Auxiliary triage method, device and equipment based on disease description information, medium

Abstract

The application provides an auxiliary triage method and device based on illness description information, equipment and a medium. The method comprises the following steps: determining a reference set from a plurality of preset sets based on a target age, and constructing a target set based on a plurality of habitual description words associated with a target part in the reference set; inputting the target set and the illness description information into an NLP model to obtain a target description word determined by the NLP model from the target set based on the illness description information; determining target symptom information based on preset symptom information associated with the target description word, and determining a triage result based on the target symptom information. The target part and the target age can be used as information indexes, the target set can be dynamically constructed based on the habitual description words conforming to the part of the patient and the description habit, the risk of misrecognition of the NLP model can be reduced by excluding irrelevant classification basis, the habitual description words are used as the triage basis, the triage accuracy is improved in the case of being unfamiliar with professional terms, and the patient experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent triage, and in particular to an auxiliary triage method and device based on disease description information, equipment and a medium. BACKGROUND

[0002] At present, most hospitals have begun to use online registration. After registering through the applet or APP of the hospital, patients can choose the corresponding department and doctor for treatment according to their own health status. However, the distribution of departments in different hospitals is different, and the subfields that each doctor is good at also have differences. Many patients still do not know how to choose the department and doctor when registering, and the patient experience is poor.

[0003] With the development of artificial intelligence technology, the natural language processing (NLP) model has begun to be applied to the field of auxiliary triage. In related technologies, the NLP model has been deployed on the triage device. The patient inputs the disease description information through the user terminal or the triage device. The triage device inputs the disease description information into the NLP model and outputs the recommended department and recommended doctor, which can improve the patient experience to a certain extent. However, the related technology directly uses the disease description information as the input of the NLP model. Although the recognition accuracy of the current NLP model is high, some patients still have insufficient language expression ability, and the disease description information is usually ambiguous, which causes the output result of the NLP model to deviate from the patient's demand. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides an auxiliary triage method and device based on disease description information, which can optimize the recognition and classification of the NLP model, improve the accuracy of auxiliary triage, and improve the patient experience.

[0005] In a first aspect, the present application provides an auxiliary triage method based on disease description information, applied to a triage device. The triage device is preconfigured with an NLP model, a plurality of preset symptom information and a plurality of preset sets. Each preset set includes the habitual description words associated with each preset symptom information. The habitual description words associated with the same preset symptom information in at least two preset sets are different from each other. Each habitual description word is associated with at least one preset part. Each preset set corresponds to a different age interval. The method comprises:

[0006] Obtaining the target age, target part and disease description information input by the patient;

[0007] determine a reference set from a plurality of preset sets based on the target age, and construct a target set based on a plurality of the habitual descriptors associated with the target part in the reference set;

[0008] input the target set and the illness description information into the NLP model, and obtain a target descriptor determined by the NLP model from the target set based on the illness description information;

[0009] determine target symptom information based on the preset symptom information associated with the target descriptor, and determine a triage result based on the target symptom information, wherein the triage result records target doctor information.

[0010] According to some embodiments of the present application, after determining the triage result based on the target symptom information, the method further comprises:

[0011] determine a first descriptor corresponding to each of the target descriptors in the illness description information, determine the target descriptors as second descriptors, and determine the target symptom information as reference symptom information;

[0012] construct reference description information based on the first descriptors, the second descriptors, and the reference symptom information;

[0013] record the reference description information, and associate the reference description information to the target doctor information.

[0014] According to some embodiments of the present application, the triage device is preset with a plurality of selectable doctor information, each of the selectable doctor information is pre-associated with at least one of the preset parts and at least one of the preset symptom information; determining the triage result based on the target symptom information comprises:

[0015] determine a plurality of the selectable doctor information associated with the target part as candidate doctor information, and traverse each of the candidate doctor information based on the illness description information, wherein at least one of the candidate doctor information is pre-associated with at least one of the reference description information;

[0016] when the first descriptor associated with the candidate doctor information is recorded in the illness description information, determine the corresponding candidate doctor information as the target doctor information;

[0017] when any of the first descriptors fails to be successfully matched based on the illness description information, determine at least one of the target doctor information from a plurality of the candidate doctor information based on the target symptom information;

[0018] generate the triage result based on any of the target doctor information.

[0019] According to some embodiments of the present application, before generating the triage result based on any of the target doctor information, the method further comprises:

[0020] When the target doctor information cannot be determined based on the illness description information and the target symptom information, determining a plurality of associated parts from a plurality of the target part pre-associated parts;

[0021] Determining a plurality of the optional doctor information associated with the associated part as the associated doctor information, wherein the associated doctor information does not include any of the candidate doctor information;

[0022] Determining the target doctor information from a plurality of the associated doctor information based on the target symptom information and the illness description information.

[0023] According to some embodiments of the present application, before inputting the target set and the illness description information into the NLP model, the method further comprises:

[0024] Inputting the illness description information and the reference description information associated with a plurality of the candidate doctor information into the NLP model to obtain the target description information determined by the NLP model from a plurality of the reference description information based on the illness description information;

[0025] Determining the candidate doctor information corresponding to the target description information as the target doctor information.

[0026] According to some embodiments of the present application, each of the plurality of preset parts is associated with at least one preset symptom information, and the target age, the target part, and the illness description information input by the patient are obtained, comprising:

[0027] Constructing a first visual interface, and displaying a part option and an age input item in the first visual interface, wherein the part option comprises each of the plurality of preset parts;

[0028] Obtaining the target age input in the age input item, and determining at least one of the plurality of preset parts selected in the part option as the target part;

[0029] Determining the preset symptom information associated with the target part as the candidate symptom information, and determining at least one prompt description information from a plurality of the reference description information based on the candidate symptom information, wherein the candidate symptom information matches the reference symptom information recorded in the prompt description information;

[0030] Constructing a second visual interface, and displaying an illness input item and each of the plurality of prompt description information in the second visual interface, and obtaining the illness description information input in the illness input item.

[0031] According to some embodiments of the present application, the triage device is preconfigured with a first recommended word set, a second recommended word set and a third recommended word set, the first recommended word set comprises a plurality of preset pain recommended words, the second recommended word set comprises a plurality of preset symptom information recommended words, and the third recommended word set comprises a plurality of preset disease recommended words, each of the preset pain recommended words, the preset symptom information recommended words and the preset disease recommended words is associated with at least one of the age intervals, after the second visual interface is constructed, the method further comprises:

[0032] When the prompt description information fails to be matched, at least one candidate pain recommended word is determined from the first recommended word set based on the target age, at least one candidate symptom recommended word is determined from the second recommended word set, and at least one candidate disease recommended word is determined from the third recommended word set;

[0033] A first input item is constructed in the second visual interface, the candidate pain recommended words are displayed in the first input item, and a target pain recommended word selected in the first input item is acquired;

[0034] A second input item is constructed in the second visual interface, the candidate symptom recommended words are displayed in the second input item, and a target symptom information recommended word selected in the second input item is acquired;

[0035] A third input item is constructed in the second visual interface, the candidate disease recommended words are displayed in the third input item, and a target disease recommended word selected in the third input item is acquired;

[0036] The target pain recommended word, the target symptom information recommended word and the target disease recommended word are combined to form the disease description information.

[0037] In a second aspect, an embodiment of the present application provides an auxiliary triage device based on disease description information, comprising at least one control processor and a memory in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the auxiliary triage method based on disease description information as described in the first aspect.

[0038] In a third aspect, an embodiment of the present application provides an electronic device comprising the auxiliary triage device based on disease description information as described in the second aspect.

[0039] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium storing computer executable instructions, and the computer executable instructions are used to execute the auxiliary triage method based on disease description information as described in the first aspect.

[0040] According to the auxiliary triage method based on disease description information provided by the embodiment of the present application, the target age, target part and disease description information input by the patient are acquired; a reference set is determined from a plurality of preset sets based on the target age, and a target set is constructed based on a plurality of associated habitual description words in the reference set based on the target part; the target set and the disease description information are input into the NLP model, and a target description word is acquired by the NLP model from the target set based on the disease description information; target symptom information is determined based on the preset symptom information associated with the target description word, and a triage result is determined based on the target symptom information, wherein the triage result records target doctor information. According to the technical scheme provided by the embodiment of the present application, the target part and the target age are used as information indexes, a target set is dynamically constructed based on habitual description words conforming to the part and the description habit of a patient, the risk of misrecognition of the NLP model is reduced by excluding irrelevant classification basis, the accuracy of triage is improved in the case that the patient is not familiar with professional symptom nouns by associating the habitual description words with the symptoms, and the patient experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is a schematic diagram of the auxiliary triage method based on disease description information provided by an embodiment of the present application;

[0042] Figure 2 is a flowchart of the auxiliary triage method based on disease description information provided by another embodiment of the present application;

[0043] Figure 3 is a schematic diagram of the operation interface of the triage device provided by another embodiment of the present application;

[0044] Figure 4 is a complete flowchart of the auxiliary triage method based on disease description information provided by another embodiment of the present application;

[0045] Figure 5 is a structural diagram of the auxiliary triage device based on disease description information provided by another embodiment of the present application. DETAILED DESCRIPTION

[0046] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application.

[0047] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by up, down, front, back, left, right and the like, is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0048] In the description of the present application, one or more is understood as one or more, more than two is understood as more than two, greater than, less than, more than and the like are understood as not including the number, above, below, within and the like are understood as including the number. If the first, second is described, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of technical features indicated.

[0049] In the description of the present application, unless otherwise explicitly limited, the words such as setting, installing, connecting and the like should be broadly understood, and those skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0050] The embodiment of the present application provides an auxiliary triage method, device, equipment and medium based on disease description information, wherein the auxiliary triage method based on disease description information comprises: acquiring target age, target part and disease description information input by a patient; determining a reference set from a plurality of preset sets based on the target age, and constructing a target set based on a plurality of the habitual description words associated in the reference set based on the target part; inputting the target set and the disease description information into the NLP model, acquiring the target description word determined by the NLP model from the target set based on the disease description information; determining target symptom information based on the preset symptom information associated with the target description word, and determining a triage result based on the target symptom information, wherein the triage result records target doctor information. According to the technical scheme of the embodiment of the present application, the target part and the target age can be used as information indexes, the target set can be dynamically constructed based on the habitual description words conforming to the part and the description habit of the patient, the risk of misrecognition of the NLP model can be reduced by excluding irrelevant classification basis, the accuracy of triage can be improved in the case that the patient is not familiar with professional symptom nouns by associating the habitual description words with the symptoms, and the patient experience can be improved.

[0051] The technical scheme of the embodiment of the present application will be further described below based on the schematic diagram of the auxiliary triage method based on disease description information shown in the drawings. Figure 1

[0052] ​The embodiment of the present application provides a kind of auxiliary triage method based on illness description information, it is applied to triage equipment, triage equipment is preset with NLP model, multiple preset symptom information and multiple preset set, each preset set includes each preset symptom information associated with usual description word, the same preset symptom information in at least two preset set associated with usual description word is different, each usual description word is associated with at least one preset part, each preset set corresponds to different age interval;With reference to Figure 2 , Figure 2 The flow chart of the auxiliary triage method based on illness description information provided by the embodiment of the present application includes but is not limited to the following steps:

[0053] S10, the target age, target part and illness description information input by patient are acquired;

[0054] S20, reference set is determined from multiple preset sets based on target age, and target set is constructed based on multiple usual description words associated in reference set based on target part;

[0055] S30, target set and illness description information are input to NLP model, and target description word is acquired, which is determined from target set based on illness description information by NLP model;

[0056] S40, target symptom information is determined based on preset symptom information associated with target description word, and triage result is determined based on target symptom information, wherein, triage result records target doctor information.

[0057] It should be noted that triage equipment 10 can be a man-machine interaction device arranged in outpatient hall, in the case where patient is not clear about the department to be registered, after reaching outpatient hall, age, sick part and illness description information are input in triage equipment, and triage equipment 10 generates triage result based on the technical scheme of the embodiment and assists patient to register, improve patient experience.

[0058] It should be noted that the target age and target part can be input from the visualization interface of the triage device, and the specific input method is not limited herein. Patients of the same age have certain similarities in the way of describing the condition, for example, older patients are more vague when describing the condition, child patients may carry exaggerated components when describing the condition, and young patients are usually more accurate in describing the condition. If all the habitual description words are used as the classification basis of the NLP model, misidentification will occur because different age groups use the same habitual description words to describe different symptom information. For example, for the symptom of “contraction pain”, the habitual description word of young patients is “contraction pain”, the habitual description word of older patients is “very painful”, and the habitual description word of child patients is “always painful”. For the symptom of “severe pain”, the habitual description word of child patients is “very painful”, which is similar to the habitual description word of older patients for “contraction pain”, and there is a risk of misidentification by the NLP model when identifying the condition description information. Based on this, since each preset set of the embodiment corresponds to a different age interval, the description habits of different age groups are distinguished by different preset sets, and after the target age is determined, a preset set is uniquely matched according to the target age as a reference set, reducing the risk of similar habitual description words for different preset symptom information in the reference set, providing an information basis for improving the recognition accuracy of the NLP model. At the same time, compared with training by inputting all habitual description words, the number of classification categories can be effectively reduced, the calculation process is simplified, and the recognition efficiency is improved.

[0059] It should be noted that the habitual description words of the embodiment are not professional medical terms, but colloquial description words. When patients input condition description information, they may not necessarily use professional medical terms accurately, but are more likely to use colloquial descriptions. Since the description habits of the same age group for similar symptoms are similar, at least one habitual description word can be set for each preset symptom information in the same age interval according to actual needs, the target description word is identified from the colloquial condition description information through the colloquial habitual description word, and then the appropriate target doctor information is determined and the triage is completed.

[0060] It should be noted that the triage device of the embodiment is an auxiliary device for assisting patients who cannot accurately describe the condition and are not familiar with how to perform registration and triage. If the patient is skilled in describing symptoms, such as a patient who has been following up a chronic disease for a long time, the patient can complete registration through a conventional online registration process, and the triage device of the embodiment is not within the scope of use. Therefore, the habitual description words of the triage device of the embodiment do not use professional medical terms at all, and the NLP model is not used for accurate symptom identification, but for identifying colloquial words. The subsequent description is not repeated.

[0061] It should be noted that the reference set is determined according to the target age, and the reference set records the describing words for different symptoms, such as pain, pain level, and disease duration, etc. In order to improve the accuracy of triage, the embodiment further acquires the target part from the triage device, the target part is a part of the body, and each preset set corresponds to a preset part. Therefore, according to the target part, a target set can be uniquely determined from a plurality of reference sets, so that the describing words recorded in the target set are used to describe the symptoms of the target part, avoiding the same symptoms of different parts leading to NLP model recognition error.

[0062] It should be noted that the embodiment does not determine the doctor who needs to be triaged by using the NLP model to diagnose the disease, but excludes the inappropriate describing words through the target part and the target age, so that the target set only records the describing words of various symptoms based on the target part of the same age layer, and the describing words of the target set are used as the classification basis of the NLP model, which can effectively reduce the number of classification categories of the NLP model, exclude the classification categories with inevitable errors, simplify the model training process, and improve the calculation efficiency and accuracy. The specific principle and algorithm of the NLP model are well known to those skilled in the art, and the embodiment does not involve the improvement of the NLP algorithm.

[0063] It should be noted that after inputting the target set and the disease description information into the NLP model, the NLP model takes the disease description information as the training input, takes the describing words of the target set as the classification category, identifies the describing words corresponding to the disease description information as the target describing words, and then determines the preset symptom information corresponding to the target describing words as the target symptom information. Since the target part is also determined, the appropriate doctor can be determined in the case of having the symptom information and the part, so as to take the matched target doctor information as the triage result. The embodiment takes the target describing words as the basis and takes the target symptom information as the transfer information to determine the target doctor information required by the final triage.

[0064] Exemplarily, as Figure 1As shown, the patient inputs the target age as age 1 and the target site as site A in the triage device 10, the triage device matches a plurality of reference sets corresponding to the age interval [age 1-age 2], and then determines a target set according to site A, the target set includes the habitual word 1-1 of the symptom information 1 and the habitual words 2-1 and 2-2 of the symptom information 2, for example, the symptom information 1 is pain, the symptom information 2 is severe pain, the habitual word 1-1 is “pain sometimes and no pain sometimes”, the habitual word 2-1 is “very painful”, the habitual word 2-2 is “extremely painful”, and the illness description information is “pain sometimes and no pain sometimes”, so the NLP model outputs the habitual word 1-1 as the target description word, thereby determining the symptom information 1 as the target symptom information, determining the doctor information 1 capable of processing the symptom information 1 as the target doctor information, and further generating a triage result to guide the patient to perform a registration operation according to the target doctor information.

[0065] In addition, in an embodiment, with reference to Figure 4 After step S40 is performed, the following steps are further included, but are not limited to:

[0066] S51, determining a first description word corresponding to each target description word in the illness description information, determining the target description word as a second description word, and determining the target symptom information as reference symptom information;

[0067] S52, constructing reference description information based on the first description word, the second description word, and the reference symptom information;

[0068] S53, recording the reference description information, and associating the reference description information to the target doctor information.

[0069] It should be noted that the illness description information can contain more description information, so a plurality of target description words can be matched, and in this embodiment, the segmented words in the illness description information matched with each target description word are determined as the first description word, the matched target description word is determined as the second description word, and the target symptom information corresponding to the target description word is determined as the reference symptom information. The first description word can be determined by obtaining the recognition log of the NLP model, and the string used to recognize each target description word in the recognition log can be obtained.

[0070] For example, the illness description information is “pain for a period of time after eating every day, and no pain”, the target description word is identified as “pain after eating” based on “eating”, and the target description word is identified as “pain sometimes and no pain sometimes” based on “pain for a period of time after eating and no pain”, and the identified target symptom information is “pain”, the first description word includes “eating” and “pain for a period of time after eating and no pain”, and the second description word includes “pain after eating” and “pain sometimes and no pain sometimes”.

[0071] It should be noted that the embodiment is based on the first description word, the second description word and the reference symptom information to construct the reference description information, and is associated with the target doctor information. The target doctor information can be associated with an information set constructed based on the patient's condition description information. When new condition description information is obtained next time, model recognition can be directly skipped, and matching with the reference description information can be directly performed. If the content recorded by the text is the same, it can be determined that the new patient and the previous patient have the same symptoms, and the same target doctor information can be directly matched, thereby improving the information matching efficiency. Moreover, adaptive collection of matching information can be realized, the corpus associated with the target doctor information is continuously increased with the continuous use of the triage device, and the matching accuracy is improved.

[0072] In addition, in an embodiment, with reference to Figure 4 , the triage device is pre-provided with a plurality of selectable doctor information, each of which is pre-associated with at least one preset part and at least one preset symptom information; in step S40, the triage result is determined based on the target symptom information, specifically including but not limited to the following steps:

[0073] S41, the plurality of selectable doctor information associated with the target part is determined as the candidate doctor information, and each candidate doctor information is traversed based on the condition description information, wherein at least one candidate doctor information is pre-associated with at least one reference description information;

[0074] S42, when the first description word associated with the candidate doctor information is recorded in the condition description information, the corresponding candidate doctor information is determined as the target doctor information;

[0075] S43, when no first description word is successfully matched based on the condition description information, at least one target doctor information is determined in the plurality of candidate doctor information based on the target symptom information;

[0076] S44, the triage result is generated based on any target doctor information.

[0077] It should be noted that the triage device is provided with a plurality of selectable doctor information, each of which can be dynamically activated according to the doctor's scheduling situation to avoid that the registration cannot be completed after the triage result is determined. Unless otherwise specified, the subsequent selectable doctor information is the doctor information that can perform the registration operation, and the doctor information that is not on duty or has been fully registered is not determined as the selectable doctor information.

[0078] It should be noted that in the embodiment, the target part is first selected from the selectable doctor information to obtain the candidate doctor information, so as to ensure that the part associated with the candidate doctor information includes the target part. For example, when the target part is the abdomen, the departments such as internal medicine, urology and endocrinology whose optional patient parts are the abdomen can be determined as the candidate doctor information. The target part is used to reduce the subsequent matching range, and the matching accuracy of the doctor information is improved.

[0079] It should be noted that after the candidate doctor information is determined, according to the description of the above embodiment, when each selectable doctor information is determined as the target doctor information, the reference description information generated based on the triage result is associated in the target doctor information, so that each selectable doctor information can be associated with multiple reference description information as the triage device is used, and the first description word carried in the reference description information can be used as a matching basis for the patient's colloquial description. When two patients describe the same disease, assigning the same target doctor information to them can ensure that the triage result is correct. Complex model calculation can be skipped, and historical information can be used to improve triage efficiency.

[0080] It should be noted that in this embodiment, whenever the target age, target part and disease description information input by a patient are obtained, the candidate doctor information is first determined according to the target part, and then the disease description information is matched with the first description word recorded in the candidate doctor information. At this time, there is no need to distinguish different target ages. According to the description of the above embodiment, the disease description information can have multiple words, and if each word can be matched with the first description word of the same reference description information, the current patient and the patient corresponding to the matched reference description information have the same description habit. At this time, there is no need to consider the age difference, but the result of matching the disease description information with the first description word is used as the basis for successful description habit matching, and the corresponding candidate doctor information is directly determined as the target doctor information.

[0081] For example, as shown in Figure 1 When the disease description information is obtained, multiple candidate doctor information is screened according to part A, which is doctor information 1, doctor information 2 and doctor information 3. When the disease description information is matched with the description word 1 of the doctor information 1, the doctor information 1 is determined as the target doctor information, and the triage result is determined.

[0082] It should be noted that when the first description word cannot be successfully matched, that is, at least one word in the disease description information is not recorded in the reference description information of the same candidate doctor information, it cannot be considered as the same description of different patients for the same symptom. At this time, the target symptom information is determined according to steps 30 and 40, and the target doctor information is matched according to the preset symptom information associated with each doctor information, for example Figure 1 As shown in When the target symptom information determined based on the NLP model is symptom information 1, the doctor information 1, the doctor information 2 and the doctor information 3 can be determined as the target doctor information. In the case of multiple target doctor information, one can be selected to generate the triage result, which will not be described here.

[0083] In addition, in an embodiment, referring to Figure 4Before step S44 is performed, the following steps are further included but not limited to:

[0084] S431, when the target doctor information is unable to be determined based on the illness description information and the target symptom information, determining a plurality of associated parts pre-associated with the target part from a plurality of preset parts;

[0085] S432, determining a plurality of selectable doctor information associated with the associated part as the associated doctor information, wherein the associated doctor information does not include any candidate doctor information;

[0086] S433, determining the target doctor information from the plurality of associated doctor information based on the target symptom information and the illness description information.

[0087] It should be noted that when the target doctor information is determined based on the illness description information and the target symptom information, it can be determined that the current patient has a mistake in describing the illness when using the triage device, and for some symptoms, it is likely that the pain will be radiated due to the association of the part, for example, toothache will cause headache due to nerve association. The present embodiment further provides a plurality of associated parts in each preset part, and after determining the target part, the associated doctor information matched successfully is screened out by using the associated part, which can be used as a compensation mechanism for the use of the wrong description of the illness description information, and the matching success rate of the triage result is improved.

[0088] It should be noted that since the candidate doctor information has failed to match, the associated doctor information does not include the previously determined candidate doctor information, and the candidate doctor information can be marked first, and after the plurality of associated doctor information is matched according to the associated part, the associated doctor information with the mark is removed, so as to ensure that any reference doctor information is not included.

[0089] It should be noted that the determination of the target doctor information from the associated doctor information based on the target symptom information and the illness description information can refer to the description of steps S42 and S43 described above, for example, matching the reference description information of the associated doctor information according to the illness description information, or determining whether the target symptom information belongs to the preset symptom information of the associated doctor information, which will not be repeated here.

[0090] In addition, in an embodiment, referring to Figure 4 Before step S30 is performed, the following steps are further included but not limited to:

[0091] S61, inputting the illness description information and the reference description information associated with the plurality of candidate doctor information into the NLP model to obtain the target description information determined by the NLP model from the plurality of reference description information according to the illness description information;

[0092] S62, determining the candidate doctor information corresponding to the target description information as the target doctor information.

[0093] It should be noted that according to the description of steps S20 and S30, the identification of the illness description information can be realized by taking the habitual descriptors recorded in the target set as the classification basis. In the case that the number of habitual descriptors recorded in the target set is large, it is likely that misidentification will occur because the semantics of multiple habitual descriptors are relatively close. In this embodiment, the NLP model is configured with the second descriptor of the reference description information. Since the second descriptor is the target descriptor determined in advance, if the NLP model can identify the second descriptor according to the illness description information at this time, the reference description information of the identified second descriptor is determined as the target description information, and the corresponding candidate doctor information is determined as the target doctor information.

[0094] It should be noted that steps S30 of the present embodiment and the above-mentioned embodiments are both for descriptor identification using the NLP model. Since the classification categories of the present embodiment are further reduced compared with the target set in step S30, the present embodiment can set a first similarity threshold for the NLP model, and a second similarity threshold is set in step S30. The first similarity threshold is greater than the second similarity threshold, so that the present embodiment performs information identification based on fewer classification categories and through a higher similarity threshold. If the matching of the target description information can still be completed at this time, it can be determined that the second descriptor in the target description information is relatively similar to the illness description information, and the target description information and the target doctor information can be determined.

[0095] In addition, in an embodiment, with reference to Figure 4 Each preset part is associated with at least one preset symptom information, and step S10 specifically includes but is not limited to the following steps:

[0096] S11, constructing a first visualization interface, displaying a part option and an age input item in the first visualization interface, wherein the part option includes each preset part;

[0097] S12, obtaining a target age input in the age input item, and determining at least one preset part selected in the part option as a target part;

[0098] S13, determining the preset symptom information associated with the target part as candidate symptom information, and determining at least one prompt description information from the plurality of reference description information based on the candidate symptom information, wherein the candidate symptom information matches the reference symptom information recorded in the prompt description information;

[0099] S14, constructing a second visualization interface, displaying an illness input item and each prompt description information in the second visualization interface, and obtaining illness description information input in the illness input item.

[0100] It should be noted that each preset site can be associated with any number of preset symptom information, which can be pre-configured according to actual needs. The embodiment uses the target site to screen the candidate symptom information, excludes the preset symptom information that the target site does not have, filters out the wrong selection from the information selection level, and improves the accuracy of information matching.

[0101] It should be noted that, as Figure 3 indicated, the first visualization interface can be generated on the triage device 10, and the site selection 11 and the age input item 12 are displayed in the first visualization interface. The target selection can be in the form of a drop-down menu, and the preset site is each display item of the drop-down menu. Multiple target sites can be selected through a multi-selection operation, which is not limited here.

[0102] It should be noted that in step S13, the preset symptom information associated with the target site is used as the candidate symptom information. According to the description of the above embodiment, each reference description information includes the reference symptom information determined at that time. The embodiment uses the candidate symptom information as an index to determine the matched multiple reference description information as the prompt description information.

[0103] It should be noted that the embodiment displays the illness input item and the prompt description information in the second visualization interface, as shown in the example interface 1 of Figure 3 , each candidate symptom information and the corresponding prompt description information are displayed in the example interface 1, and the patient is prompted to describe his own illness through visual text, thereby improving the accuracy of the illness description information. For example, when the patient sees the prompt description 1, he can directly select the prompt description 1 as the illness description information because it is similar to his own symptoms. At this time, the candidate symptom information 1 can be directly determined as the target symptom information, and the subsequent target doctor information is determined.

[0104] It is worth noting that when recording the reference description information, the target age can also be saved as the reference age of the reference description information. After inputting a new target age, the prompt description information is filtered out in combination with the target age, ensuring that the description prompt for the patient can meet the age range of the patient, reducing the understanding threshold of the patient, and improving the input accuracy of the illness description information.

[0105] In addition, in an embodiment, referring to Figure 4 , the triage device is preconfigured with a first recommended word set, a second recommended word set and a third recommended word set. The first recommended word set includes a plurality of preset pain recommendation words, the second recommended word set includes a plurality of preset symptom information recommendation words, and the third recommended word set includes a plurality of preset illness recommendation words. Each of the preset pain recommendation words, the preset symptom information recommendation words and the preset illness recommendation words is associated with at least one age interval. After the second visualization interface is constructed in step S14, the following steps are included but not limited to:

[0106] S141, when the prompt description information is not matched, determining at least one candidate pain recommendation word from the first recommendation word set based on the target age, determining at least one candidate symptom recommendation word from the second recommendation word set, and determining at least one candidate disease recommendation word from the third recommendation word set;

[0107] S142, constructing a first input item in the second visualization interface, displaying the candidate pain recommendation word in the first input item, and obtaining a target pain recommendation word selected in the first input item;

[0108] S143, constructing a second input item in the second visualization interface, displaying the candidate symptom recommendation word in the second input item, and obtaining a target symptom information recommendation word selected in the second input item;

[0109] S144, constructing a third input item in the second visualization interface, displaying the candidate disease recommendation word in the third input item, and obtaining a target disease recommendation word selected in the third input item;

[0110] S145, grouping the target pain recommendation word, the target symptom information recommendation word, and the target disease recommendation word into disease description information.

[0111] It should be noted that when the prompt description information is not matched, it can be determined that the prior patient does not have the same disease description at this time. On this basis, the embodiment further guides the patient to input accurate disease description information through the first input item, the second input item and the third input item.

[0112] It should be noted that the triage device can be pre-set with the first recommendation word set, the second recommendation word set and the third recommendation word set, respectively corresponding to pain, symptoms and diseases, and the pre-set pain recommendation word is used as a reference for pain description, for example Figure 3 As shown in the figure, the first recommendation word set includes pain recommendation word 1, pain recommendation word 2, pain recommendation word 3, pain recommendation word 4 and pain recommendation word 5, for example, pain recommendation word 1 is “not very painful”, pain recommendation word 2 is “generally painful, occasionally painful”, pain recommendation word 3 is “generally painful, always painful”, pain recommendation word 4 is “very painful, painful after eating”, and pain recommendation word 5 is “very painful, always painful”. The embodiment uses the habitual description word to identify and classify the patient's colloquial description information, so the pre-set pain recommendation word, the pre-set symptom recommendation word and the pre-set disease recommendation word should also be colloquial language to ensure that it can meet the usage habits of patients who are not familiar with professional medical terms. The pre-set symptom recommendation word can be a visible symptom description such as “skin itching” and “skin acne”, and the pre-set disease recommendation word is used to describe the disease duration and disease onset time, such as “for one month” and “pain after eating xx food”. Herein, it is not described one by one.

[0113] It should be noted that according to the description of step S20, the embodiment is based on the description habits of different age groups, so as to exclude the incorrect classification categories of the NLP model, and therefore the embodiment matches the corresponding content from the first description word set, the second description word set and the third description word set after determining the target age, for example, each preset pain description word is associated with an age interval, and the candidate pain description word is matched through the age interval, and the rest is the same.

[0114] It should be noted that the embodiment displays the first input item, the second input item and the third input item in sequence, and does not use simultaneous display. Through the strategy of displaying in sequence, the patient can be gradually guided to accurately describe the condition from different dimensions, and the influence on the accuracy of description when considering multiple dimensions at the same time can be avoided.

[0115] Exemplarily, as shown in an example interface 2, Figure 3 after inputting the target site and the target age, the first input item is displayed in the second visualization interface, each candidate pain description word is displayed through the first input item, after obtaining the target pain recommendation word, the second input item is displayed in the second visualization interface, each candidate symptom description word is displayed through the second input item, after obtaining the target symptom description word, the third input item is displayed in the second visualization interface, each candidate condition recommendation word is displayed through the third input item, and finally the condition description information is combined according to the selection of the patient in each input item, so as to improve the accuracy of subsequent recognition.

[0116] As shown in Figure 5 , Figure 5 is a structural diagram of an auxiliary triage device based on condition description information provided by an embodiment of the present application. The present application also provides an auxiliary triage device based on condition description information, which comprises:

[0117] The processor 401 can be implemented in a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute related programs to realize the technical solutions provided by the embodiments of the present application.

[0118] The memory 402 can be implemented in the form of a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a Random Access Memory (RAM), etc. The memory 402 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 402 and are called and executed by the processor 401 to implement the auxiliary triage method based on the illness description information according to the embodiments of the present application;

[0119] The input / output interface 403 is configured to realize information input and output.

[0120] The communication interface 404 is configured to realize the communication interaction between the device and other devices, and the communication can be realized in a wired manner (for example, a USB, a network cable, etc.) or in a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0121] The bus 405 is configured to transmit information between various components (for example, the processor 401, the memory 402, the input / output interface 403, and the communication interface 404) of the device.

[0122] The processor 401, the memory 402, the input / output interface 403, and the communication interface 404 are connected to each other through the bus 405 to realize the communication connection between the devices.

[0123] The embodiments of the present application also provide an electronic device, which comprises the auxiliary triage device based on illness description information as described above.

[0124] The embodiments of the present application also provide a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program. When the computer program is executed by a processor, the auxiliary triage method based on illness description information is realized.

[0125] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely with respect to the processor, which can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The above-described device embodiments are only illustrative, and units described as separate components can or can not be physically separated, implemented in one place, or distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0126] Those of ordinary skill in the art can understand that all or some steps in the above disclosed method and system can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those of ordinary skill in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, as known to those of ordinary skill in the art, communication media generally includes computer readable instructions, data structures, program modules or other data in modulated data signals such as carrier waves or other transport mechanisms, and can include any information delivery medium.

[0127] The above is a specific description of the preferred embodiment of the present application, but the present application is not limited to the above-described embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application. These equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. An auxiliary triage method based on illness description information, characterized by, The application is applied to a triage device, the triage device is provided with an NLP model, a plurality of selectable doctor information, a plurality of preset symptom information and a plurality of preset sets, each of the preset sets includes a habitual descriptor associated with each of the preset symptom information, the habitual descriptors associated with the same preset symptom information in at least two of the preset sets are different from each other, each of the habitual descriptors is associated with at least one preset part, each of the preset sets corresponds to a different age interval, each of the selectable doctor information is previously associated with at least one of the preset parts and at least one of the preset symptom information, and the method comprises: obtaining a target age, a target part and a condition description information input by a patient; determining a reference set from a plurality of preset sets based on the target age, and constructing a target set based on a plurality of habitual descriptors associated with the target part in the reference set; inputting the target set and the condition description information into the NLP model, and obtaining a target descriptor determined by the NLP model from the target set based on the condition description information; determining a target symptom information based on the preset symptom information associated with the target descriptor, and determining a triage result based on the target symptom information, wherein the triage result records target doctor information; after determining the triage result based on the target symptom information, the method further comprises: determining a first descriptor corresponding to each of the target descriptors in the condition description information, determining the target descriptor as a second descriptor, and determining the target symptom information as a reference symptom information, wherein the first descriptor is determined according to the recognition log of the NLP model; constructing a reference description information based on the first descriptor, the second descriptor and the reference symptom information, and adding the reference description information to the corpus corresponding to the target doctor information; recording the reference description information and associating the reference description information to the target doctor information; when new condition description information and new target part are obtained, candidate doctor information is determined according to a plurality of selectable doctor information associated with the new target part, and the corpus of each of the candidate doctor information is traversed based on the new condition description information, wherein at least one of the candidate doctor information is previously associated with at least one of the reference description information; when the first descriptor associated with the candidate doctor information is recorded in the new condition description information, the corresponding candidate doctor information is determined as new target doctor information, and the recognition of the NLP model is skipped.

2. The triage support method based on the illness description information according to claim 1, characterized by, determining a triage result based on the target symptom information, comprising: when no first descriptor is successfully matched based on the condition description information, at least one of the target doctor information is determined in a plurality of the candidate doctor information based on the target symptom information; generating the triage result based on any of the target doctor information.

3. The triage support method based on the illness description information according to claim 2, characterized by, before generating the triage result based on any of the target doctor information, the method further comprises: determining, from the plurality of preset positions, a plurality of associated positions pre-associated with the target position when the target doctor information cannot be determined based on the condition description information and the target symptom information; determining, as associated doctor information, a plurality of the selectable doctor information associated with the associated positions, wherein the associated doctor information does not include any of the candidate doctor information; determining the target doctor information from the plurality of associated doctor information based on the target symptom information and the condition description information.

4. The triage support method based on the illness description information according to claim 2, characterized by, Before inputting the target set and the condition description information into the NLP model, the method further comprises: inputting the condition description information and the reference description information associated with the plurality of candidate doctor information into the NLP model to obtain target description information determined by the NLP model from the plurality of reference description information based on the condition description information; determining the candidate doctor information corresponding to the target description information as the target doctor information.

5. The triage support method based on the illness description information according to claim 1, characterized by, Each of the preset positions is associated with at least one preset symptom information, and the target age, the target position, and the condition description information input by the patient are obtained, comprising: constructing a first visualization interface, wherein the first visualization interface displays a position option and an age input item, and the position option includes each of the preset positions; obtaining the target age input in the age input item, and determining at least one of the preset positions selected in the position option as the target position; determining the preset symptom information associated with the target position as candidate symptom information, and determining at least one prompt description information from the plurality of reference description information based on the candidate symptom information, wherein the candidate symptom information matches the reference symptom information recorded in the prompt description information; constructing a second visualization interface, wherein the second visualization interface displays a condition input item and each of the prompt description information, and obtaining the condition description information input in the condition input item.

6. The triage support method based on the illness description information according to claim 5, wherein The triage device is preconfigured with a first recommended word set, a second recommended word set, and a third recommended word set, the first recommended word set includes a plurality of preset pain recommended words, the second recommended word set includes a plurality of preset symptom information recommended words, and the third recommended word set includes a plurality of preset condition recommended words, each of the preset pain recommended words, the preset symptom information recommended words, and the preset condition recommended words is associated with at least one age interval, and after constructing the second visualization interface, the method further comprises: when the prompt description information cannot be matched, determining at least one candidate pain recommended word from the first recommended word set, at least one candidate symptom recommended word from the second recommended word set, and at least one candidate condition recommended word from the third recommended word set based on the target age; constructing a first input item in the second visualization interface, displaying the candidate pain recommended word in the first input item, and obtaining a target pain recommended word selected in the first input item; constructing a second input item in the second visualization interface, displaying the candidate symptom recommendation words in the second input item, and obtaining a target symptom information recommendation word selected in the second input item; constructing a third input item in the second visualization interface, displaying the candidate disease condition recommendation words in the third input item, and obtaining a target disease condition recommendation word selected in the third input item; combining the target pain feeling recommendation word, the target symptom information recommendation word, and the target disease condition recommendation word to obtain the disease condition description information.

7. An auxiliary triage device based on condition description information, characterized in that: The apparatus comprises at least one control processor and a memory connected in communication with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to perform the method for assisting triage based on disease condition description information according to any one of claims 1 to 6.

8. An electronic device, comprising: The apparatus for assisting triage based on disease condition description information comprises the apparatus according to claim 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to perform the method for assisting triage based on disease condition description information according to any one of claims 1 to 6.

Images