CN113870998A - Interrogation method, device, electronic equipment and storage medium - Google Patents
Interrogation method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113870998A CN113870998A CN202111152045.7A CN202111152045A CN113870998A CN 113870998 A CN113870998 A CN 113870998A CN 202111152045 A CN202111152045 A CN 202111152045A CN 113870998 A CN113870998 A CN 113870998A
- Authority
- CN
- China
- Prior art keywords
- information
- inquiry
- department
- doctor
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000003993 interaction Effects 0.000 claims description 44
- 238000003745 diagnosis Methods 0.000 claims description 21
- 208000024891 symptom Diseases 0.000 claims description 17
- 230000002452 interceptive effect Effects 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013145 classification model Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012417 linear regression Methods 0.000 description 7
- 206010012601 diabetes mellitus Diseases 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 206010019233 Headaches Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 231100000869 headache Toxicity 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 206010068319 Oropharyngeal pain Diseases 0.000 description 1
- 201000007100 Pharyngitis Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 208000032023 Signs and Symptoms Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The disclosure provides an inquiry method, an inquiry device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent recommendation and deep learning. The specific implementation scheme is as follows: acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified or not; and determining a target inquiry department according to the judgment result of the classification and the inquiry information. The method and the device can improve the accuracy rate of the department division of the department of the triage.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the field of intelligent recommendation and deep learning technologies, and in particular, to an inquiry method, an apparatus, an electronic device, and a storage medium.
Background
With the development of computer technology and internet, the patient can be treated and asked in an on-line way, so that the patient can more conveniently obtain the diagnosis and treatment of the doctor.
The on-line inquiry system judges departments based on the chief complaint information of the user and distributes the user to doctors of the corresponding departments for further diagnosis and treatment.
Disclosure of Invention
The disclosure provides an inquiry method, an inquiry device, electronic equipment and a storage medium.
According to an aspect of the present disclosure, there is provided an inquiry method including:
acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified or not;
and determining a target inquiry department according to the judgment result of the classification and the inquiry information.
According to an aspect of the present disclosure, there is provided an inquiry apparatus including:
the subject classification judging module is used for acquiring the inquiry information of the inquiry user and judging whether the inquiry information can be classified;
and the diagnosis department determining module is used for determining a target diagnosis department according to the judgment result of the diagnosis and the inquiry information.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of interrogation described in any of the embodiments of the disclosure, or to perform the method of interrogation described in any of the embodiments of the disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of or the method of any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of interrogation according to any of the embodiments of the present disclosure, or performs the method of interrogation according to any of the embodiments of the present disclosure.
The method and the device for generating the character fonts can improve the accuracy of the character fonts generated by the inquiry model.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic illustration of an interrogation method provided in accordance with an embodiment of the disclosure;
FIG. 2 is a schematic diagram of an interrogation method provided in accordance with an embodiment of the disclosure;
FIG. 3 is a schematic diagram of an interrogation method provided in accordance with an embodiment of the disclosure;
FIG. 4 is a schematic diagram of an interrogation method provided in accordance with an embodiment of the disclosure;
FIG. 5 is a schematic view of an interrogation apparatus provided in accordance with an embodiment of the disclosure;
FIG. 6 is a block diagram of an electronic device for implementing an interrogation method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of an inquiry method disclosed according to an embodiment of the present disclosure, and this embodiment may be applied to a case where a user obtains a triage department corresponding to inquiry information. The method of this embodiment may be executed by an interrogation apparatus, which may be implemented in software and/or hardware, and is specifically configured in an electronic device with certain data operation capability, where the electronic device may be a client device or a server device, and the client device may be a mobile phone, a tablet computer, a vehicle-mounted terminal, a desktop computer, and the like.
S101, acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified.
The embodiment of the disclosure can be applied to an application scene of on-line inquiry, or can also be applied to an application scene of self-help diagnosis guiding of diagnosis guiding equipment. The inquiry user refers to a user who needs to be diagnosed, specifically, a user who needs to judge whether the condition of an illness is mild or urgent and belongs to a special subject according to main symptoms and signs, and reasonably arranges diagnosis and treatment information of a department, a doctor and the like for the patient to see the illness. The inquiry information can be content describing diseases to be diagnosed of the inquiry user, and can comprise at least one of the following items: user attribute information, symptom information, and historical visit information, and the user attribute information may include name, gender, age, and the like. The historical visit information may include the location of the lesion, past disease, historical medication, and historical visit data (e.g., doctor's diagnosis records and medical image data). The inquiry information is used for performing inquiry on the inquiry users, and specifically comprises the step of dividing the inquiry users into departments and the step of allocating doctors, wherein the division means determining the inquiry departments to which the inquiry users belong, and the allocation doctors means determining the recommended doctors of the inquiry users in the determined inquiry departments.
The inquiry information may be input in at least one of text, voice, image, or video. The voice can be converted into text, and image recognition is carried out to recognize characters in the image, or some medical images are recognized based on some image recognition models to obtain recognition results. The input text or the recognized text can be further analyzed and intention recognized, and an analysis result and an intention recognition result are obtained. The text may be input into an analytic model including a Long Short-Term Memory (LSTM) network and a softmax network, or including a two-way LSTM network and a Conditional Random Field (CRF) network, and feature information in the inquiry information may be obtained as an analytic result, for example, at least one of text length, user attribute information, underlying diseases, symptoms, and drugs. The text is also used for inputting into the intention recognition model, and the intention recognition result corresponding to the text is obtained, and the text is "what hospital is the best hospital for treating diabetes? ", the intent recognition result includes that the underlying disease is diabetes, and that a highly ranked consulting department for treatment of diabetes is queried. In addition, the analysis result and the intention recognition result can be input into a pre-established knowledge graph, inverted indexing is carried out, and associated department information is obtained, wherein the knowledge graph comprises the corresponding relation between the analysis result and the intention recognition result and the department information. The analysis result, the intention recognition result and the associated department information can be associated with the inquiry information.
The subject classification judgment means that whether the inquiry user can be classified according to the inquiry information. In fact, the more definite the main questions in the inquiry information input by the inquiry user, the more beneficial the subject classification. The more vague the problem, the less favorable the classification. By the classification judgment, whether classification can be performed or not can be judged in advance before the classification result is determined, and classification can be further performed according to the classification judgment result, so that the classification accuracy can be improved. As described above, the determination of the propriety of division may be performed by inputting the analysis result corresponding to the inquiry information, the intention recognition result, and the associated department information.
The branch judgment can be as follows: inputting the inquiry information into a pre-trained section judgment model to obtain a section judgment result output by the section judgment model, wherein the section judgment model can be a classification model and is used for outputting a section judgment result or a section judgment result. The discipline-enabled judging model may be a machine learning model, specifically, a deep learning model, and exemplarily includes a current logistic regression model and a Neural Network model (NN). The training samples may include inquiry information and a result of determination as to whether the inquiry information corresponds to a disciplinary decision. Alternatively, the discipline-enabled or disciplined judgment may be: and detecting whether the inquiry information comprises the content corresponding to each parameter according to the preset template comprising each parameter, and determining whether the branch judgment result can be obtained according to the parameter lacking the content. Illustratively, the parameters lacking the content include a parameter a and a parameter B, and the result of determining whether the subject can be classified is that the subject cannot be classified; the parameters lacking the content comprise a parameter A, and the result of determining whether the subject can be classified is the subject classification.
And S102, determining a target inquiry department according to the judgment result of the classification and the inquiry information.
The target consulting department may refer to a department to which the consulting user belongs, and the target consulting department is used for the consulting user to select a doctor under the department to register and perform disease diagnosis.
Determining a target inquiry department according to the inquiry information under the condition that the branch judgment result is that the branch can be made; and under the condition that the classification can not be judged, prompting the user to increase information, updating the inquiry information, and determining a target inquiry department based on the updated inquiry information. Or, continuing to judge whether the department can be classified or not based on the updated inquiry information, prompting the user to increase information under the condition that the department cannot be classified, continuously updating the inquiry information until the judgment result of the department can be classified, and determining the target inquiry department according to the current updated inquiry information.
Determining a target inquiry department according to the inquiry information under the condition that the branch judgment result is that the branch can be determined, wherein the inquiry information can be input into a pre-trained branch model to obtain a branch result output by the branch model, namely determining the target inquiry department, and the branch model can be a neural network model; or the corresponding relation between the inquiry information and the inquiry departments is established in advance, and the target inquiry departments corresponding to the inquiry information are inquired.
In the prior art, in the process of online inquiry, the branch result is determined according to inquiry information input by a patient, but the inquiry information provided by the patient is fuzzy, unclear or incomplete, and the like, so that the branch result is inaccurate.
According to the technical scheme, the target inquiry department is determined according to the inquiry information and the result of the judgment on the classification, so that the accuracy of the inquiry information is improved, the inquiry information is clearer, and the accuracy of the classification is improved.
Fig. 2 is a flow chart of another inquiry method disclosed in the embodiment of the present disclosure, which is further optimized and expanded based on the above technical solution, and can be combined with the above various alternative embodiments. Determining a target inquiry department according to the judgment result of the classification and the inquiry information, which is embodied as follows: performing man-machine interaction with the inquiry user to acquire interaction information and update the inquiry information under the condition that the subject classification can not be performed or not according to the judgment result; and determining a target inquiry department according to the updated inquiry information.
S201, acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified.
And S202, performing man-machine interaction with the inquiry user to obtain interaction information and updating the inquiry information under the condition that the subject classification can not be performed according to the subject classification judgment result.
And judging whether the subject can be classified or not, wherein the result is that the subject cannot be classified, and the inquiry information is not enough to determine the target inquiry department. And the system is in man-machine interaction with an inquiry user, and is used for acquiring more detailed inquiry information from the inquiry user and enriching the inquiry information. Specifically, the human-computer interaction process is as follows: questions are provided to an interview user, who provides answers to the questions. The interaction information is used to update the interrogation information. The interactive information is a preset question and an answer input by the inquiry user aiming at the preset question. Updating the inquiry information may refer to adding the interactive information to the inquiry information to modify the inquiry information.
In fact, the interactive information includes the preset questions and the corresponding answer texts, which do not conform to the word habits of the user, and the inquiry information is the information input by the word habits of the user. Updating the inquiry information according to the interactive information may refer to converting the interactive information into information corresponding to the expression type of the inquiry information, and fusing the information with the inquiry information to update the inquiry information. For example, updating the interrogation information may include: inputting the interactive information into a pre-trained text generation model to obtain an inquiry text output by the text generation model, and fusing the inquiry text and the inquiry information, wherein the text generation model can be a neural network model and is used for converting initial information into information of user expression habits. Alternatively, updating the interrogation information may include: and extracting keywords from the interactive information based on a preset text template, adding the keywords to a position corresponding to the text template to generate an inquiry text, and fusing the inquiry information. The fusion refers to splicing the inquiry text and the inquiry information under the condition that the inquiry information is a text, and the fusion can convert the inquiry text into information of a type corresponding to the inquiry information and splicing the information with the inquiry information under the condition that the inquiry information is a non-text. For example, the interaction information is: the previous disease is diabetes. The inquiry information is as follows: i continued for 3 consecutive days. The updated inquiry information is as follows: i had diabetes with continuous headache for 3 days.
Optionally, the performing human-computer interaction with the inquiry user to obtain interaction information includes: acquiring question information, and performing man-machine interaction with the inquiry user according to the question information; acquiring answer information provided by the inquiry user based on the question information; and determining interactive information according to the question information and the answer information.
The question information is used for being provided for the inquiry user, and the inquiry user is obtained to provide answer information so as to determine interactive information. The answer information refers to the content of the inquiry user reply aiming at the question information. At least one question can be selected from a plurality of preset questions as question information and provided to the inquiry user respectively, and accordingly, an answer to each question is obtained as answer information. The question information may include a plurality of associated questions for which answer information is input by the user at the inquiry, and the question associated with the question is selected as the next question, for example, question 1 is: is there fever? The associated problem 2 is: is there a symptom of sore throat? Alternatively, it may be set that the question information has a plurality of associated question information, and the next question is determined from the plurality of associated questions according to the answer information. This is not limitative.
And determining the interactive information according to the at least one question and the corresponding answer. It will be appreciated that some questions, whether a judgment type question is a question or not, and that the combination of the question and the answer may determine the symptoms or past illness of the user being asked, for example, the questions are: whether symptoms of headache are present or not, the answer is: at this time, the inquiry user provides information that symptoms of headache are present. If only the answer is used, the real meaning of the user can not be determined.
The method comprises the steps of performing human-computer interaction with an inquiry user through pre-configured questions, obtaining answer information provided by the inquiry user aiming at the question information, determining the interaction information through the question information and the answer information, accurately and completely obtaining information such as real inquiry content and real past diseases of the inquiry user, updating the inquiry information based on the interaction information, enriching the content of the inquiry information, improving the representativeness of the inquiry information, and accordingly improving the accuracy of the branch departments.
Optionally, the obtaining of the question information includes at least one of: inquiring corresponding associated departments according to the inquiry information, and determining corresponding question information according to the accompanying symptoms of the associated departments; inquiring a corresponding target scene according to the inquiry information, and inquiring question information corresponding to the target scene according to the corresponding relation between the scene and the question information; and generating question information based on the pre-trained doctor-patient interaction model.
The associated department may refer to a department capable of making medical inquiry information. Accompanying symptoms may refer to symptoms that the associated department can diagnose. Inquiring the corresponding associated department according to the inquiry information, which can be analyzing the inquiry information and identifying the intention, inputting the analysis result and the intention identification result into a pre-established knowledge graph, indexing, acquiring the associated department information, determining the associated department, and extracting the accompanying symptoms of the associated department from the associated department information. The corresponding question information is determined according to the accompanying symptoms of the related department, and the confirmation question of at least one accompanying symptom can be generated as the question information. For example, a question of "whether there is a accompanying symptom" is generated, for example, by using the accompanying symptoms corresponding to different associated departments as candidates, and the question is confirmed by the inquiring user to obtain the corresponding answer.
Different scenes can be correspondingly configured according to the condition that the subjects can not be classified. A plurality of inquiry messages can be collected in advance, the analysis result and the intention recognition result of each inquiry message can be obtained, and the inquiry messages can be classified or manually classified, wherein each class is defined as a scene. According to the target scene corresponding to the inquiry information query, the type of the inquiry information can be determined, and a clustering algorithm or a classification model and the like can be specifically adopted. And manually editing the question information related to the inquiry process in different scenes, establishing the corresponding relation between the scenes and the question information, and selecting the question information related to the different inquiry processes by matching the inquiry information with the scenes.
The first two are to determine corresponding question information based on the interrogation information. And finally, generating a problem based on the doctor-patient interaction model, wherein the generated problem does not have a corresponding relation with the inquiry information. Historical doctor-patient conversations can be collected in advance, the question of a doctor is used as input, the answer of a patient is used as output, and a doctor-patient interaction model is trained. The doctor-patient interaction model is made to learn doctor inquiry logic, and candidate items, namely questions, are generated through the doctor-patient interaction model as question information. Illustratively, the doctor-patient interaction model includes a hidden Space (Latent Space) based end-to-end Pre-Training dialogue generation model (Plato), a Sequence-to-Sequence model (Seq 2Seq) or a feature generation Pre-Training model (DiagGPT), and the like.
At least one mode can be selected to generate problems, and under the condition of adopting at least two modes, problem information obtained in different modes can be fused, similar repeated problems are eliminated, and the problem information is obtained.
The questions are generated in various ways, so that the content of the questions can be enriched, the coverage range of the questions can be increased, the representativeness of the questions can be improved, the representativeness of answers provided by the inquiry user can be improved, and inquiry information can be enriched.
And S203, determining a target inquiry department according to the updated inquiry information.
And determining the target inquiry department according to the updated inquiry information, wherein the content can be added into the inquiry information so as to enrich more accurate inquiry information and determine the target inquiry department, so that the determination accuracy of the inquiry department can be improved.
Optionally, the determining a target interrogation department according to the updated interrogation information includes: inputting the updated inquiry information into a pre-trained department classification model to obtain a first classification result; and/or determining a second classification result in a corresponding relation between pre-established standard information and departments according to the updated inquiry information; and determining a target inquiry department according to the first classification result and the second classification result.
The first classification result is a target consulting department determined based on a department classification model. The second classification result is a target consulting department determined based on the retrieval mode.
And the department classification model is used for determining a target inquiry department corresponding to the inquiry information according to the inquiry information. The training samples include the interrogation information and the corresponding interrogation departments. For example, the department classification model is a pre-trained Neural network model, and illustratively, the department classification model includes a pre-trained model and a softmax model, a pre-trained model and a Text Convolutional Neural network model (Textcnn), or a pre-trained model and an LSTM model, and the like.
And the standard information is used for carrying out similarity retrieval with the inquiry information so as to determine a target inquiry department corresponding to the inquiry information. The standard information may be information obtained by performing abstract definition on the inquiry information, and may be understood as information obtained by classifying a plurality of inquiry information, extracting common features in each class, and performing abstract definition, and the information is used as the standard information of the class. And the corresponding relation between the standard information and the departments is used for determining the target inquiry departments corresponding to the inquiry information. And inquiring standard information corresponding to the inquiry information in a retrieval mode, and determining a target inquiry department corresponding to the corresponding standard information as the target inquiry department corresponding to the inquiry information. The search mode may be an Approximate Nearest Neighbor search mode (ANN), and for example, the standard information and the departments may be manually constructed into a library, and the inquiry information and the standard information may be subjected to ANN similarity index search to obtain departments corresponding to the similar standard information.
In the case of the update of the inquiry information, the aforementioned inquiry information may be replaced with the updated inquiry information.
And under the condition that only the first classification result is obtained, the second classification result is empty, and the target inquiry department is determined according to the first classification result and the second classification result, namely the first classification result is actually determined as the target inquiry department. And in the case that only the second classification result is obtained, the first classification result is empty, the target inquiry department is determined according to the first classification result and the second classification result, and the second classification result is actually determined as the target inquiry department. In the case of obtaining the first classification result and the second classification result, the first classification result and the second classification result may be fused to determine the target consulting department. The fusion method may be to modify the first classification result based on the second classification result. The priority of the second classification result is higher than that of the first classification result, or the second classification result can be directly determined as the target interrogation department.
By calculating the first classification result and/or the second classification result, determining the target interrogation department according to the first classification result and the second classification result, performing classification in multiple modes, and fusing the classification results to determine the target interrogation department, the classification accuracy can be improved.
According to the technical scheme, the method and the system have the advantages that the method and the system can perform man-machine interaction with the inquiry user under the condition that the classification can be judged or not, guide the inquiry user to describe the self condition more completely, obtain the interaction information and update the inquiry information, can increase the content of the inquiry information, improve the integrity of the inquiry information, enable the inquiry information to be more accurate, determine the target inquiry department according to the updated inquiry information, and can improve the accuracy of the target inquiry department, so that the classification accuracy is improved.
Fig. 3 is a flow chart of another inquiry method disclosed in the embodiments of the present disclosure, which is further optimized and expanded based on the above technical solutions, and can be combined with the above various alternative embodiments. The interrogation method was optimized as: acquiring at least one piece of candidate doctor information corresponding to the target consulting department; sequencing the information of each candidate doctor according to the inquiry information and the information of each candidate doctor; and determining recommended doctor information according to the sequencing result.
S301, acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified.
S302, determining a target inquiry department according to the judgment result of the classification and the inquiry information.
S303, acquiring at least one piece of candidate doctor information corresponding to the target consulting department.
The alternative doctor information may refer to information of doctors affiliated with the target consulting department.
The alternative doctor information is used for screening recommended doctor information and is provided for the inquiry user so as to suggest the inquiry user to register in a targeted manner, and the purpose of triage is finally achieved. The candidate doctor information is not limited to one hospital, and a candidate department that is the same as or similar to the target inquiry department may be selected from a plurality of hospitals, at least one candidate doctor belonging to the candidate department may be determined, and information of each doctor of each candidate department may be collected to form a correspondence between departments and doctor information. The physician information may include at least one of: the doctor's professional department, adept diseases, disease treatment mode and service time, etc. The corresponding relation between the doctor information and departments can be established according to professional departments in the doctor information. And inquiring the corresponding department according to the target consulting department, and determining the corresponding doctor information as the alternative doctor information.
S304, sorting the information of each candidate doctor according to the inquiry information and the information of each candidate doctor.
According to the inquiry information and the candidate doctor information, the matching degree between the inquiry information and each candidate doctor information can be determined, and the candidate doctor information is sorted according to the matching degree. And in the case of no classification, sorting the candidate doctor information according to the updated inquiry information and the candidate doctor information. The inquiry information is updated, the diagnosis intention of an inquiry user is clarified, the updated inquiry information is copied and combined with each candidate doctor information respectively to obtain at least one input information, the input information is input into a pre-trained linear regression model to obtain the score output by the linear regression model, and the candidate doctor information in the corresponding input information is sorted according to the score. The linear regression model is used for simulating a linear relation between the inquiry information and the doctor information and the matching degree between the inquiry information and the doctor information, wherein the training sample comprises inquiry characteristic information extracted from the inquiry information, doctor characteristic information extracted from the doctor information and a matching score between the inquiry information and the doctor information. The feature information may be represented in a vector form, and the inquiry feature information may include the aforementioned analysis result, the intention recognition result, and the like. The doctor feature information may include keywords in the doctor information, wherein the doctor feature information may be extracted from the doctor information based on a pre-trained text recognition model, or the doctor feature information may be extracted from the doctor information according to a preset template.
And S305, determining recommended doctor information according to the sequencing result.
The recommended doctor information is used for being recommended to the inquiry user so as to suggest the inquiry user to select the recommended doctor to make diagnosis and treat, accurate triage is achieved, and diagnosis and treatment effects are improved. According to the sorting result, the candidate doctor information with the top rank can be screened from the sorting result and determined as the recommended doctor information. For example, the first candidate doctor information may be determined as recommended doctor information; or 1-3 candidate doctor information may be determined as recommended doctor information. There are other cases, and no particular limitation is imposed.
Optionally, the sorting the information of the candidate doctors according to the inquiry information and the information of the candidate doctors includes: inquiring the severity corresponding to the inquiry information in a pre-established corresponding relation between standard information and the severity; and sequencing the information of each candidate doctor according to the inquiry information, the corresponding severity and the information of each candidate doctor.
The standard information may refer to the foregoing description. Severity refers to the severity of the condition of the user being asked for, and severity can include severity and lack of severity; or may also include extreme severity, severe severity, moderate severity, low severity, and no severity. The corresponding relation between the standard information and the severity is used for determining the corresponding severity of the inquiry information. And inquiring standard information corresponding to the inquiry information in a retrieval mode, and determining the severity corresponding to the standard information as the severity corresponding to the inquiry information. The retrieval mode may be an ANN, and illustratively, the standard information and the severity may be manually constructed into a library, and the inquiry information and the standard information are subjected to ANN similarity index retrieval to obtain the severity corresponding to the similar standard information.
Under the condition that the medical information can not be classified, the inquiry information is updated, the diagnosis intention and the disease severity of an inquiry user are clarified, the updated inquiry information and the updated severity are copied and are respectively combined with each candidate doctor information to obtain at least one input information, the input information is input into a pre-trained linear regression model, the score output by the linear regression model is obtained, and the candidate doctor information in the corresponding input information is sequenced according to the score. Specifically, the severity is added to the inquiry characteristic information, that is, the inquiry characteristic information may include the aforementioned analysis result, intention recognition result, severity, and the like. And copying the inquiry characteristic information, respectively combining the inquiry characteristic information with the doctor characteristic information of each candidate doctor information to obtain at least one piece of input information, inputting the input information into a pre-trained linear regression model, obtaining the score output by the linear regression model, and sequencing the candidate doctor information in the corresponding input information according to the score.
In addition, in the corresponding relation based on the standard information and the severity, the severity corresponding to the inquiry information is inquired, and under the condition that the inquiry result is empty, a low-level doctor can be pre-distributed to the inquiry user for inquiring the disease condition and preliminarily diagnosing the disease, and the severity of the disease condition is judged to obtain the severity determined by the doctor; alternatively, the severity of the interrogation user input may also be obtained. Wherein, the low-level doctor is opposite to the high-level doctor, and the high-level doctor can refer to the expert-level doctor; a low-ranked doctor may be an outpatient level doctor; alternatively, a high-grade doctor may refer to a doctor in Hospital; a low ranking physician may be a physician in a hospital.
By determining the severity of the inquiry user, doctor recommendation can be performed according to the severity of the illness state of the inquiry user, grading diagnosis and treatment are further realized on the basis of branch departments, the accuracy of triage is improved, recommended doctors are provided, the accuracy of triage recommendation is improved, and user experience is improved.
According to the technical scheme, the recommended doctor information is screened from the alternative doctor information by acquiring the at least one alternative doctor information corresponding to the inquiry information and based on the inquiry information, so that medical resources can be reasonably utilized, a proper doctor is provided for an inquiry user, grading diagnosis and treatment are realized, and the needle sorting accuracy is improved.
Fig. 4 is a flowchart of another inquiry method disclosed in the embodiment of the present disclosure, which is a specific application scenario of the inquiry method.
S401, acquiring inquiry information of an inquiry user.
S402, judging whether the inquiry information can be classified, and if so, executing S403; otherwise, S404 is performed.
And S403, determining a target inquiry department according to the inquiry information, and executing S405.
S404, performing man-machine interaction with the inquiry user, acquiring interaction information, and updating the inquiry information.
And the user answers and is spliced and fused with the inquiry information to obtain the updated inquiry information.
S405, inquiring the severity corresponding to the inquiry information in the pre-established corresponding relation between the standard information and the severity, and judging whether the severity can be inquired; if so, go to S406; otherwise, S407 is executed.
S406, allocating low-level doctors to the inquiry users, and inquiring diagnosis by the low-level doctors to obtain the severity.
S407, determining that the recommended doctor information is a recommended authoritative third doctor according to the severity, the inquiry information and at least one piece of alternative doctor information corresponding to the target inquiry department.
And sequencing the information of each candidate doctor according to the inquiry information, the corresponding severity and the information of each candidate doctor. And determining recommended doctor information according to the sequencing result. In the case of severe severity, the recommended physician information is the authoritative trifid physician of the target consulting department.
By judging whether the subject can be classified in advance, under the condition that the subject cannot be classified, the inquiry information is updated through man-machine interaction, the inquiry user is guided to express the basic condition of the user more completely, the content of the inquiry information can be increased, the integrity of the inquiry information is improved, the inquiry information is more accurate, the accuracy of the subject can be improved, the recommended doctor information is screened and provided for the inquiry user through acquiring the severity of the inquiry information and acquiring at least one piece of alternative doctor information corresponding to a target inquiry department, medical resources can be reasonably utilized, a proper doctor is provided for the inquiry user, graded diagnosis and treatment are realized, and the accuracy of the subject classification is improved.
According to the embodiment of the disclosure, fig. 5 is a structural diagram of an inquiry apparatus in the embodiment of the disclosure, and the embodiment of the disclosure is suitable for a case where a user acquires a triage department corresponding to inquiry information. The device is realized by software and/or hardware and is specifically configured in electronic equipment with certain data operation capacity.
An interrogation apparatus 500, as shown in fig. 5, comprises: a department-capable judging module 501 and a [108] department-determining module 502; wherein,
a subject-classification-possible judging module 501, configured to acquire inquiry information of an inquiry user, and judge whether the inquiry information is subject-classified;
and the triage department determining module 502 is used for determining a target inquiry department according to the result of the triage judgment and the inquiry information.
According to the technical scheme, the target inquiry department is determined according to the inquiry information and the result of the judgment on the classification, so that the accuracy of the inquiry information is improved, the inquiry information is clearer, and the accuracy of the classification is improved.
Further, the triage department determination module 502 includes: the inquiry information updating unit is used for carrying out man-machine interaction with the inquiry user under the condition that the classification can be judged or not is not available, acquiring interaction information and updating the inquiry information; and the triage department re-determining unit is used for determining a target inquiry department according to the updated inquiry information.
Further, the inquiry information updating unit includes: the human-computer interaction subunit is used for acquiring the question information and performing human-computer interaction with the inquiry user according to the question information; the answer information acquisition subunit is used for acquiring answer information provided by the inquiry user based on the question information; and the interactive information determining unit is used for determining interactive information according to the question information and the answer information.
Further, the human-computer interaction subunit is configured to perform at least one of the following: inquiring corresponding associated departments according to the inquiry information, and determining corresponding question information according to the accompanying symptoms of the associated departments; inquiring a corresponding target scene according to the inquiry information, and inquiring question information corresponding to the target scene according to the corresponding relation between the scene and the question information; and generating question information based on the pre-trained doctor-patient interaction model.
Further, the interrogation apparatus 500 further includes: the branch doctor acquisition module is used for acquiring at least one piece of candidate doctor information corresponding to the target consulting department; the doctor sequencing module is used for sequencing the information of each alternative doctor according to the inquiry information and the information of each alternative doctor; and the doctor recommending module is used for determining recommended doctor information according to the sorting result.
Further, the physician ranking module comprises: the severity determining unit is used for inquiring the severity corresponding to the inquiry information in the pre-established corresponding relation between the standard information and the severity; and the severity sorting unit is used for sorting the information of each candidate doctor according to the inquiry information, the corresponding severity and the information of each candidate doctor.
Further, the triage department determination module 502 includes: the model classification unit is used for inputting the updated inquiry information into a pre-trained department classification model to obtain a first classification result; and/or a search classification unit, which is used for determining a second classification result in the corresponding relation between the pre-established standard information and departments according to the updated inquiry information; and the classification fusion unit is used for determining a target inquiry department according to the first classification result and the second classification result.
The inquiry device can execute the inquiry method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects for executing the inquiry method.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the respective methods and processes described above, such as the inquiry method or the inquiry method. For example, in some embodiments, the interrogation method or interrogation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When loaded into RAM 603 and executed by the computing unit 601, a computer program may perform the above described interrogation method or one or more steps of the interrogation method. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the or an interrogation method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (17)
1. A method of interrogation comprising:
acquiring inquiry information of an inquiry user, and judging whether the inquiry information can be classified or not;
and determining a target inquiry department according to the judgment result of the classification and the inquiry information.
2. The method of claim 1, wherein determining a target interrogation department based on the discipline discriminability determination and the interrogation information comprises:
performing man-machine interaction with the inquiry user to acquire interaction information and update the inquiry information under the condition that the subject classification can not be performed or not according to the judgment result;
and determining a target inquiry department according to the updated inquiry information.
3. The method of claim 2, wherein the human-computer interaction with the interview user to obtain interactive information comprises:
acquiring question information, and performing man-machine interaction with the inquiry user according to the question information;
acquiring answer information provided by the inquiry user based on the question information;
and determining interactive information according to the question information and the answer information.
4. The method of claim 3, wherein the obtaining issue information comprises at least one of:
inquiring corresponding associated departments according to the inquiry information, and determining corresponding question information according to the accompanying symptoms of the associated departments;
inquiring a corresponding target scene according to the inquiry information, and inquiring question information corresponding to the target scene according to the corresponding relation between the scene and the question information; and
generating question information based on a pre-trained doctor-patient interaction model.
5. The method of claim 1, further comprising:
acquiring at least one piece of candidate doctor information corresponding to the target consulting department;
sequencing the information of each candidate doctor according to the inquiry information and the information of each candidate doctor;
and determining recommended doctor information according to the sequencing result.
6. The method of claim 5, wherein said ranking each of the candidate physician information according to the interrogation information and each of the candidate physician information comprises:
inquiring the severity corresponding to the inquiry information in a pre-established corresponding relation between standard information and the severity;
and sequencing the information of each candidate doctor according to the inquiry information, the corresponding severity and the information of each candidate doctor.
7. The method of claim 2, wherein the determining a target interrogation department from the updated interrogation information comprises:
inputting the updated inquiry information into a pre-trained department classification model to obtain a first classification result; and/or
According to the updated inquiry information, determining a second classification result in a corresponding relation between pre-established standard information and departments;
and determining a target inquiry department according to the first classification result and the second classification result.
8. An interrogation apparatus comprising:
the subject classification judging module is used for acquiring the inquiry information of the inquiry user and judging whether the inquiry information can be classified;
and the diagnosis department determining module is used for determining a target diagnosis department according to the judgment result of the diagnosis and the inquiry information.
9. The apparatus of claim 8, wherein the triage department determination module comprises:
the inquiry information updating unit is used for carrying out man-machine interaction with the inquiry user under the condition that the classification can be judged or not is not available, acquiring interaction information and updating the inquiry information;
and the triage department re-determining unit is used for determining a target inquiry department according to the updated inquiry information.
10. The apparatus of claim 9, wherein the interrogation information update unit comprises:
the human-computer interaction subunit is used for acquiring the question information and performing human-computer interaction with the inquiry user according to the question information;
the answer information acquisition subunit is used for acquiring answer information provided by the inquiry user based on the question information;
and the interactive information determining unit is used for determining interactive information according to the question information and the answer information.
11. The apparatus of claim 10, wherein the human-machine interaction subunit is configured to at least one of: inquiring corresponding associated departments according to the inquiry information, and determining corresponding question information according to the accompanying symptoms of the associated departments; inquiring a corresponding target scene according to the inquiry information, and inquiring question information corresponding to the target scene according to the corresponding relation between the scene and the question information; and generating question information based on the pre-trained doctor-patient interaction model.
12. The apparatus of claim 8, further comprising:
the branch doctor acquisition module is used for acquiring at least one piece of candidate doctor information corresponding to the target consulting department;
the doctor sequencing module is used for sequencing the information of each alternative doctor according to the inquiry information and the information of each alternative doctor;
and the doctor recommending module is used for determining recommended doctor information according to the sorting result.
13. The apparatus of claim 12, wherein the physician ordering module comprises:
the severity determining unit is used for inquiring the severity corresponding to the inquiry information in the pre-established corresponding relation between the standard information and the severity;
and the severity sorting unit is used for sorting the information of each candidate doctor according to the inquiry information, the corresponding severity and the information of each candidate doctor.
14. The apparatus of claim 9, wherein the triage department determination module comprises:
the model classification unit is used for inputting the updated inquiry information into a pre-trained department classification model to obtain a first classification result; and/or
The search classification unit is used for determining a second classification result in the corresponding relation between the pre-established standard information and departments according to the updated inquiry information;
and the classification fusion unit is used for determining a target inquiry department according to the first classification result and the second classification result.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the interrogation method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the interrogation method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method of interrogation according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152045.7A CN113870998A (en) | 2021-09-29 | 2021-09-29 | Interrogation method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152045.7A CN113870998A (en) | 2021-09-29 | 2021-09-29 | Interrogation method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870998A true CN113870998A (en) | 2021-12-31 |
Family
ID=79000517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111152045.7A Pending CN113870998A (en) | 2021-09-29 | 2021-09-29 | Interrogation method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870998A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114566264A (en) * | 2022-01-28 | 2022-05-31 | 北京泽桥医疗科技股份有限公司 | 3D model and content intelligent recommended doctor online timely application feedback system |
| CN116936058A (en) * | 2023-09-14 | 2023-10-24 | 北京健康有益科技有限公司 | Intelligent diagnosis guiding method and system based on deep learning and knowledge graph |
-
2021
- 2021-09-29 CN CN202111152045.7A patent/CN113870998A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114566264A (en) * | 2022-01-28 | 2022-05-31 | 北京泽桥医疗科技股份有限公司 | 3D model and content intelligent recommended doctor online timely application feedback system |
| CN116936058A (en) * | 2023-09-14 | 2023-10-24 | 北京健康有益科技有限公司 | Intelligent diagnosis guiding method and system based on deep learning and knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11334635B2 (en) | Domain specific natural language understanding of customer intent in self-help | |
| CN111090987B (en) | Method and apparatus for outputting information | |
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN112307215B (en) | Data processing method, device and computer readable storage medium | |
| CN108885623A (en) | The lexical analysis system and method for knowledge based map | |
| US10586237B2 (en) | Method, apparatus, and computer-readable media for customer interaction semantic annotation and analytics | |
| US20200192921A1 (en) | Suggesting text in an electronic document | |
| CN116501960B (en) | Content retrieval method, device, equipment and medium | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium | |
| JP2021163473A (en) | Method and apparatus for pushing information, electronic apparatus, storage medium, and computer program | |
| CN113407677A (en) | Method, apparatus, device and storage medium for evaluating quality of consultation session | |
| CN112749238A (en) | Search ranking method and device, electronic equipment and computer-readable storage medium | |
| CN117909466A (en) | Domain question-answering system, construction method, electronic device and storage medium | |
| US20230359932A1 (en) | Classification process systems and methods | |
| CN111931034A (en) | Data searching method, device, equipment and storage medium | |
| Fu | Natural language processing in urban planning: A research agenda | |
| CN113505293B (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN114664421A (en) | Doctor-patient matching method and device, electronic equipment, medium and product | |
| CN113961811A (en) | Conversational recommendation method, device, equipment and medium based on event map | |
| CN114153948A (en) | Question-answer knowledge base construction method, intelligent interaction method and device | |
| CN113326438A (en) | Information query method and device, electronic equipment and storage medium | |
| US11914844B2 (en) | Automated processing and dynamic filtering of content for display | |
| CN118069811B (en) | LLM-based document knowledge question-answering method and system | |
| CN116453702B (en) | Data processing method, device, system and medium for autism behavior feature set | |
| CN116775813B (en) | Service searching method, device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |