by using the adjustment coefficient value; on the contrary, if the patient's speech input continuity is low, it means that the patient has a low degree of understanding of his own condition, and the probability that he belongs to the target patient is higher. At this time, the adjustment coefficient value is set to a larger value (for example, 1.1, 1.2), and the first number of the first response semantic content output by the aforementioned semantic aggregation model is adjusted to a larger second number by using the adjustment coefficient value. Obviously, the adjustment coefficient value is negatively correlated with the continuity of the speech input. Finally, the second number is compared with the preset value to determine whether the patient is the target patient.

[0036] In addition, the continuity of voice input and the third quantity and total duration obtained above all conform to a negative correlation relationship. Moreover, the present invention does not specifically limit the conversion formula or comparison table of all the above negative correlation relationships.

[0037] In some embodiments, generating and outputting a set of inquiry questions to the target patient according to each of the first response semantic contents includes: The disease type corresponding to each of the first response semantic contents is determined based on the comparison relationship data between the disease type and the disease symptoms, and a set of inquiry questions is generated based on other disease symptoms corresponding to the disease type and output to the target patient.

[0038] In this embodiment, the first response semantic content parsed from the first response semantic content includes at least one disease symptom, and the disease symptom is compared with the disease type and the disease symptom comparison relationship number to determine the disease type (which may be multiple) to which it belongs, and then based on other symptoms of the disease type included in the disease symptom and the disease type and disease symptom comparison relationship number, a set of inquiry questions is generated and asked to the patient accordingly.

[0039] For example, the first response semantic content contains the content of "stomach ache", and based on the matching of the disease symptoms, disease types and disease symptoms, multiple diseases such as gastritis, appendicitis, and gallstones are obtained, and then other symptoms corresponding to gastritis, appendicitis, and gallstones are determined from the disease symptoms, disease types and disease symptoms. Based on this, the patient is asked in turn whether he has "vomiting symptoms" and "flatulence symptoms" of gastritis, whether he has "transferred right lower abdominal pain", "low fever", etc., whether he has "fever / chills", "biliary colic", etc. Through the questioning, several diseases associated with the symptom "stomach ache" can be excluded one by one, and finally it is confirmed to be appendicitis.

[0040] In some embodiments, the step of obtaining a second number of expert doctors based on the semantic content of each group of the second responses includes: A semantic similarity calculation is performed between the semantic content of the second response of each group and the medical skill description information corresponding to each expert doctor, and a second number of expert doctors whose semantic similarity is higher than a semantic similarity threshold are screened out.

[0041] In this embodiment, medical skill description information is established in advance for each expert doctor, including the department to which he belongs, the diseases he is good at treating, the rank, etc., and the semantic similarity calculation is performed between each group of second response semantic content extracted from the second response voice content and the medical skill description information corresponding to each expert doctor, and the expert doctor with a semantic similarity higher than the semantic similarity threshold is determined as the expert doctor suitable for the target patient and screened out. The second number of suitable expert doctors screened out can be preset or determined by the patient.

[0042] like Figure 3 As shown, the embodiment of the present invention also discloses an agent-based expert doctor recommendation system, which is applied to an agent, and the system includes a prompt module, a first analysis module, an inquiry module, and a second analysis module; The prompt module is used to output a set of prompt questions to the patient and receive a first answer voice input by the patient in response to the set of prompt questions; The first analysis module is used to extract a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and if a first number of the first response semantic contents is higher than a preset value, the patient is determined to be a target patient; wherein the semantic similarity between the first response semantic contents of each group is lower than a similarity threshold; The inquiry module is used to generate and output a set of inquiry questions to the target patient according to each of the first response semantic contents, and receive a second response voice input by the target patient in response to the set of inquiry questions; The second analysis module uses a semantic analysis plug-in to extract several groups of second response semantic contents from the second response voice, screens a second number of expert doctors based on each group of second response semantic contents, and outputs them to the target patient.

[0043] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0044] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0045] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the method described in the above embodiment is implemented.

[0046] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the device according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0047] References herein to "one embodiment," "embodiment," or "one or more embodiments" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. In addition, please note that examples of the term "in one embodiment" do not necessarily all refer to the same embodiment.

[0048] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0049] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0050] In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or limiting the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative rather than restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. An agent-based expert doctor recommendation method, applied to an agent, characterized in that: The method comprises the following steps: Outputting a set of prompt questions to the patient, and receiving a first response voice input by the patient in response to the set of prompt questions; Extracting a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and determining that the patient is a target patient if a first number of the first response semantic contents is higher than a preset value; wherein the semantic similarity between the groups of the first response semantic contents is lower than a similarity threshold; Generate and output a set of inquiry questions to the target patient according to each of the first response semantic contents, and receive a second response speech input by the target patient in response to the set of inquiry questions; A semantic analysis plug-in is used to extract several groups of second response semantic contents from the second response speech, and a second number of expert doctors are screened based on each group of second response semantic contents and output to the target patient.

2. The agent-based expert doctor recommendation method according to claim 1, characterized in that: The step of outputting a set of prompt questions to the patient and receiving a first response voice input by the patient in response to the set of prompt questions includes: Determine whether the patient's operation selection information is received, if not, execute the following step S0; If yes, determine whether the operation selection information is a prompt mode, if yes, execute the following step S0; if no, do not execute the following step S0; S0: Output a set of prompt questions to the patient, and receive a first response voice input by the patient in response to the set of prompt questions.

3. The agent-based expert doctor recommendation method according to claim 2, characterized in that: A semantic analysis plug-in is used to extract several groups of first answer semantic contents from the first answer speech, including: A semantic analysis plug-in is used to extract a plurality of response sentences from the first response speech, and each of the response sentences is input into a semantic aggregation model based on a large model, and the semantic aggregation model outputs a plurality of groups of the first response semantic contents; wherein each group of the first response semantic contents contains a plurality of the response sentences; Among them, the semantic aggregation model based on the big model is embedded with the comparison relationship data between disease types and disease symptoms.

4. The agent-based expert doctor recommendation method according to claim 3, characterized in that: Determining that the patient is a target patient comprises: Extracting a plurality of voice interruption node segments from the first answer voice content, calculating a third number and a total duration of each voice interruption node segment, and evaluating the voice input continuity according to the third number and the total duration; Determine an adjustment coefficient value according to the continuity of the speech input; Calculating the first quantity of the first response semantic content output by the semantic aggregation model, and multiplying the first quantity by the adjustment coefficient value to obtain an adjusted second quantity; If the second number of the patient is higher than a preset value, the patient is determined to be a target patient.

5. The agent-based expert doctor recommendation method according to claim 4, characterized in that: A set of inquiry questions is generated and output to the target patient according to the semantic content of each of the first responses, including: The disease type corresponding to each of the first response semantic contents is determined based on the comparison relationship data between the disease type and the disease symptoms, and a set of inquiry questions is generated based on other disease symptoms corresponding to the disease type and output to the target patient.

6. The agent-based expert doctor recommendation method according to claim 5, characterized in that: A second number of expert doctors are obtained based on the semantic content of the second responses of each group, including: A semantic similarity calculation is performed between the semantic content of the second response of each group and the medical skill description information corresponding to each expert doctor, and a second number of expert doctors whose semantic similarity is higher than a semantic similarity threshold are screened out.

7. An agent-based expert doctor recommendation system, applied to an agent, the system comprising a prompt module, a first analysis module, an inquiry module, and a second analysis module; characterized in that: The prompt module is used to output a set of prompt questions to the patient and receive a first answer voice input by the patient in response to the set of prompt questions; The first analysis module is used to extract a plurality of groups of first response semantic contents from the first response speech using a semantic analysis plug-in, and if a first number of the first response semantic contents is higher than a preset value, the patient is determined to be a target patient; wherein the semantic similarity between the first response semantic contents of each group is lower than a similarity threshold; The inquiry module is used to generate and output a set of inquiry questions to the target patient according to the semantic contents of each of the first responses, and receive a second response voice input by the target patient in response to the set of inquiry questions; The second analysis module uses a semantic analysis plug-in to extract several groups of second response semantic contents from the second response voice, screens a second number of expert doctors based on each group of second response semantic contents, and outputs them to the target patient.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that: When the computer program product runs on a terminal, the method according to any one of claims 1 to 6 is implemented.

Images