A medical self-service machine intelligent diagnosis guidance system and method

Abstract

The present invention provides a medical self-service machine intelligent diagnosis guidance system and method, wherein the system includes: a first display module, used to display a preset discomfort part selection interface; a first receiving module, used to receive the discomfort part selected by the user; a second display module, used to display a preset discomfort symptom selection interface corresponding to the discomfort part; a second receiving module, used to receive the discomfort symptom selected by the user; a third display module, used to display a preset registration department selection interface corresponding to the discomfort symptom; a third receiving module, used to receive the registration department selected by the user and print a receipt. The medical self-service machine intelligent diagnosis guidance system and method of the present invention introduces a discomfort part selection interface, a discomfort symptom selection interface and a registration department selection interface, and intuitively allows patients to select discomfort parts, discomfort symptoms and registration departments, realizes automated intelligent diagnosis guidance, reduces labor costs, and improves diagnosis guidance efficiency.

Description

Technical Field

[0001] The present invention relates to the field of smart medical guidance technology, and in particular to a medical self-service machine smart medical guidance system and method. Background Art

[0002] At present, patients need to register after entering the hospital. With the popularity of medical self-service machines, more and more patients choose to use medical self-service machines to register. However, generally, there is a guide next to each medical self-service machine to ask the patient about the discomfort area, symptoms, etc., and help them choose the registration department. Doing so has a high labor cost and low guidance efficiency.

[0003] Therefore, a solution is urgently needed. Summary of the invention

[0004] One of the purposes of the present invention is to provide a medical self-service machine intelligent guidance system, which introduces an discomfort part selection interface, an discomfort symptom selection interface and a registration department selection interface, so that patients can intuitively select discomfort parts, discomfort symptoms and registration departments, realize automated intelligent guidance, reduce labor costs, and improve guidance efficiency.

[0005] An embodiment of the present invention provides a medical self-service machine intelligent diagnosis guidance system, comprising:

[0006] A first display module, used for displaying a preset discomfort part selection interface;

[0007] A first receiving module is used to receive the discomfort part input by the patient;

[0008] A second display module, used for displaying a preset discomfort symptom selection interface corresponding to the discomfort part;

[0009] A second receiving module is used to receive discomfort symptoms input by the patient;

[0010] A third display module is used to display a preset registration department selection interface corresponding to the discomfort symptom;

[0011] The third receiving module is used to receive the registration department input by the patient and print the corresponding receipt.

[0012] Preferably, the medical self-service machine intelligent diagnosis guidance system also includes:

[0013] Recommended modules for this include:

[0014] Get the number of people in the queue;

[0015] When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed;

[0016] Receive symptom description information input by the patient;

[0017] Preprocessing the symptom description information;

[0018] Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined;

[0019] Displaying a list of physicians who are experts in the above-mentioned fields;

[0020] physicians who are skilled in receiving patient input;

[0021] Print the registration receipt of the specialist doctor.

[0022] Preferably, the recommendation module preprocesses the symptom description information, including:

[0023] Parsing the symptom description information to obtain a human voice segment and a corresponding segment time;

[0024] Based on the segment time, the vocal segment is arranged on a preset time axis;

[0025] Obtain a persona portrait of the patient;

[0026] Based on the character portrait, determining a patient vocal segment and a non-patient vocal segment from the vocal segments;

[0027] Determine a vocal segment cluster that meets the segment cluster condition from the time axis;

[0028] Effectively verifying the non-patient vocal segment in the vocal segment cluster;

[0029] Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster;

[0030] Based on the semantic analysis technology, the patient's symptom condition is determined according to the patient's vocal segment and the remaining non-patient vocal segments in the vocal segment cluster, and used as the preprocessing result;

[0031] Wherein, the fragment cluster conditions include:

[0032] The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments;

[0033] There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold.

[0034] Preferably, the recommendation module effectively verifies the non-patient vocal segment in the vocal segment cluster, including:

[0035] Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library;

[0036] If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved;

[0037] Determine whether the person image meets any image trigger condition in a preset image trigger condition library;

[0038] When none of them meet the requirements, the effective verification is passed.

[0039] Preferably, the recommendation module determines a list of physicians with expertise based on the preprocessing results and a preset physician database, including:

[0040] Based on the preprocessing results, determining a plurality of skilled physician conditions;

[0041] Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold;

[0042] Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

[0043] An embodiment of the present invention provides a medical self-service machine intelligent diagnosis guidance method, comprising:

[0044] Display the preset discomfort part selection interface;

[0045] Receive patient input of the site of discomfort;

[0046] Displaying a preset discomfort symptom selection interface corresponding to the discomfort part;

[0047] Receive patient input of discomfort symptoms;

[0048] Displaying a preset registration department selection interface corresponding to the discomfort symptom;

[0049] Receive the registration department entered by the patient and print the corresponding receipt.

[0050] Preferably, the medical self-service machine intelligent diagnosis guidance method further includes:

[0051] Get the number of people in the queue;

[0052] When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed;

[0053] Receive symptom description information input by the patient;

[0054] Preprocessing the symptom description information;

[0055] Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined;

[0056] Displaying a list of physicians who are experts in the above-mentioned fields;

[0057] physicians who are skilled in receiving patient input;

[0058] Print the registration receipt of the specialist doctor.

[0059] Preferably, the preprocessing of the symptom description information includes:

[0060] Parsing the symptom description information to obtain a human voice segment and a corresponding segment time;

[0061] Based on the segment time, the vocal segment is arranged on a preset time axis;

[0062] Obtain a persona portrait of the patient;

[0063] Based on the character portrait, determining a patient vocal segment and a non-patient vocal segment from the vocal segments;

[0064] Determine a vocal segment cluster that meets the segment cluster condition from the time axis;

[0065] Effectively verifying the non-patient vocal segment in the vocal segment cluster;

[0066] Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster;

[0067] Based on the semantic analysis technology, the patient's symptom condition is determined according to the patient's vocal segment and the remaining non-patient vocal segments in the vocal segment cluster, and used as the preprocessing result;

[0068] Wherein, the fragment cluster conditions include:

[0069] The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments;

[0070] There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold.

[0071] Preferably, the effective verification of the non-patient vocal segment in the vocal segment cluster includes:

[0072] Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library;

[0073] If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved;

[0074] Determine whether the person image meets any image trigger condition in a preset image trigger condition library;

[0075] When none of them meet the requirements, the effective verification is passed.

[0076] Preferably, the method of determining a list of physicians with expertise based on the preprocessing results and a preset physician database includes:

[0077] Based on the preprocessing results, determining a plurality of skilled physician conditions;

[0078] Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold;

[0079] Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

[0080] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0081] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0083] Figure 1 A schematic diagram of a medical self-service machine intelligent diagnosis guidance system in an embodiment of the present invention;

[0084] Figure 2 Schematic diagram of a smart medical guidance method of a medical self-service machine in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0086] The embodiment of the present invention provides a medical self-service machine intelligent diagnosis guidance system, such as Figure 1 As shown, including:

[0087] The first display module 1 is used to display a preset discomfort part selection interface;

[0088] The first receiving module 2 is used to receive the discomfort part input by the patient;

[0089] The second display module 3 is used to display a preset discomfort symptom selection interface corresponding to the discomfort part;

[0090] The second receiving module 4 is used to receive the discomfort symptoms input by the patient;

[0091] The third display module 5 is used to display the preset registration department selection interface corresponding to the discomfort symptom;

[0092] The third receiving module 6 is used to receive the registration department input by the patient and print a corresponding receipt.

[0093] When the patient comes to the medical self-service machine, the machine first displays an interface for selecting the part of discomfort; the interface for selecting the part of discomfort can be a human body model, and the user clicks on the part on the human body model to select the part of discomfort; then, the medical self-service machine displays an interface for selecting symptoms of discomfort; the interface for selecting symptoms of discomfort contains a variety of symptoms of discomfort parts, for example, if the discomfort part is the eyes, the interface for selecting symptoms of discomfort contains dryness, itching, pain, photophobia, etc.; finally, the medical self-service machine displays an interface for selecting the registration department; the interface for selecting the registration department contains the department of the attending doctor corresponding to the discomfort symptom, for example, ophthalmology; after the registration is completed, a receipt is printed, and the patient can go to the corresponding department according to the receipt to wait for the consultation.

[0094] This application introduces an discomfort site selection interface, a discomfort symptom selection interface and a registration department selection interface, which allow patients to intuitively select discomfort sites, discomfort symptoms and registration departments, realize automated intelligent medical guidance, reduce labor costs and improve medical guidance efficiency.

[0095] In one embodiment, the medical self-service machine intelligent diagnosis guidance system further includes:

[0096] Recommended modules for this include:

[0097] Get the number of people in the queue;

[0098] When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed;

[0099] Receive symptom description information input by the patient;

[0100] Preprocessing the symptom description information;

[0101] Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined;

[0102] Display the list of physicians who are experts in the above-mentioned fields;

[0103] physicians who are skilled in receiving patient input;

[0104] Print the registration receipt of the physician.

[0105] The number of people in the queue is the number of patients waiting in line to register using the medical self-service machine; the number threshold can be, for example: 5; it takes a long time for patients to describe their symptoms and recommend a skilled doctor for them. Only when the number of people in the queue is small, wait for patients to describe their symptoms to recommend a skilled doctor for them, so as to avoid unreasonable registration queues in front of the medical self-service machine; there is a prompt text "Tell me your symptoms and I will recommend a doctor for you" on the symptom description prompt interface; the symptom description information is the voice information generated by the patient's symptom introduction; the purpose of preprocessing is to eliminate irrelevant voices and determine the patient's specific symptoms based on the voice information; the doctor database contains information on different doctors in the hospital, and the information can be gender, age, specialty disease, experience level, etc.; after determining the patient's specific symptoms, the doctor database can be used to recommend a skilled doctor for the patient, determine the skilled doctor list and display it, at this time, the patient can select the skilled doctor by himself, after the selection, the medical self-service machine prints the registration receipt of the skilled doctor, and the patient finds the corresponding skilled doctor according to the receipt and waits for consultation. The embodiment of the present invention realizes another guidance method, in which the patient introduces his specific symptoms to the medical self-service machine, and the medical self-service machine can recommend a skilled doctor for him, which is more humane and intelligent.

[0106] In one embodiment, the recommendation module pre-processes the symptom description information, including:

[0107] Parse the symptom description information to obtain a human voice segment and a corresponding segment time; the segment time is the start and end time of the human voice segment;

[0108] Based on the segment time, the vocal segment is set on a preset time axis; when setting, the time axis position area corresponding to the segment time is found on the time axis, and the vocal segment is set on the area;

[0109] Obtain a patient's portrait; the portrait may include gender, age, etc.;

[0110] Based on the character portrait, a patient vocal segment and a non-patient vocal segment are determined from the vocal segments; gender and age can roughly reflect the timbre of the patient, so the patient vocal segment and the non-patient vocal segment can be determined from the vocal segments, the patient vocal segment is generated by the patient, and the non-patient vocal segment is not generated by the patient, for example, generated by the patient's accompanying family members;

[0111] Determine a vocal segment cluster that meets the segment cluster condition from the time axis;

[0112] Performing effective verification on the non-patient vocal segment in the vocal segment cluster; when the non-patient vocal segment passes the effective verification, it means that the non-patient vocal segment can be used to determine the patient's symptoms; otherwise, it needs to be eliminated;

[0113] Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster;

[0114] Based on the semantic analysis technology, the patient's symptom status is determined according to the patient's vocal segment and the remaining non-patient vocal segment in the vocal segment cluster, and used as the preprocessing result; the patient's vocal segment and the remaining non-patient vocal segment in the vocal segment cluster can be used to determine the patient's symptoms, perform semantic analysis, and determine the patient's symptom status;

[0115] Wherein, the fragment cluster conditions include:

[0116] The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments;

[0117] There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold. The existence of intersection means that there is an overlap between the vocal segments; the minimum interval distance refers to the distance between the sides of two vocal segments that are close to each other; the distance unit on the time axis is a time unit; the distance threshold can be, for example: 5 seconds;

[0118] The vocal segment clusters selected using the segment cluster conditions represent such an actual application scenario: when patients introduce their own symptoms, they may introduce incomplete or incorrect information, and their accompanying personnel may take the initiative to supplement and correct them. When such an actual application scenario occurs, the non-patient vocal segments in the vocal segment cluster are effectively verified. If the verification is passed, it means that the patient's accompanying personnel are indeed actively supplementing and correcting, and the corresponding non-patient vocal segments can also be used to determine the patient's symptoms. This greatly improves the applicability of the system.

[0119] In one embodiment, the recommendation module effectively verifies the non-patient vocal segment in the vocal segment cluster, including:

[0120] Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library;

[0121] If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved;

[0122] Determine whether the person image meets any image trigger condition in a preset image trigger condition library;

[0123] When none of them meet the requirements, the effective verification is passed.

[0124] When a non-patient vocal segment in a vocal segment cluster contains a first triggering semantic word, it means that the non-patient vocal segment can also be used to determine the patient's symptoms; for example: the first triggering semantic word is "he last night", "he is uncomfortable" (the accompanying person refers to the patient as "he", indicating that he is actively supplementing and correcting the symptoms for the patient), etc. When the image triggering condition is met, it means that the non-patient vocal segment cannot be used to determine the patient's symptoms, for example: the image triggering condition is that the patient has an unexpected expression (at this time, the patient may think that someone is interrupting, etc.). The embodiment of the present invention intelligently and adaptively verifies the non-patient vocal segments in the vocal segment cluster, thereby improving the applicability of the system.

[0125] In one embodiment, the recommendation module determines a list of physicians with expertise based on the preprocessing results and a preset physician database, including:

[0126] Based on the preprocessing results, determining a plurality of skilled physician conditions;

[0127] Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold;

[0128] Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

[0129] The preprocessing result is the specific symptoms of the patient, and the expert physician condition is that the physician is good at solving the specific symptoms of the patient in the preprocessing result; the larger the type weight, the more suitable the physician is for the patient if the physician meets the corresponding expert physician condition; the weight and threshold can be, for example: 80; the reception status is the number of patients waiting to be seen by the physician.

[0130] The embodiment of the present invention provides a medical self-service machine intelligent diagnosis guidance method, such as Figure 2 As shown, including:

[0131] Step S1: displaying a preset discomfort part selection interface;

[0132] Step S2: receiving the discomfort site input by the patient;

[0133] Step S3: displaying a preset discomfort symptom selection interface corresponding to the discomfort part;

[0134] Step S4: receiving discomfort symptoms input by the patient;

[0135] Step S5: displaying a preset registration department selection interface corresponding to the discomfort symptom;

[0136] Step S6: Receive the registration department entered by the patient and print the corresponding receipt.

[0137] The smart medical guidance method of the medical self-service machine also includes:

[0138] Get the number of people in the queue;

[0139] When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed;

[0140] Receive symptom description information input by the patient;

[0141] Preprocessing the symptom description information;

[0142] Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined;

[0143] Displaying a list of physicians who are experts in the above-mentioned fields;

[0144] physicians who are skilled in receiving patient input;

[0145] Print the registration receipt of the specialist doctor.

[0146] The preprocessing of the symptom description information includes:

[0147] Parsing the symptom description information to obtain a human voice segment and a corresponding segment time;

[0148] Based on the segment time, the vocal segment is arranged on a preset time axis;

[0149] Obtain a persona portrait of the patient;

[0150] Based on the character portrait, determining a patient vocal segment and a non-patient vocal segment from the vocal segments;

[0151] Determine a vocal segment cluster that meets the segment cluster condition from the time axis;

[0152] Effectively verifying the non-patient vocal segment in the vocal segment cluster;

[0153] Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster;

[0154] Based on the semantic analysis technology, the patient's symptom condition is determined according to the patient's vocal segment and the remaining non-patient vocal segments in the vocal segment cluster, and used as the preprocessing result;

[0155] Wherein, the fragment cluster conditions include:

[0156] The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments;

[0157] There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold.

[0158] The effectively verifying the non-patient vocal segment in the vocal segment cluster includes:

[0159] Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library;

[0160] If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved;

[0161] Determine whether the person image meets any image trigger condition in a preset image trigger condition library;

[0162] When none of them meet the requirements, the effective verification is passed.

[0163] The list of physicians with expertise is determined based on the pre-processing results and the preset physician database, including:

[0164] Based on the preprocessing results, determining a plurality of skilled physician conditions;

[0165] Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold;

[0166] Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

[0167] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A medical self-service machine intelligent guidance system, characterized in that: include: A first display module, used for displaying a preset discomfort part selection interface; A first receiving module is used to receive the discomfort part input by the patient; A second display module, used for displaying a preset discomfort symptom selection interface corresponding to the discomfort part; A second receiving module is used to receive discomfort symptoms input by the patient; A third display module is used to display a preset registration department selection interface corresponding to the discomfort symptom; The third receiving module is used to receive the registration department input by the patient and print the corresponding receipt; Also includes: Recommended modules for this include: Get the number of people in queue; When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed; Receive symptom description information input by the patient; Preprocessing the symptom description information; Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined; Displaying a list of physicians who are experts in the above-mentioned fields; physicians who are skilled in receiving patient input; Printing the registration receipt of the physician; The recommendation module preprocesses the symptom description information, including: Parsing the symptom description information to obtain a human voice segment and a corresponding segment time; Based on the segment time, the vocal segment is arranged on a preset time axis; Obtain a persona portrait of the patient; Based on the character portrait, determining a patient vocal segment and a non-patient vocal segment from the vocal segments; Determine a vocal segment cluster that meets the segment cluster condition from the time axis; Effectively verifying the non-patient vocal segment in the vocal segment cluster; Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster; Based on the semantic analysis technology, the patient's symptom condition is determined according to the patient's vocal segment and the remaining non-patient vocal segments in the vocal segment cluster, and used as the preprocessing result; Wherein, the fragment cluster conditions include: The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments; There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold; The recommendation module effectively verifies the non-patient vocal segment in the vocal segment cluster, including: Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library; If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved; Determine whether the person image meets any image trigger condition in a preset image trigger condition library; When none of them meet the requirements, the effective verification is passed.

2. The medical self-service machine intelligent guidance system as claimed in claim 1, characterized in that: The recommendation module determines a list of physicians who are experts based on the preprocessing results and the preset physician database, including: Based on the preprocessing results, determining a plurality of skilled physician conditions; Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold; Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

3. A medical self-service machine intelligent guidance method, characterized in that: include: Display the preset discomfort part selection interface; Receive patient input of the site of discomfort; Displaying a preset discomfort symptom selection interface corresponding to the discomfort part; Receive patient input of discomfort symptoms; Displaying a preset registration department selection interface corresponding to the discomfort symptom; Receive the registration department entered by the patient and print the corresponding receipt; Also includes: Get the number of people in queue; When the number of people in the queue is less than or equal to a preset threshold, a preset symptom description prompt interface is displayed; Receive symptom description information input by the patient; Preprocessing the symptom description information; Based on the pre-processing results and the preset physician database, a list of physicians with expertise is determined; Displaying a list of physicians who are experts in the above-mentioned fields; physicians who are skilled in receiving patient input; Printing the registration receipt of the physician; The preprocessing of the symptom description information includes: Parsing the symptom description information to obtain a human voice segment and a corresponding segment time; Based on the segment time, the vocal segment is arranged on a preset time axis; Obtain a persona portrait of the patient; Based on the character portrait, determining a patient vocal segment and a non-patient vocal segment from the vocal segments; Determine a vocal segment cluster that meets the segment cluster condition from the time axis; Effectively verifying the non-patient vocal segment in the vocal segment cluster; Eliminating the non-patient vocal segments that have not passed effective verification in the vocal segment cluster; Based on the semantic analysis technology, the patient's symptom condition is determined according to the patient's vocal segment and the remaining non-patient vocal segments in the vocal segment cluster, and used as the preprocessing result; Wherein, the fragment cluster conditions include: The vocal segment cluster includes at least one of the patient vocal segments and at least one of the non-patient vocal segments; There is an intersection between two adjacent vocal segments in the vocal segment cluster or the minimum interval distance is less than or equal to a preset distance threshold; The effectively verifying the non-patient vocal segment in the vocal segment cluster includes: Determining whether the non-patient vocal segment in the vocal segment cluster contains a first trigger semantic word in a preset trigger semantic word library; If it is included, the effective verification is passed; otherwise, the person image of the patient within the segment time of the non-patient human voice segment in the human voice segment cluster is retrieved; Determine whether the person image meets any image trigger condition in a preset image trigger condition library; When none of them meet the requirements, the effective verification is passed.

4. A medical self-service machine intelligent guidance method as claimed in claim 3, characterized in that: The list of physicians with expertise is determined based on the pre-processing results and the preset physician database, including: Based on the preprocessing results, determining a plurality of skilled physician conditions; Determine from the physician database a plurality of physicians to be selected who meet the conditions of the skilled physician and the corresponding physician reception status; the sum of the preset type weights corresponding to the condition types of the skilled physician conditions met by the physician to be selected is greater than or equal to the preset weight and threshold; Based on the multiple doctors to be selected and the corresponding doctor reception status, the list of skilled doctors is generated.

Images