阅读说明：本技术 智能问诊方法、装置、设备及存储介质 (Intelligent inquiry method, device, equipment and storage medium ) 是由 喻凌威 周宝 陈远旭 于 2021-08-31 设计创作，主要内容包括：本申请涉及AI技术领域,并公开了一种智能问诊方法,包括：获取用户的人脸信息和声音信息；基于所述人脸信息确定待诊断的用户信息,根据所述用户信息获取用户的历史诊断信息；根据所述历史诊断信息生成提示信息,所述提示信息用于指示用户输入身体症状；接收用户根据所述提示信息输入的身体症状信息,将所述身体症状信息和所述声音信息输入预设的AI疾病诊断模型进行分析,得到所述用户的身体诊断结果和就医指导信息并显示。能够在减少用户就医流程的同时,综合对用户身体状况进行诊断并给出合理的就医指导信息。(The application relates to the technical field of AI and discloses an intelligent inquiry method, which comprises the following steps: acquiring face information and sound information of a user; determining user information to be diagnosed based on the face information, and acquiring historical diagnosis information of a user according to the user information; generating prompt information according to the historical diagnosis information, wherein the prompt information is used for indicating a user to input physical symptoms; and receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user. The medical treatment process of the user can be reduced, meanwhile, the physical condition of the user can be comprehensively diagnosed, and reasonable medical treatment guide information can be provided.)

1. An intelligent interrogation method, the method comprising:

acquiring face information and sound information of a user;

determining the identity identification information of the user based on the face information, and acquiring historical diagnosis information of the user according to the identity identification information;

generating prompt information according to the historical diagnosis information, wherein the prompt information is used for indicating a user to input physical symptoms;

and receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user.

2. The intelligent inquiry method of claim 1, wherein the obtaining historical diagnostic information of the user based on the identification information comprises:

and determining historical diagnosis information stored in association with the identity identification information by taking the identity identification information as an association field.

3. The intelligent inquiry method according to claim 1 or 2, wherein the generating of the prompt message according to the historical diagnosis information comprises:

preprocessing the historical diagnosis information to obtain a characteristic variable;

calculating the characteristic variables by using a preset judgment rule to obtain a calculation result;

and obtaining prompt information according to the calculation result, wherein the prompt information is used for indicating the user to input physical symptoms.

4. The intelligent inquiry method of claim 3, wherein the characteristic variables are variables composed of characteristics associated with body state data of the user, and the preprocessing the historical diagnosis information to obtain the characteristic variables comprises:

extracting target diagnosis information with the occurrence frequency larger than a preset frequency from the historical diagnosis information, and acquiring user body state data associated with the target diagnosis information;

determining characteristics associated with the acquired physical state data of the user, and forming the characteristic variables.

5. The intelligent inquiry method according to claim 4, wherein the calculating the characteristic variables by using the preset judgment rule to obtain the calculation result comprises:

judging the characteristic variables by using a pre-trained decision tree model to obtain the probability of each preset disease associated with the body state data of the user; wherein the probability of each preset disease associated with the user body state data is the calculated result.

6. The intelligent inquiry method according to claim 3, wherein said preset AI disease diagnosis model is an AI TCM diagnosis model, said AI TCM diagnosis model comprising a data processing network layer, a neural network layer, a training network layer and a detection network layer;

the step of inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis to obtain and display the physical diagnosis result and the medical instruction information of the user comprises the following steps:

inputting the physical symptom information and the sound information into the AI traditional Chinese medicine diagnosis model, respectively performing data expansion processing on the physical symptom information and the sound information through the data processing network layer, and randomly dividing the expanded data into a training sample set and a testing sample set;

building the AI traditional Chinese medicine diagnosis model based on the training sample set and the neural network layer, and training the AI traditional Chinese medicine diagnosis model based on the training sample set through the training network layer;

verifying the trained AI traditional Chinese medicine diagnosis model based on a test sample set through the detection network layer, and obtaining the trained AI traditional Chinese medicine diagnosis model after the verification is passed;

and analyzing the physical symptom information and the sound information by using the trained AI traditional Chinese medicine diagnosis model to obtain and display the physical diagnosis result and the medical instruction information of the user.

7. The intelligent interrogation method of claim 6, wherein the building of the AI TCM diagnostic model based on the training sample set and the neural network layer and the training of the AI TCM diagnostic model based on the training sample set by the training network layer comprises:

training a main network of the AI traditional Chinese medicine diagnosis model based on the training sample set, acquiring a first prediction result of a first classification output function, and determining whether the first prediction result of the first classification output function is the same as a preset disease;

and if the first prediction result is the same as the preset disease, retraining the main network of the AI traditional Chinese medicine diagnosis model based on the sound data, and monitoring a second prediction result of a second classification output function until the second prediction result is the same as the preset disease.

8. An intelligent interrogation apparatus, comprising:

the first acquisition module is used for acquiring face information and voice information of a user;

the second acquisition module is used for determining the identity identification information of the user based on the face information and acquiring the historical diagnosis information of the user according to the identity identification information;

the generating module is used for generating prompt information according to the historical diagnosis information, and the prompt information is used for indicating a user to input physical symptoms;

and the obtaining module is used for receiving the physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying the physical diagnosis result and the medical instruction information of the user.

9. An intelligent interrogation apparatus, comprising:

a memory and a processor;

the memory is used for storing a computer program;

the processor for executing the computer program and implementing the steps of the intelligent interrogation method of any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to carry out the steps of the intelligent interrogation method according to any one of claims 1 to 7.

Technical Field

The present application relates to the field of AI technologies, and in particular, to an intelligent inquiry method, apparatus, device, and storage medium.

Background

With the development and application of artificial intelligence technology, great convenience is brought to the life of people. However, there are major drawbacks in disease diagnosis. The disease diagnosis process is influenced by various factors, such as the current physical state of a user and historical case information, and the like, but the data acquired by the existing machine during automatic disease diagnosis is often single, and only specific physical symptoms can be judged, so that the physical health condition of the user cannot be comprehensively evaluated, and reasonable medical guidance can be given.

Disclosure of Invention

The application provides an intelligent inquiry method, an intelligent inquiry device, an intelligent inquiry equipment and a storage medium, wherein an AI disease diagnosis model is used for analyzing body symptom information and sound information of a user to obtain a body diagnosis result and medical instruction information of the user, so that the medical procedure of the user can be reduced, and meanwhile, comprehensive diagnosis can be made on the body health of the user and reasonable medical instruction information can be provided.

In a first aspect, the present application provides a method for intelligent interrogation, the method comprising:

acquiring face information and sound information of a user;

determining the identity identification information of the user based on the face information, and acquiring historical diagnosis information of the user according to the identity identification information;

generating prompt information according to the historical diagnosis information, wherein the prompt information is used for indicating a user to input physical symptoms;

and receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user.

In a second aspect, the present application further provides an intelligent interrogation apparatus, comprising:

the first acquisition module is used for acquiring face information and voice information of a user;

the second acquisition module is used for determining the identity identification information of the user based on the face information and acquiring the historical diagnosis information of the user according to the identity identification information;

the generating module is used for generating prompt information according to the historical diagnosis information, and the prompt information is used for indicating a user to input physical symptoms;

and the obtaining module is used for receiving the physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying the physical diagnosis result and the medical instruction information of the user.

In a third aspect, the present application further provides an intelligent inquiry apparatus, comprising:

a memory and a processor;

the memory is used for storing a computer program;

the processor is configured to execute the computer program and to implement the steps of the intelligent interrogation method according to the first aspect when executing the computer program.

In a fourth aspect, the present application also provides a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the intelligent interrogation method according to the first aspect.

The application discloses an intelligent inquiry method, an intelligent inquiry device, intelligent inquiry equipment and a storage medium, wherein face information and voice information of a user are obtained, identity identification information of the user is determined based on the face information, and historical diagnosis information of the user is obtained according to the identity identification information of the user; then generating prompt information for instructing a user to input physical symptoms according to the historical diagnosis information; and finally, receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user. The medical treatment process of the user can be reduced, meanwhile, the physical condition of the user can be comprehensively diagnosed, and reasonable medical treatment guide information can be provided.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of an intelligent inquiry method provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart diagram of a method for intelligent interrogation provided in an embodiment of the present application;

FIG. 3 is a flowchart illustrating an implementation of S203 in FIG. 2;

FIG. 4 is a flowchart illustrating an implementation of S204 in FIG. 2;

FIG. 5 is a schematic structural diagram of an intelligent inquiry apparatus provided in an embodiment of the present application;

fig. 6 is a schematic block diagram of a structure of an intelligent inquiry apparatus provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

The embodiment of the application provides an intelligent inquiry method, an intelligent inquiry device, intelligent inquiry equipment and a storage medium. The intelligent inquiry method provided by the embodiment of the application comprises the steps of firstly, obtaining face information and sound information of a user, determining the identity information of the user based on the face information, and obtaining historical diagnosis information of the user according to the identity information of the user; then generating prompt information for instructing a user to input physical symptoms according to the historical diagnosis information; and finally, receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user. The medical treatment process of the user can be reduced, meanwhile, the physical condition of the user can be comprehensively diagnosed, and reasonable medical treatment guide information can be provided.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.

Referring to fig. 1, fig. 1 is a schematic view of an application scenario of the intelligent inquiry method according to the embodiment of the present application. In the present embodiment, the intelligent inquiry method is applied to the robot 102. Specifically, assuming that the user 101 wants to know the health condition of the user through the robot 102 and wants to obtain effective medical guidance information, the robot 102 first needs to acquire face information and sound information of the user 101, then discriminates the id information of the user 101 according to the acquired face information, further acquires historical diagnosis information of the user 101 according to the id information, further generates prompt information for instructing the user to input physical symptoms according to the acquired historical diagnosis information, and analyzes the physical symptom information input by the user and the acquired sound information according to a preset AI disease diagnosis model to obtain and display the physical diagnosis result and the medical guidance information of the user 101.

The robot 102 is an intelligent machine capable of working autonomously, has basic features such as perception, decision, execution and the like, can assist or even replace human beings to complete some complex and heavy works, executes various tasks mainly through programmable actions, and has a programming capability. In this embodiment, the robot 102 structurally includes a head and a support, and a camera device and a voice collecting device are disposed on the head (both the camera device and the voice collecting device are not shown in the figure), the camera device is used for acquiring face information of a user, and the voice collecting device is used for collecting voice information; a processor with programming capability is arranged inside the robot 102, and is used for determining the identity information of the user based on the face information and acquiring the historical diagnosis information of the user according to the identity information. It should be noted that the structure of the robot 102 is not limited in any way in the present application, and this embodiment is only an exemplary representation.

In addition, the embodiment does not specifically limit the camera device and the voice capturing device. Optionally, the historical diagnosis information of the user may be pre-associated with the identification information of the user and stored in the robot 102, specifically, a storage space may be provided in the robot 102, the historical diagnosis information of the user and the identification information of the user may also be pre-associated with each other and stored in the cloud, and the robot 102 may obtain the historical diagnosis information of the user from the cloud.

In addition, the robot 102 is also provided with a display 1021, for example, the display 1021 is arranged at the head of the robot 102 and is used for displaying the prompt information generated according to the historical diagnosis information; an input window 1022 is further disposed corresponding to the display 1021 for a user to input a physical symptom, wherein a relative position between the display 1021 and the input window 1022 is not limited herein. Optionally, the input window 1022 may also be provided with a drop-down menu or selection item for the user to select the physical symptom information.

In particular, the operation of the robot 102 may be as described below with respect to various embodiments of the intelligent interrogation method.

Referring to fig. 2, fig. 2 is a schematic flow chart of an intelligent inquiry method according to an embodiment of the present application. The intelligent inquiry method can be executed by an intelligent inquiry device, the intelligent inquiry device can be a server or a terminal, and the server can be a single server or a server cluster. The terminal can be a handheld terminal, a notebook computer, a wearable device or a robot and the like.

As shown in fig. 2, fig. 2 is a flowchart of an implementation of the intelligent inquiry method according to an embodiment of the present application.

The method specifically comprises the following steps: step S201 to step S204. The details are as follows:

s201, acquiring face information and voice information of a user.

In the embodiment of the application, the face information of the user comprises a face image of the user acquired through the camera device, and the sound information comprises an audio signal which is acquired through the sound acquisition device and is emitted by the user within a preset time. Specifically, camera equipment and sound collection equipment all set up on intelligent inquiry equipment, and this application embodiment does not do any restriction to camera equipment and sound collection equipment, can be any camera equipment and sound collection equipment that have now.

S202, determining the identity information of the user based on the face information, and acquiring historical diagnosis information of the user according to the identity information.

Optionally, the face information is recognized according to a preset face recognition model, a target object matched with the face information is obtained, and the identity information of the target object is obtained, where the identity information of the target object is the identity information of the user. The preset face recognition model is not specifically limited in this embodiment, and may be an existing face recognition model such as a deep learning network model and a neural network model.

In addition, in the embodiment of the application, the face information may be analyzed by using a geometric feature comparison algorithm or a template comparison algorithm to determine the identification information of the user.

The identity identification information of the user comprises information which can uniquely identify the identity of the user, such as a name, a telephone number, an identity card number or a driving license number.

Illustratively, the obtaining the historical diagnosis information of the user according to the identification information includes: and determining historical diagnosis information which is stored in association with the identity identification information by taking the identity identification information as an association field, wherein the historical diagnosis information which is stored in association with the identity identification information is the historical diagnosis information of the user.

It should be noted that, in the embodiment of the present application, the identification information of the user and the historical diagnosis information may be stored in the intelligent inquiry apparatus in an associated manner, or may be stored in the cloud in an associated manner.

And S203, generating prompt information according to the historical diagnosis information, wherein the prompt information is used for indicating a user to input physical symptoms.

The historical diagnostic information may include, among other things: medical records, diagnostic result information, diagnostic reference data, and user portrait information of the user over a specified period of time. Specifically, the user portrait information is user characteristic information, such as age, sex, height, body type, occupation, and the like, which is determined according to information registered by the user when he visits a doctor, and in this embodiment, the user portrait information is stored in a preset database.

Illustratively, as shown in fig. 3, fig. 3 is a flowchart of a specific implementation of S203 in fig. 2. As can be seen from fig. 3, in the present embodiment, S203 includes S2031 to S2033. The details are as follows:

s2031, preprocessing the historical diagnosis information to obtain characteristic variables.

In particular, the feature variables are variables composed of features associated with the user's physical state data. For example, the user body state data is that blood glucose data is higher than a normal index value, the feature associated with the blood glucose data being higher than the normal index value is diabetes, and if the user body state data is that body weight is higher than the normal index value, the feature associated with the body weight being higher than the normal index value is obesity; illustratively, in this embodiment, the preprocessing the historical diagnostic information to obtain a feature variable includes: extracting target diagnosis information with the occurrence frequency larger than a preset frequency from the historical diagnosis information, and acquiring user body state data associated with the target diagnosis information; determining characteristics associated with the acquired physical state data of the user, and forming the characteristic variables.

And S2032, calculating the characteristic variables by using a preset judgment rule to obtain a calculation result.

The calculating the characteristic variables by using a preset judgment rule to obtain a calculation result includes: judging the characteristic variables by using a pre-trained decision tree model to obtain the probability of each preset disease associated with the body state data of the user; wherein the probability of each preset disease associated with the user body state data is the calculated result.

Specifically, the decision tree model trained in advance comprises a strategy layer, a decision layer and results, the strategy layer, the decision layer and the results form a tree diagram, the tree diagram is used for carrying out sequence decision on the characteristic variables, and the probability of each preset disease associated with the body state data of the user is obtained by taking the maximum expectation of the characteristic variables as a decision criterion.

S2033, obtaining prompt information according to the calculation result, wherein the prompt information is used for indicating a user to input physical symptoms.

Specifically, according to the probability of each preset disease associated with the user body state data, the disease category corresponding to the maximum probability value is obtained, after the basic category corresponding to the maximum probability value is determined, the user body symptom associated with the disease category is determined, and the prompt information is generated. For example, according to the probability of each preset disease associated with the body state data of the user, if the disease type corresponding to the maximum probability value is determined to be stomach illness, the body symptoms of the user associated with the stomach illness are determined, and the method comprises the following steps: meal amount, meal frequency, food type, physical symptoms caused by the correspondence of each food type, and the like.

And S204, receiving the physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying the physical diagnosis result and the hospitalizing guidance information of the user.

The preset AI disease diagnosis model is an AI traditional Chinese medicine diagnosis model which comprises a data processing network layer, a neural network layer, a training network layer and a detection network layer.

Illustratively, as shown in fig. 4, fig. 4 is a flowchart of a specific implementation of S204 in fig. 2. As shown in fig. 4, in the present embodiment, S204 includes S2041 to S2044, which are detailed as follows:

s2041, inputting the physical symptom information and the sound information into the AI traditional Chinese medicine diagnosis model, performing data expansion processing on the physical symptom information through the data processing network layer, and randomly dividing the expanded data into a training sample set and a testing sample set.

Specifically, the data processing network layer expands the physical symptom information to obtain physical symptom information similar to the physical symptom information; specifically, the physical symptom information includes at least one of tongue information (such as tongue coating, thickness, color, and the like), blood pressure data, body temperature data, daily eating habit data, heart rate data, weight value, and the like. For example, if the physical symptom information includes a weight value of 50KG, the data network layer obtains a plurality of weight values that fluctuate around the weight value, and obtains a plurality of expanded weight values.

S2042, the AI traditional Chinese medicine diagnosis model is built based on the training sample set and the neural network layer, and the AI traditional Chinese medicine diagnosis model is trained based on the training sample set and the sound information through the training network layer.

In the implementation, the voice information of the user is added into the training sample, so that the AI model can diagnose the sound-related basic according to the voice information of the user and improve the diagnosis accuracy.

Specifically, diseases that may be caused by the change in sound include throat tumors, laryngitis, lung diseases, vocal cord diseases, and the like, and these diseases associated with the change in sound are often difficult to accurately diagnose from general physical symptom data.

Illustratively, training the AI chinese medical diagnostic model based on the training sample set and the sound information by the training network layer includes: training a main network of the AI traditional Chinese medicine diagnosis model based on the training sample set, obtaining a first prediction result of a first classification output function (also called an expected failure function), and determining whether the first prediction result of the first classification output function is the same as a preset disease; and if the first prediction result is the same as the preset disease, retraining the main network of the AI traditional Chinese medicine diagnosis model based on the sound data, and monitoring a second prediction result of a second classification output function (also called an expected sufficient function) until the second prediction result is the same as the preset disease.

The main network of the AI diagnostic model is a Bayesian network, which can simulate the relationship among hundreds of diseases, risk factors and symptoms. In addition, two classification output functions, a first classification output function and a second classification output function, are connected to the bayesian network. Wherein, the first classification output function is a diagnosis measure against the fact and is called an expected failure function, and the second classification output function is a diagnosis measure against the fact and is called an expected sufficient function. The Bayesian network represents the prediction results between diseases, symptoms and risk factors as binary nodes, either on (representing true) or off (representing false), and outputs the prediction results through the first classification output function and the second classification output function, respectively.

Specifically, the first classification output function may be expressed as:

the second classification output function may be expressed as:

wherein, in the first classification function and the second classification function, E_dis(D, ε): representing a first prediction of a first classification output function, E_suff(D, ε): and representing a second prediction result of the second classification output function, wherein epsilon is fact evidence, S + is evidence-conclusive fact state, S '+ is evidence-conclusive fact state, D represents predicted disease, F represents preset disease, and S' is counter-fact symptom evidence state.

And S2043, verifying the trained AI traditional Chinese medicine diagnosis model based on the test sample set and the sound information through the detection network layer, and obtaining the trained AI traditional Chinese medicine diagnosis model after the verification is passed.

Specifically, the test sample set and the sound information are input into a trained AI traditional Chinese medicine diagnosis model, the test sample set and the sound information are analyzed in the trained AI traditional Chinese medicine diagnosis model, if the probability values of a first prediction result output by the first classification function and a second prediction result output by the second classification function, which are the same as a preset disease, are both greater than a preset probability value, the verification is determined to be passed, otherwise, the verification is not passed. It is understood that, when the verification fails, the AI chinese medical diagnosis model needs to be trained based on the training sample set and the sound information until the verification passes.

And S2044, analyzing the physical symptom information and the sound information by using the trained AI traditional Chinese medicine diagnosis model to obtain and display the physical diagnosis result and the medical guidance information of the user.

Specifically, the trained AI traditional Chinese medicine diagnosis model is used for analyzing the body symptom information and the sound information to obtain a probability value of the preset disease obtained by the user, and a body diagnosis result and hospitalizing guidance information of the user are generated according to the probability value of the preset disease obtained by the user.

Optionally, an aid menu button is correspondingly set on the intelligent inquiry equipment for each disease, and the prompt information is information required for disease diagnosis corresponding to the aid menu button. Specifically, the aid menu key is arranged on a display of the intelligent inquiry equipment.

Optionally, the prompt information may be sent to a voice broadcast terminal, so that the voice broadcast terminal sends a voice prompt according to the prompt information.

Exemplarily, the characteristic variables are calculated by using a preset judgment rule to obtain a calculation result; after obtaining the prompt information according to the calculation result, the method may further include:

acquiring information required by disease diagnosis input by a user based on an AIDE menu; determining service prompt information according to the information required by disease diagnosis and a pre-established disease diagnosis pre-judgment model; and sending the service prompt information to a user image information display end for displaying so as to prompt the user to enter a corresponding service queue.

That is, after the user selects and inputs the information required for disease diagnosis according to the IVR menu, the robot determines the type of the disease diagnosed by the user at this time or the type of the diagnosis channel required to be used according to the information required for disease diagnosis input by the client and the pre-established disease diagnosis pre-judging model (for example, the pre-established disease diagnosis pre-judging model is a probability information matrix model), so as to obtain the service prompt information, and the service prompt information is displayed on the user portrait information display end, so that the service staff and the user can know the disease diagnosis progress of the user in time after seeing the displayed service prompt information.

As can be seen from the above analysis, in the intelligent inquiry method provided in this embodiment, first, by acquiring the face information and the voice information of the user, the identification information of the user is determined based on the face information, and the historical diagnosis information of the user is acquired according to the identification information of the user; then generating prompt information for instructing a user to input physical symptoms according to the historical diagnosis information; and finally, receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user. The medical treatment process of the user can be reduced, meanwhile, the physical condition of the user can be comprehensively diagnosed, and reasonable medical treatment guide information can be provided.

Referring to fig. 5, fig. 5 is a schematic structural diagram of an intelligent inquiry apparatus according to an embodiment of the present application. The intelligent interrogation apparatus 500 is used to perform the steps of the intelligent interrogation method shown in the embodiment of fig. 2. The intelligent interrogation apparatus 500 may be a single server or a cluster of servers, or the intelligent interrogation apparatus 500 may be a terminal, which may be a handheld terminal, a laptop, a wearable device, or a robot, etc.

As shown in fig. 5, the intelligent inquiry apparatus 500 includes:

a first obtaining module 501, configured to obtain face information and sound information of a user;

a second obtaining module 502, configured to determine identity information of the user based on the face information, and obtain historical diagnosis information of the user according to the identity information;

a generating module 503, configured to generate prompt information according to the historical diagnosis information, where the prompt information is used to instruct a user to input a physical symptom;

an obtaining module 504, configured to receive physical symptom information input by the user according to the prompt information, input the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, obtain a physical diagnosis result and medical guidance information of the user, and display the result.

In an embodiment, the second obtaining module 502 is specifically configured to:

and determining historical diagnosis information stored in association with the identity identification information by taking the identity identification information as an association field.

In an embodiment, the generating module 503 includes:

the first obtaining unit is used for preprocessing the historical diagnosis information to obtain a characteristic variable;

the second obtaining unit is used for calculating the characteristic variables by using a preset judgment rule to obtain a calculation result;

and the third obtaining unit is used for obtaining prompt information according to the calculation result, wherein the prompt information is used for indicating the user to input physical symptoms.

In one embodiment, the first obtaining unit includes:

the acquisition subunit is used for extracting target diagnosis information with the occurrence frequency greater than the preset frequency from the historical diagnosis information and acquiring user body state data associated with the target diagnosis information;

and the forming subunit is used for determining the characteristics associated with the acquired physical state data of the user and forming the characteristic variables.

In an embodiment, the second obtaining unit is specifically configured to:

judging the characteristic variables by using a pre-trained decision tree model to obtain the probability of each preset disease associated with the body state data of the user; wherein the probability of each preset disease associated with the user body state data is the calculated result.

In one embodiment, the preset AI disease diagnosis model is an AI traditional Chinese medicine diagnosis model, and the AI traditional Chinese medicine diagnosis model comprises a data processing network layer, a neural network layer, a training network layer and a detection network layer;

a deriving module 504, comprising:

the processing unit is used for inputting the physical symptom information and the sound information into the AI traditional Chinese medicine diagnosis model, respectively performing data expansion processing on the physical symptom information and the sound information through the data processing network layer, and randomly dividing the expanded data into a training sample set and a testing sample set;

the training unit is used for building the AI traditional Chinese medicine diagnosis model based on the training sample set and the neural network layer and training the AI traditional Chinese medicine diagnosis model based on the training sample set through the training network layer;

the verification unit is used for verifying the trained AI traditional Chinese medicine diagnosis model based on a test sample set through the detection network layer, and obtaining the trained AI traditional Chinese medicine diagnosis model after the verification is passed;

and the fourth obtaining unit is used for analyzing the physical symptom information and the sound information by using the trained AI traditional Chinese medicine diagnosis model to obtain and display the physical diagnosis result and the medical guidance information of the user.

In one embodiment, a training unit comprises:

the acquisition subunit is used for training a main network of the AI traditional Chinese medicine diagnosis model based on the training sample set, acquiring a first prediction result of a first classification output function and determining whether the first prediction result of the first classification output function is the same as a preset disease;

and the detection subunit is used for retraining the main network of the AI traditional Chinese medicine diagnosis model based on the sound data if the first prediction result is the same as the preset disease, and monitoring a second prediction result of a second classification output function until the second prediction result is the same as the preset disease.

It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the intelligent inquiry apparatus and the modules described above may refer to the corresponding processes in the embodiment of the intelligent inquiry method described in the embodiment of fig. 2, and are not described herein again.

The intelligent interrogation method described above may be implemented in the form of a computer program which may be run on an apparatus as shown in figure 5.

Referring to fig. 6, fig. 6 is a schematic block diagram of a structure of an intelligent inquiry apparatus according to an embodiment of the present application. The intelligent interrogation apparatus 600 includes a processor, a memory and a network interface connected by a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the intelligent methods of interrogation.

The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.

The internal memory provides an environment for the execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any of the methods for intelligent interrogation.

The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the configuration shown in FIG. 6 is a block diagram of only a portion of the configuration associated with the subject application and does not constitute a limitation on the terminal to which the subject application is applied, and that a particular intelligent interrogation apparatus 600 may include more or less components than shown, or combine certain components, or have a different arrangement of components.

It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:

acquiring face information and sound information of a user;

determining the identity identification information of the user based on the face information, and acquiring historical diagnosis information of the user according to the identity identification information;

generating prompt information according to the historical diagnosis information, wherein the prompt information is used for indicating a user to input physical symptoms;

and receiving physical symptom information input by the user according to the prompt information, inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis, and obtaining and displaying a physical diagnosis result and hospitalizing guidance information of the user.

In an embodiment, the obtaining historical diagnostic information of the user according to the identification information includes:

and determining historical diagnosis information stored in association with the identity identification information by taking the identity identification information as an association field.

In an embodiment, the generating a prompt message according to the historical diagnosis information includes:

preprocessing the historical diagnosis information to obtain a characteristic variable;

calculating the characteristic variables by using a preset judgment rule to obtain a calculation result;

and obtaining prompt information according to the calculation result, wherein the prompt information is used for indicating the user to input physical symptoms.

In an embodiment, the preprocessing the historical diagnosis information to obtain the characteristic variable includes:

extracting target diagnosis information with the occurrence frequency larger than a preset frequency from the historical diagnosis information, and acquiring user body state data associated with the target diagnosis information;

determining characteristics associated with the acquired physical state data of the user, and forming the characteristic variables.

In an embodiment, the calculating the characteristic variable by using a preset determination rule to obtain a calculation result includes:

judging the characteristic variables by using a pre-trained decision tree model to obtain the probability of each preset disease associated with the body state data of the user; wherein the probability of each preset disease associated with the user body state data is the calculated result.

In one embodiment, the preset AI disease diagnosis model is an AI traditional Chinese medicine diagnosis model, and the AI traditional Chinese medicine diagnosis model comprises a data processing network layer, a neural network layer, a training network layer and a detection network layer;

the step of inputting the physical symptom information and the sound information into a preset AI disease diagnosis model for analysis to obtain and display the physical diagnosis result and the medical instruction information of the user comprises the following steps:

inputting the physical symptom information and the sound information into the AI traditional Chinese medicine diagnosis model, respectively performing data expansion processing on the physical symptom information and the sound information through the data processing network layer, and randomly dividing the expanded data into a training sample set and a testing sample set;

building the AI traditional Chinese medicine diagnosis model based on the training sample set and the neural network layer, and training the AI traditional Chinese medicine diagnosis model based on the training sample set through the training network layer;

verifying the trained AI traditional Chinese medicine diagnosis model based on a test sample set through the detection network layer, and obtaining the trained AI traditional Chinese medicine diagnosis model after the verification is passed;

and analyzing the physical symptom information and the sound information by using the trained AI traditional Chinese medicine diagnosis model to obtain and display the physical diagnosis result and the medical instruction information of the user.

In an embodiment, the building the AI chinese medical science diagnostic model based on the training sample set and the neural network layer, and training the AI chinese medical science diagnostic model based on the training sample set through the training network layer includes:

training a main network of the AI traditional Chinese medicine diagnosis model based on the training sample set, acquiring a first prediction result of a first classification output function, and determining whether the first prediction result of the first classification output function is the same as a preset disease;

and if the first prediction result is the same as the preset disease, retraining the main network of the AI traditional Chinese medicine diagnosis model based on the sound data, and monitoring a second prediction result of a second classification output function until the second prediction result is the same as the preset disease.

In an embodiment of the present application, a computer-readable storage medium is further provided, where a computer program is stored in the computer-readable storage medium, where the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the intelligent inquiry method provided in the embodiment of fig. 1 in the present application.

The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.

While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.