Intelligent service system and method for treating trigeminal neuralgia
Through the intelligent service system for treating trigeminal neuralgia, the language selection map and online matching function are used to solve the problem of inconvenient communication between patients, and the provision of convenient doctor-patient communication and personalized rehabilitation plans, improving treatment efficiency and patient experience .
Patent Information
- Application Number
- CN202410948954.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-16
AI Technical Summary
Patients with trigeminal neuralgia need to communicate frequently with doctors during treatment and rehabilitation, but due to the condition, it is difficult to open their mouths or unable to speak normally, which leads to inconvenient communication and needs to go to the hospital to communicate frequently, which is cumbersome and inconvenient.
A smart service system for the treatment of trigeminal neuralgia is designed. By generating a language quick selection map, patients can quickly enter the questioning language with the assistance of the system, without having to speak, and remote communication is achieved by matching idle doctors online. The system also provides personalized rehabilitation. Plans, such as Chinese medicine ear drop therapy.
It realizes the convenience of online communication between patients with trigeminal neuralgia and doctors, reduces the frequency of hospital visits, improves the applicability of communication when the disease occurs, and provides personalized rehabilitation plans to improve treatment effect.
Smart Images

Figure CN118919100A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of treatment services, and in particular to an intelligent service system and method for treating trigeminal neuralgia. Background Art
[0002] Trigeminal neuralgia is a common cranial nerve disease. The treatment period of trigeminal neuralgia is relatively long. During the treatment and rehabilitation period, patients need to keep communicating with their doctors. Doctors can make the latest diagnosis and treatment decisions based on the patient's new symptoms.
[0003] However, when patients want to communicate with doctors, they often need to go to the hospital, which is rather cumbersome.
[0004] In addition, when patients communicate with doctors, it is mostly when they experience an attack of trigeminal neuralgia. However, the trigeminal nerve is the nerve responsible for managing facial sensation and movement. Its dysfunction may cause weak or loss of control of oral muscle contractions, which in turn affects the ability to open the mouth. The patient cannot speak normally, affecting the patient's communication with the doctor.
[0005] Therefore, a solution is urgently needed. Summary of the invention
[0006] One of the purposes of the present invention is to provide an intelligent service system for the treatment of trigeminal neuralgia. By displaying the patient's question language to online idle doctors, and displaying the reply language of the online idle doctors to the patient, online communication between trigeminal neuralgia patients and doctors is achieved, and patients do not need to go to the hospital frequently, which improves convenience. Secondly, a language quick selection graph is introduced, and patients can quickly input question language based on the language quick selection graph with the assistance of the system without speaking, which improves the applicability of the system in situations where trigeminal neuralgia attacks may cause patients to be unable to speak normally.
[0007] An embodiment of the present invention provides a trigeminal neuralgia treatment intelligent service system, comprising:
[0008] The first service module is used to generate a language quick selection map based on the multimodal information of the patient when the patient inputs a trigeminal neuralgia treatment service request, and display the language quick selection map to the patient;
[0009] The second service module is used to assist the patient to input the question language based on the language quick selection map, match the patient with an online available doctor, and display the question language to the online available doctor;
[0010] The third service module is used for displaying the reply language to the patient when the online idle doctor inputs the reply language to reply the question language.
[0011] Preferably, the trigeminal neuralgia treatment intelligent service system further includes:
[0012] The fourth service module is used to include:
[0013] Obtain patient condition information from the patient;
[0014] Based on the patient's condition information, determine a personalized rehabilitation plan for trigeminal neuralgia; wherein the personalized rehabilitation plan for trigeminal neuralgia is a rehabilitation plan for external ear drops therapy or post-auricular smear therapy of the traditional Chinese medicine Sanchaqing;
[0015] Show the patient a personalized rehabilitation program for trigeminal neuralgia.
[0016] Preferably, the first service module generates a language quick selection map based on the multimodal information of the patient, including:
[0017] Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information;
[0018] Sort each service demand by demand probability from large to small to obtain a service demand sequence;
[0019] The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence;
[0020] The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node;
[0021] Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph;
[0022] Use the current initial map as the language quick selection map.
[0023] Preferably, the second service module assists the patient to input the question language based on the language quick selection map, including:
[0024] When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map;
[0025] When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period;
[0026] Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster;
[0027] Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content;
[0028] generating a viewing angle constraint condition based on the first target content;
[0029] Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period;
[0030] When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period;
[0031] The clustering conditions include:
[0032] The same perspective cluster contains at least a threshold number of consecutive first perspectives in the viewing perspective sequence;
[0033] and,
[0034] The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold;
[0035] The viewing angle constraints include:
[0036] When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
[0037] Preferably, the second service module matches the patient with an online available doctor, including:
[0038] Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
[0039] Preferably, the trigeminal neuralgia treatment intelligent service system further includes:
[0040] The fourth service module is used to include:
[0041] When a patient inputs a video consultation request, the online available doctors are asked whether they agree to the video consultation request;
[0042] When the online available doctor agrees to the video consultation request, the online available doctor can conduct a video consultation with the patient.
[0043] An intelligent service method for treating trigeminal neuralgia provided by an embodiment of the present invention includes:
[0044] When a patient inputs a service request for trigeminal neuralgia treatment, a language speed selection map is generated based on the patient's multimodal information, and the language speed selection map is displayed to the patient;
[0045] Assist patients to input question language based on the language quick selection map, match online doctors who are available for patients, and display the question language to online doctors who are available;
[0046] When the online available doctor inputs a reply language in reply to the question language, the reply language is displayed to the patient.
[0047] Preferably, the generating of a language quick selection atlas based on the multimodal information of the patient comprises:
[0048] Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information;
[0049] Sort each service demand by demand probability from large to small to obtain a service demand sequence;
[0050] The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence;
[0051] The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node;
[0052] Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph;
[0053] Use the current initial map as the language quick selection map.
[0054] Preferably, the method of assisting the patient to input question language based on the language speed selection atlas includes:
[0055] When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map;
[0056] When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period;
[0057] Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster;
[0058] Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content;
[0059] generating a viewing angle constraint condition based on the first target content;
[0060] Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period;
[0061] When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period;
[0062] The clustering conditions include:
[0063] The same perspective cluster contains at least a threshold number of consecutive first perspectives in the viewing perspective sequence;
[0064] and,
[0065] The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold;
[0066] The viewing angle constraints include:
[0067] When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
[0068] Preferably, matching the patient with an online available doctor includes:
[0069] Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
[0070] Preferably, the trigeminal neuralgia treatment intelligent service method further comprises:
[0071] When a patient inputs a video consultation request, the online available doctors are asked whether they agree to the video consultation request;
[0072] When the online available doctor agrees to the video consultation request, the online available doctor can conduct a video consultation with the patient.
[0073] 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.
[0074] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0075] 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:
[0076] Figure 1 A schematic diagram of a trigeminal neuralgia treatment intelligent service system according to an embodiment of the present invention;
[0077] Figure 2 This is a schematic diagram of an intelligent service method for treating trigeminal neuralgia in an embodiment of the present invention. DETAILED DESCRIPTION
[0078] 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.
[0079] The embodiment of the present invention provides a trigeminal neuralgia treatment intelligent service system, such as Figure 1 As shown, including:
[0080] The first service module 1 is used to generate a language quick selection map based on the multimodal information of the patient when the patient inputs a trigeminal neuralgia treatment service request, and display the language quick selection map to the patient;
[0081] The second service module 2 is used to assist the patient to input the question language based on the language quick selection map, match the patient with an online available doctor, and display the question language to the online available doctor;
[0082] The third service module 3 is used to display the reply language to the patient when the online idle doctor inputs the reply language to reply the question language.
[0083] The working principle and beneficial effects of the above technical solution are:
[0084] When a patient inputs a request for trigeminal neuralgia treatment service, it indicates that the patient wants to obtain trigeminal neuralgia treatment service; the patient's multimodal information includes: the patient's historical symptom information corresponding to trigeminal neuralgia, historical medication information, historical examination report information, etc.; based on the multimodal information, the relevant service needs of the patient's request for trigeminal neuralgia treatment service can be predicted, and a language quick selection map can be generated. There are a large number of candidate languages that meet the patient's service needs in the language quick selection map. With the assistance of the system, the patient can quickly select some candidate languages to form a question language; after obtaining the question language, an online idle doctor is matched for the patient, and the question language is displayed to the online idle doctor; after seeing the question language, the online idle doctor inputs a reply language to reply to the question language based on his or her own experience in trigeminal neuralgia treatment; after obtaining the reply language, the patient can take corresponding treatment measures by viewing the reply language.
[0085] This application enables online communication between trigeminal neuralgia patients and doctors by displaying the patient's question language to online available doctors, and displaying the reply language of the online available doctors to the patient. Patients do not need to go to the hospital frequently, which improves convenience. Secondly, a language quick selection map is introduced. With the assistance of the system, patients can quickly input question language based on the language quick selection map without speaking, which improves the applicability of the system in situations where trigeminal neuralgia may cause patients to be unable to speak normally.
[0086] In one embodiment, the trigeminal neuralgia treatment intelligent service system further includes:
[0087] The fourth service module is used to include:
[0088] Obtain patient condition information from the patient;
[0089] Based on the patient's condition information, determine a personalized rehabilitation plan for trigeminal neuralgia; wherein the personalized rehabilitation plan for trigeminal neuralgia is a rehabilitation plan for external ear drops therapy or post-auricular smear therapy of the traditional Chinese medicine Sanchaqing;
[0090] Show the patient a personalized rehabilitation program for trigeminal neuralgia.
[0091] It is also possible to obtain the patient's condition information, such as medical history, age, historical medication, etc.; determine a personalized rehabilitation plan based on the patient's condition information; and display the personalized rehabilitation plan to the patient, so that the patient can receive corresponding treatment based on the personalized rehabilitation plan.
[0092] Among them, the rehabilitation plan of the Chinese medicine Sanchaqing external ear drop therapy or behind-the-ear smear therapy is as follows:
[0093] To treat trigeminal neuralgia, use Sanchaqing ear drops therapy. Drop the medicine into the external auditory canal, 1-5 drops each time (60 drops in 10 ml) depending on the severity of the condition, once in the morning and once in the evening. Keep it on the back of the pillow for 10-15 minutes after each drop. After the active ingredients of the medicine are absorbed, wipe it with a medical cotton swab.
[0094] The specific treatment process is as follows: In the first week, the patient was treated with ear drops twice a day, once in the morning and once in the evening. In the morning, the patient was treated with ear drops in the right ear and in the evening, and 1 drop (60 drops / 10 ml) was applied each time to the external auditory canal. After the drops, the patient was placed on the side of the pillow for 15 minutes. After the effective ingredients of the liquid medicine were absorbed, the patient was wiped with a medical cotton swab to remove the remaining liquid in the external auditory canal. After one week of treatment, the degree of pain was significantly reduced, the number of pains was reduced, and the trigger pain was reduced. From the second week, 2 drops were applied each time, and the pain symptoms were significantly improved. The dosage of carbamazepine was reduced from 1.2g to 1.0g per day. From the third week, 3-4 drops were applied each time. By the end of the three courses of treatment, carbamazepine was completely discontinued, spontaneous and triggered pain disappeared, the trigger point disappeared, and there was no pain attack when eating, brushing teeth, washing face, talking, and sleeping. The patient's mental state and life returned to normal. No recurrence was observed during the four-year follow-up.
[0095] In one embodiment, the first service module 1 generates a language quick selection map based on the multimodal information of the patient, including:
[0096] Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information;
[0097] Sort each service demand by demand probability from large to small to obtain a service demand sequence;
[0098] The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence;
[0099] The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node;
[0100] Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph;
[0101] Use the current initial map as the language quick selection map.
[0102] The working principle and beneficial effects of the above technical solution are:
[0103] The service demand prediction model is an artificial intelligence model that is trained on a neural network model based on a large amount of multimodal information of different trigeminal neuralgia patients marked with service needs and demand probabilities as training samples (for example: based on the patient's historical symptom information, historical medication information, and historical examination report information, the patient's treatment progress can be determined, and it is predicted which symptoms the patient will have under the treatment progress, and solutions to these symptoms will be sought as service needs, and demand probabilities will be assigned, and the service needs and demand probabilities will be marked on the patient's historical symptom information, historical medication information, and historical examination report information); the service demand prediction model can predict the patient's multiple service needs and corresponding demand probabilities based on the patient's multimodal information; there are multiple levels in the initial graph, each level has 1 main node and multiple sub-nodes, and each sub-node at the same level is connected to the main node respectively, and the demand The greater the probability, the smaller the level of the main node where the corresponding service demand is set, and multiple pre-associated candidate languages for the service demand are set on the sub-nodes of the same level, so that the patient can view it with priority when viewing; the pre-associated candidate languages for the service demand are languages that can be selected by the patient to express the service demand. For example, if the service demand is how to solve the problem of tears during an attack of trigeminal neuralgia, the corresponding pre-associated candidate languages are "symptoms during an attack", "unceasing tears", "tears lasting about 30 seconds", "tears lasting about 1 minute", etc.; the main nodes without service demand and the sub-nodes without the candidate languages in the initial graph are eliminated; the initial graph after the main nodes that need to set service demand have all set service demand and the sub-nodes that need to set the candidate languages have all set the candidate languages, and the main nodes without service demand and the sub-nodes without the candidate languages are eliminated are used as the language quick selection graph.
[0104] After viewing the language quick selection graph, the patient in the embodiment of the present invention first views the service requirements on the main node of a smaller level and the candidate languages on the child nodes of the same level, that is, the patient can preferentially view the candidate languages that have service requirements that are more likely to meet his or her actual needs, and then select the candidate languages according to his or her actual needs to generate the question language, which greatly improves the rationality of the construction of the language quick selection graph, improves the efficiency of the patient in inputting the question language, and also improves the patient experience.
[0105] In one embodiment, the second service module 2 assists the patient to input question language based on the language quick selection graph, including:
[0106] When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map;
[0107] When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period;
[0108] Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster;
[0109] Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content;
[0110] generating a viewing angle constraint condition based on the first target content;
[0111] Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period;
[0112] When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period;
[0113] The clustering conditions include:
[0114] The same perspective cluster contains at least a threshold number of consecutive first perspectives in the viewing perspective sequence;
[0115] and,
[0116] The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold;
[0117] The viewing angle constraints include:
[0118] When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
[0119] The working principle and beneficial effects of the above technical solution are:
[0120] The first duration can be, for example, 20 seconds. If the patient selects at least one candidate language within the first time period, it means that the patient has seen the service requirements and corresponding candidate languages that meet his or her actual needs in the language speed selection map displayed to him or her, and has made a selection. Therefore, based on the first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period, the question language is generated. The first language logic is the preset logic between the candidate languages. For example, if the candidate languages are "symptoms during the attack", "continuous tears", and "tears lasting about 30 seconds", the corresponding logic is that the symptoms during the attack are continuous tears and the tears lasting about 30 seconds. When the patient selects the first language logic, the question language is generated. If no language is selected from the language selection map within the time period, it means that the prediction of service demand is inaccurate, and the patient does not see the service demand that meets his or her actual needs in the language selection map displayed to him or her. At this time, the patient needs further assistance; when the patient views the language selection map, viewing perspectives will continue to be generated, and the viewing perspectives are sorted in the order of generation time to obtain a viewing perspective sequence; in the clustering condition, the number threshold can be, for example: 2; the overlap threshold can be 70%; when the same perspective cluster contains at least the number of consecutive first perspectives in the viewing perspective sequence and the overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to 1, the patient is automatically selected. When the overlap threshold is exceeded, it means that when the patient views the language selection map from multiple perspectives, the perspective changes are not much different, indicating that the patient is viewing it carefully; therefore, through the clustering condition, the multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster, and the service needs and the selected languages visible under the overlapping perspectives between the first perspectives in the same perspective cluster (the overlapping perspective exists in each first perspective in the same perspective cluster) are the content that the patient views carefully, which serves as the first target content; the second duration of the second time period can be, for example, 30 seconds; the first target content is that the patient views carefully in the first time period, but does not make a choice, indicating that the first target content does not meet the patient's actual needs. In the perspective constraint condition, when the second target content has a pre-associated content association relationship with the first target content, it means that if the first target content does not meet the patient's actual service needs, the second target content will not meet the patient's actual service needs. For example, if the first target content is a service demand for "symptom description", and the candidate voices are "symptoms during an attack", "tearing does not stop", and "tearing lasts about 30 seconds", then the second target content with a pre-set content association relationship is a service demand for "how to relieve tearing symptoms with medication", etc. (the patient does not first describe the details of the tearing symptoms to the doctor and will not directly consult how to use the medication);The second target content is about to be visible in the second perspective, which means that the second target content is close to the visible range of the second perspective. For example, the straight-line distance between the visible range of the second perspective is less than 10 cm. If the second target content is about to be visible in the second perspective for the first time, the second target content is constrained to be invisible in the second perspective, because the second target content must not meet the actual service needs of the patient. However, when the second target content is not about to be visible in the second perspective for the first time, it can be viewed by the patient to avoid system inference errors or prevent the patient from having temporary needs; similarly, when the patient selects at least one candidate language from the language selection map within the second time period and enters the question completion instruction, the question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period; the second language logic is the same as the first language logic, which will not be repeated here. ;
[0121] When assisting a patient to input a question language based on a language quick selection map, an embodiment of the present invention, if the patient selects a candidate language from the language quick selection map within a first time period, a question language is generated based on the candidate language selected by the patient, thereby realizing rapid determination of the question language; in addition, taking into account the situation where the patient's service demand prediction is inaccurate, an emergency assistance means is provided to constrain the second perspective of the patient viewing the language quick selection map within the second time period, so as to prevent the patient from viewing the second target content that does not meet his or her actual service needs as much as possible, thereby greatly improving the rationality of the assistance, improving the applicability of the system, and improving the patient experience.
[0122] In one embodiment, the second service module 2 matches the patient with an online available doctor, including:
[0123] Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
[0124] Technicians can set up a doctor matching mechanism, for example: matching patients with online available doctors who have historically seen the patient.
[0125] In one embodiment, the trigeminal neuralgia treatment intelligent service system further includes:
[0126] The fourth service module is used to include:
[0127] When a patient inputs a video consultation request, the online available doctors are asked whether they agree to the video consultation request;
[0128] When the online available doctor agrees to the video consultation request, the online available doctor can conduct a video consultation with the patient.
[0129] Patients can request a video consultation, and when the online available doctor agrees, the online available doctor can conduct a video consultation with the patient.
[0130] The embodiment of the present invention provides a trigeminal neuralgia treatment intelligent service method, such as Figure 2 As shown, including:
[0131] S1. When a patient inputs a trigeminal neuralgia treatment service request, a language selection map is generated based on the patient's multimodal information, and the language selection map is displayed to the patient;
[0132] S2, assisting the patient to input the question language based on the language quick selection map, matching the patient with an online available doctor, and displaying the question language to the online available doctors;
[0133] S3. When the online idle doctor inputs a reply language in reply to the question language, the reply language is displayed to the patient.
[0134] The method of generating a language quick selection map based on the multimodal information of the patient includes:
[0135] Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information;
[0136] Sort each service demand by demand probability from large to small to obtain a service demand sequence;
[0137] The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence;
[0138] The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node;
[0139] Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph;
[0140] Use the current initial map as the language quick selection map.
[0141] The method of assisting the patient to input question language based on the language speed selection atlas includes:
[0142] When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map;
[0143] When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period;
[0144] Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster;
[0145] Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content;
[0146] generating a viewing angle constraint condition based on the first target content;
[0147] Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period;
[0148] When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period;
[0149] The clustering conditions include:
[0150] The same perspective cluster contains at least a threshold number of consecutive first perspectives in the viewing perspective sequence;
[0151] and,
[0152] The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold;
[0153] The viewing angle constraints include:
[0154] When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
[0155] The process of matching patients with available online doctors includes:
[0156] Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
[0157] The smart service method for treating trigeminal neuralgia also includes:
[0158] When a patient inputs a video consultation request, the online available doctors are asked whether they agree to the video consultation request;
[0159] When the online available doctor agrees to the video consultation request, the online available doctor can conduct a video consultation with the patient.
[0160] 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 trigeminal neuralgia treatment intelligent service system, characterized in that: include: The first service module is used to generate a language quick selection map based on the multimodal information of the patient when the patient inputs a trigeminal neuralgia treatment service request, and display the language quick selection map to the patient; The second service module is used to assist the patient to input the question language based on the language quick selection map, match the patient with an online available doctor, and display the question language to the online available doctor; The third service module is used for displaying the reply language to the patient when the online idle doctor inputs the reply language to reply the question language.
2. The trigeminal neuralgia treatment intelligent service system according to claim 1, characterized in that: Also includes: The fourth service module is used to include: Obtain patient condition information from the patient; Based on the patient's condition information, determine a personalized rehabilitation plan for trigeminal neuralgia; wherein the personalized rehabilitation plan for trigeminal neuralgia is a rehabilitation plan for external ear drops therapy or post-auricular smear therapy of the traditional Chinese medicine Sanchaqing; Show the patient a personalized rehabilitation program for trigeminal neuralgia.
3. The trigeminal neuralgia treatment intelligent service system according to claim 1, characterized in that: The first service module generates a language quick selection map based on the multimodal information of the patient, including: Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information; Sort each service demand by demand probability from large to small to obtain a service demand sequence; The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence; The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node; Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph; Use the current initial map as the language quick selection map.
4. The trigeminal neuralgia treatment intelligent service system according to claim 3, characterized in that: The second service module assists the patient in inputting question language based on the language quick selection graph, including: When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map; When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period; Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster; Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content; generating a viewing angle constraint condition based on the first target content; Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period; When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period; The clustering conditions include: The same perspective cluster contains at least a threshold number of first perspectives in a viewing perspective sequence; and, The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold; The viewing angle constraints include: When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
5. The trigeminal neuralgia treatment intelligent service system according to claim 1, characterized in that: The second service module matches the patient with an online available doctor, including: Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
6. The trigeminal neuralgia treatment intelligent service system according to claim 1, characterized in that: Also includes: The fourth service module is used to include: When a patient inputs a video consultation request, the online available doctors are asked whether they agree to the video consultation request; When the online available doctor agrees to the video consultation request, the online available doctor can conduct a video consultation with the patient.
7. A smart service method for treating trigeminal neuralgia, characterized in that: include: When a patient inputs a request for trigeminal neuralgia treatment service, a language speed selection map is generated based on the patient's multimodal information, and the language speed selection map is displayed to the patient; Assist patients to input question language based on the language quick selection map, match online doctors who are available for patients, and display the question language to online doctors who are available; When the online available doctor inputs a reply language in reply to the question language, the reply language is displayed to the patient.
8. The intelligent service method for treating trigeminal neuralgia according to claim 7, characterized in that: The method of generating a language quick selection map based on the multimodal information of the patient includes: Based on the pre-trained service demand prediction model, the patient's multiple service demands and corresponding demand probabilities are predicted according to multimodal information; Sort each service demand by demand probability from large to small to obtain a service demand sequence; The i-th service demand in the service demand sequence is set on the master node of the i-th level in the initial graph; i = 1, 2, 3, ..., N; N is the total number of service demands in the service demand sequence; The multiple candidate languages pre-associated with the i-th service demand in the service demand sequence are respectively set on each sub-node of the i-th level in the initial graph; one candidate language is set on each sub-node; in the initial graph, each sub-node of the same level is connected to the main node respectively, and the smaller the level, the higher the priority of displaying the service demand set on the main node of the corresponding level and the candidate languages set on each sub-node; Eliminate the main nodes that do not set service requirements and the sub-nodes that do not set the candidate language in the initial graph; Use the current initial map as the language quick selection map.
9. The intelligent service method for treating trigeminal neuralgia according to claim 8, characterized in that: The method of assisting the patient to input question language based on the language speed selection atlas includes: When the patient selects at least one candidate language from the language speed selection map within a first time period and inputs a question completion instruction, a question language is generated based on a first language logic pre-associated between the candidate languages selected by the patient from the language speed selection map within the first time period; the first time period is a time period of a first duration before the patient views the language speed selection map; When the patient does not select any candidate language from the language speed selection atlas within the first time period, obtaining a viewing angle sequence of the patient viewing the language speed selection atlas within the first time period; Based on a clustering condition, multiple first perspectives in the viewing perspective sequence are divided into at least one perspective cluster; Obtaining the service requirements and candidate languages visible in the overlapping perspectives between the first perspectives in the same perspective cluster in the language quick selection graph, and using them as the first target content; generating a viewing angle constraint condition based on the first target content; Based on the perspective constraint condition, a perspective constraint is imposed on a second perspective of the patient viewing the language speed selection atlas within a second time period; the second time period is a time period of a second duration that is after the first time period and adjacent to the second time period; When the patient selects at least one candidate language from the language selection map within the second time period and inputs a question completion instruction, a question language is generated based on the second language logic pre-associated between the candidate languages selected by the patient from the language selection map within the second time period; The clustering conditions include: The same perspective cluster contains at least a threshold number of first perspectives in a viewing perspective sequence; and, The overlap between two adjacent first perspectives in the same perspective cluster is greater than or equal to the overlap threshold; The viewing angle constraints include: When the second target content is about to be visible at the second viewing angle for the first time, the second target content is constrained to be invisible at the second viewing angle; the second target content is other service requirements and candidate languages that have a pre-associated content association relationship with the first target content in the language quick selection graph.
10. The intelligent service method for treating trigeminal neuralgia according to claim 7, characterized in that: The process of matching patients with available online doctors includes: Based on the doctor matching mechanism, online idle doctors are matched for patients from the online idle doctor database.
Citation Information
Patent Citations
Content recommendation method and device
CN111736752A
Knowledge graph assisted automatic diagnosis dialogue system
CN113889259A
Magnetic resonance image remote inquiry system and method combined with artificial intelligence language model
CN117012404A
Generative question answering method and device based on knowledge graph and storage medium
CN118069817A
Medical interview support system, medical interview support method, medical interview sheet creation device, prescription, medical interview sheet code, and program
JP2020194374A
