CN111354452A

CN111354452A - Diagnosis guide method, system, electronic device and computer readable storage medium

Info

Publication number: CN111354452A
Application number: CN202010167947.7A
Authority: CN
Inventors: 李良斌; 陈孝良; 王晶儒
Original assignee: Beijing SoundAI Technology Co Ltd
Current assignee: Beijing SoundAI Technology Co Ltd
Priority date: 2020-03-11
Filing date: 2020-03-11
Publication date: 2020-06-30

Abstract

The embodiment of the disclosure discloses a diagnosis guiding method, a diagnosis guiding system, electronic equipment and a computer readable storage medium. The diagnosis guiding method comprises the following steps: responding to the received diagnosis guide triggering information, and acquiring information of a diagnosis seeking user; selecting an interactive model according to the information of the diagnosis user; sending a second voice signal to the diagnosis user through the interactive model; analyzing a third voice signal sent by the diagnosis user through the interactive model; and responding to the received ending signal, and generating the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal. Through the interactive model in the method, the information of the patient is acquired through voice before the patient is subjected to outpatient examination to generate the referral information, so that the technical problem that the information of the patient is not comprehensively acquired in the prior art is solved.

Description

Diagnosis guide method, system, electronic device and computer readable storage medium

Technical Field

The present disclosure relates to the field of intelligent dialogues, and in particular, to a method, a system, an electronic device, and a computer-readable storage medium for guiding a medical doctor.

Background

With the increasingly fierce market in the medical field, the quality of life of people is continuously improved, and the requirements of the public on the medical quality, the medical environment, the medical time and the efficiency are higher and higher.

In the prior art, because the medical knowledge of a patient is limited, the patient is difficult to accurately judge the department to be registered, so that the problems of wrong department selection and the like often occur in appointment registration, which brings great inconvenience to the patient; in addition, after the patient finishes hanging the number, the patient directly faces the doctor to make a diagnosis, and because the diagnosis time of the doctor is limited and the patient is tense, the patient often forgets to say some diseases, forgets to ask about matters to be noticed and the like. This may lead to inaccurate diagnosis due to incomplete information, and then re-registration is required, which wastes time and medical resources. Therefore, how to accurately and comprehensively acquire the information of the patient becomes an urgent problem to be solved.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, an embodiment of the present disclosure provides a method for guiding a doctor, including:

responding to the received diagnosis guide triggering information, and acquiring information of a diagnosis seeking user;

selecting an interactive model according to the information of the diagnosis user;

sending a second voice signal to the diagnosis user through the interactive model;

analyzing a third voice signal sent by the diagnosis user through the interactive model;

and responding to the received ending signal, and generating the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal.

Further, the method further comprises:

and storing the diagnosis guide information into a server.

Further, the method further comprises:

acquiring a fourth voice signal of the doctor user;

responding to the fourth voice signal of the doctor user and the information of the diagnosis seeking user, and acquiring the diagnosis guide information of the diagnosis seeking user;

selecting a case generation model according to the information of the diagnosis seeking user and the diagnosis guide information;

acquiring a fifth voice signal of a doctor user and a sixth voice signal of the diagnosis user;

and generating a case document of the diagnosis user according to the fifth voice signal and the sixth voice signal through the case generation model.

Further, the obtaining information of the user seeking diagnosis in response to receiving the diagnosis guide triggering information includes:

acquiring a first voice signal of a user seeking diagnosis;

and acquiring the information of the diagnosis user in response to the detection that the first voice signal comprises the target voice.

Further, the generating, in response to receiving an end signal, the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal includes:

in response to receiving an end signal, generating a memo interface to prompt the consulting user to input a seventh voice signal;

and responding to a seventh voice signal input by the diagnosis user, and generating the diagnosis guide information of the diagnosis user according to the second voice signal, the third voice signal and the seventh voice signal.

Further, the obtaining information of the diagnosis user in response to detecting that the first voice signal includes the target voice includes:

in response to the fact that the first voice signal comprises a preset awakening word, verifying identity information of the diagnosis user;

and responding to the verification that the identity information of the diagnosis user passes, and acquiring the registration information of the diagnosis user.

Further, the selecting an interaction model according to the information of the diagnosis user includes:

and acquiring a corresponding interaction model according to department information in the registration information of the diagnosis user, wherein the interaction model is used for generating inquiry information corresponding to the department and analyzing a voice signal of the diagnosis user.

Further, the sending a second voice signal to the diagnosis user through the interactive model includes:

the interactive model generates inquiry information according to the information of the diagnosis user;

synthesizing a second voice signal according to the inquiry information;

and sending the second voice signal to the diagnosis user.

in response to receiving an end signal, generating a referral text according to the query information and the semantics of the third voice signal;

and generating the diagnosis guide information of the diagnosis seeking user according to the diagnosis guide text.

Further, the storing the information of the medical guide to a server includes:

and storing the diagnosis guide information into the server according to the information of the diagnosis seeking user and the generation time of the diagnosis guide information, wherein the diagnosis guide information is stored in the sequence of the generation time.

Further, the obtaining of the diagnosis guide information of the diagnosis seeking user in response to the fourth voice signal of the doctor user including the information of the diagnosis seeking user includes:

responding to the fourth voice of the doctor user and including the registration information of the diagnosis seeking user, and acquiring the diagnosis guide information of the diagnosis seeking user from the server according to the registration information.

Further, the selecting a case generation model according to the information of the diagnosis user and the diagnosis guide information includes:

and selecting a corresponding case generation model according to the registration information of the diagnosis seeking user and the disease information in the diagnosis guide information, wherein the case generation model comprises a semantic analysis model corresponding to the registration information and the disease information.

Further, the generating, by the case generation model, a case document of the diagnosis user according to the fifth speech signal and the sixth speech signal includes:

parsing semantics in the fifth and sixth speech signals through the case generation model;

and filling the preset items of the case document according to the semantics to obtain the case document of the diagnosis user.

In a second aspect, an embodiment of the present disclosure provides a diagnosis guide system, including:

the system comprises a first voice acquisition device, a user information acquisition device and an interaction device;

the first voice acquisition device is used for acquiring a first voice signal of a diagnosis user;

the user information acquisition device is used for acquiring the information of the user seeking a diagnosis;

the interaction means is for:

sending a second voice signal to the diagnosis user through the interactive model; analyzing a third voice signal sent by the diagnosis user through the interactive model;

In a third aspect, an embodiment of the present disclosure provides a diagnosis guiding device, including:

the system comprises a consultation user information acquisition module, a consultation user information acquisition module and a consultation prompting module, wherein the consultation user information acquisition module is used for responding to received consultation guiding triggering information and acquiring information of a consultation user;

the interactive model selection module is used for selecting an interactive model according to the information of the diagnosis user;

the second voice signal sending module is used for sending a second voice signal to the diagnosis user through the interactive model;

the third voice signal analysis module is used for analyzing a third voice signal sent by the diagnosis user through the interactive model;

and the diagnosis guide information generation module is used for responding to a received ending signal and generating the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal.

In a fourth aspect, an embodiment of the present disclosure provides 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 any of the method of the first aspect.

In a fifth aspect, the disclosed embodiments provide a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing a computer to execute the method for guiding a patient according to any one of the foregoing first aspects.

The foregoing is a summary of the present disclosure, and for the purposes of promoting a clear understanding of the technical means of the present disclosure, the present disclosure may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 is a schematic view of an application scenario of an embodiment of the present disclosure;

fig. 2 is a schematic flow chart of a method for guiding a patient according to an embodiment of the present disclosure;

fig. 3 is a schematic further flowchart illustrating step S202 of the method for guiding a patient according to the present disclosure;

fig. 4 is a schematic further flowchart of step S206 of the diagnosis guiding method according to the embodiment of the disclosure

FIG. 5 is a schematic flow chart of a method for guiding a patient according to an embodiment of the present disclosure;

FIG. 6 is a schematic view of a diagnostic guidance system provided by an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an embodiment of a diagnostic guide apparatus provided in an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an electronic device provided according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

Fig. 1 is a schematic view of an application scenario of the embodiment of the present disclosure. As shown in fig. 1, the voice sent by the user 101 is received by a terminal device 103, typically, the terminal device 103 is an intelligent terminal in various forms, the terminal device 103 is connected with a voice recognition device 105 through a network 104, wherein the voice recognition device 105 may be a computer or an intelligent terminal or the like; the network 104 on which the terminal device 103 communicates with the voice recognition device 105 may be a wireless network, such as a 5G network and a wifi network, or may be a wired network, such as an optical fiber network. In the application scenario, the user 101 makes a dialogue with the terminal device 103, the terminal device 103 collects voice and sends the voice to the voice recognition device 105, and the semantic meaning of the recognized voice is recorded; when the doctor user 102 communicates with the consulting user 101, the semantic text recorded by the terminal device 103 can be called, and the terminal device 106 can record the real-time conversation between the doctor user 102 and the consulting user 101, and generate a case or a diagnosis book.

It is understood that the speech recognition device 105 may be disposed with the terminal device 103 and the terminal device 106, that is, the terminal device 103 and the terminal device 106 may integrate speech recognition functions, so that the speech input of the user can be directly recognized in the terminal device 103 or the terminal device 106.

Fig. 2 is a flowchart of an embodiment of a method for guiding a doctor provided by an embodiment of the present disclosure, where the method for guiding a doctor provided by this embodiment may be executed by a diagnosis guiding apparatus, the diagnosis guiding apparatus may be implemented as software, or implemented as a combination of software and hardware, and the diagnosis guiding apparatus may be integrated in a certain device in a diagnosis guiding system, such as a diagnosis guiding server or a diagnosis guiding terminal device. As shown in fig. 2, the method comprises the steps of:

step S201, responding to the received diagnosis guide triggering information, and acquiring the information of the diagnosis seeking user;

the diagnosis guide triggering information is triggering information generated by a diagnosis seeking user through various triggering modes. For example, the diagnosis user may insert a smart card into the terminal device by using the smart card insertion card to generate the diagnosis guide trigger message, or the diagnosis user may click on a touch screen of the terminal device by using a finger to generate the diagnosis guide trigger message, or the diagnosis user may trigger the diagnosis guide trigger message by using voice wakeup or face recognition, etc.

The following description will take the example of generating the diagnosis guide trigger message by voice wakeup as an example, and it can be understood that other suitable triggering manners may be introduced into the present disclosure, and the present disclosure does not limit this.

Optionally, the step S201 includes:

acquiring a first voice signal of a user seeking diagnosis;

In this step, the terminal device 103 acquires, through a voice acquisition device, a first voice signal sent by a diagnosis seeking user, and in an exemplary application scenario, the first voice signal is a trigger voice signal sent when the user is near the terminal device 103, and is used for triggering the terminal device 103 to guide the user.

Illustratively, the first voice signal is a voice signal of which the distance between the sound source and the terminal device 103 is smaller than a first distance threshold. In this embodiment, the voice signal collected by the terminal device 103 is further recognized only after the distance between the user and the terminal device 103 is less than the predetermined distance.

After receiving the first voice signal, recognizing the voice signal through a voice recognition technology. Illustratively, the speech signal is encoded and decoded by a speech recognition model, and then a text corresponding to the speech signal is output. Typically, the encoding process is a process of extracting features of the speech signal, which may extract features of the speech signal, and typical speech signal features may be mel-frequency cepstrum coefficients and the like; typically, the decoding process is a process of decoding the encoded data and outputting a text by using an acoustic model and a language model, wherein the acoustic model is used for recognizing the speech in the speech signal feature, and the language model is used for recognizing the language of the speech so as to recognize the text corresponding to the semantic output of the speech.

And triggering the subsequent diagnosis guiding step when the first voice signal is recognized to comprise the target voice.

Illustratively, the obtaining information of the diagnosing user in response to detecting that the first voice signal includes the target voice comprises:

step S301, in response to the fact that the first voice signal is detected to include a preset awakening word, verifying identity information of the diagnosis seeking user;

step S302, responding to the identity information of the diagnosis user passing verification, and acquiring registration information of the diagnosis user.

In step S301, a target voice, i.e., a wakeup word, in the first voice signal is first detected. For example, the awakening word may be "seeing a doctor", for example, when the user seeking to diagnose says "i want to see a doctor" or "i want to see a doctor", it is recognized that "seeing a doctor" is included in the voice of the user seeking to diagnose, at this time, an identity verification step is further started to verify the identity of the user seeking to diagnose; the identity information of the diagnosis seeking user can be identity information of the diagnosis seeking user, such as voiceprint information, facial features or fingerprint information, and typically, the user needs to register own identity information in the diagnosis guide system in advance, and in the step, if the identity information of the diagnosis seeking user does not exist in the system, the user is reminded to register the identity information.

In step S302, if the identity information of the diagnosis user passes the verification, registration information of the diagnosis user is acquired. The registration information is used for hanging departments, doctors and queuing numbers in advance. In one embodiment, the registration information of the user for diagnosis may not be obtained in the step, and at this time, the user is not registered in advance, and at this time, the user may be reminded to register first, and the user may use the diagnosis guide system after obtaining the registration information through registration of other channels. Or in this step, when the user seeking for a diagnosis does not have registration information, in order to obtain the registration information of the user, a registration step can be further provided for the user seeking for a diagnosis, at this time, a registration model can be selected to prompt the user to describe own symptoms by voice, the registration model automatically selects a proper department and a doctor to register the user by recognizing the voice of the user, if the user seeking for a diagnosis says that the user has a bit cough and chest distress, the registration model recognizes the cough and the chest distress in the department, recommends the user to register the number of the respiratory department, and after the user seeking for a diagnosis confirms, the registration information of the user is obtained as the respiratory department.

For example, the information of the diagnosis user may further include body state information of the diagnosis user, and in this case, the diagnosis guidance system may include an infrared heat detection device, a blood pressure measurement device, a weight scale, or other body state measurement devices, and if the first voice signal of the user includes the target voice, the body state information of the user is collected through the body state measurement devices.

Step S202, selecting an interaction model according to the information of the diagnosis user;

because a plurality of departments exist in the hospital and the diseases of each department are different, a plurality of different interactive models can be set according to the linguistic data corresponding to the different diseases of each department, and the language model of each interactive model is trained by the linguistic data of the corresponding department, so that the subsequent recognition of the voice of the user seeking diagnosis can be more accurate.

Illustratively, the step S202 includes:

Illustratively, the interaction model is invoked by a dialog engine for managing a dialog of the consulting user with the referral system. After the interaction model is selected, the dialogue engine generates dialogue with the diagnosis user according to the interaction model, and can generate different inquiry information according to different departments so as to inquire the disease of the diagnosis user, and analyze the voice information responded by the diagnosis user so as to analyze the confirmation information or the disease information in the voice information.

Step S203, sending a second voice signal to the diagnosis user through the interactive model;

exemplarily, the step S203 includes:

synthesizing a second voice signal according to the inquiry information;

and sending the second voice signal to the diagnosis user.

The query information may be a preset fixed question, such as: "you are not comfortable", the query message is general information, and any interaction model can start a conversation with the query message; or "whether you cough", "whether you feel oppressed feeling in chest", "whether you are headache", and the like, when the preset fixed question is related to the department corresponding to the interactive model. Alternatively, the query message may be a query message generated according to the voice of the user seeking diagnosis, identity information, and the like, for example, the user has previously said "i have a cough", the query message may be a question related to a cough symptom, such as "whether you are running a nose or not", and the query message may include "whether you are high in blood pressure" or not, for example, if the age of the user seeking diagnosis is shown in the identity information to be older. It is understood that the query message may be generated according to any information of the user seeking a diagnosis, and will not be described herein.

For example, the query information is text information, and the text information needs to be fed back to the user for diagnosis after being generated, the query information may be synthesized into a second voice signal through a voice synthesis technology, and then sent to the user for diagnosis through an audio playing device, such as a sound box.

It will be appreciated that the second speech signal may also be narrative information, which is answered in accordance with a query in the user's speech information.

Step S204, analyzing a third voice signal sent by the diagnosis user through the interactive model;

after hearing the second voice signal, the diagnosing user answers to the question in the second voice signal, and the answered voice is the third voice signal.

Illustratively, the step S204 includes:

acquiring a third voice signal of the user seeking to diagnose;

and recognizing the semantics of the third voice signal through the interaction model.

The sentences in the third speech signal differ according to the sentences in the second speech signal, which is illustratively a query sentence, such as "what feeling you feel? "," how long did you cough? "the sentence pattern needs to be answered by the next consulting user with a statement sentence, and the interaction model needs to identify the entity content in the third speech signal; the sentence in the second speech signal may also be a confirmation sentence, such as "you cough for do", which does not require the statement in the user's sentence next, but only needs to identify the confirmation word therein, such as "yes", "no", etc., whose content "cough" is in the second speech signal. The second voice signal may also be an answer to a third voice signal, for example, the diagnosing user may send a query "how much i need to pay attention to" in the third voice signal, and the interaction module may generate order information for the disease information according to the previously received disease information and send the order information to the diagnosing user in the form of the second voice signal.

It is understood that the second speech signal of step S203 and the third speech signal of step S204 may comprise a plurality of sentences to form a dialog of the consulting user with the consultation system, in which case the steps S203 and S204 are executed in a loop until the dialog is finished.

Step S205, in response to receiving the end signal, generating the diagnosis guiding information of the diagnosis seeking user according to the second voice signal and the third voice signal.

The ending signal can be ending voice sent by the user seeking to diagnose, wherein the ending voice comprises a wakeup word of an ending command; or the end signal may be an end signal sent by the diagnosing user touching an end button or the like, at this time, the dialogue engine ends the dialogue between the diagnosing user and the diagnosis guidance system, and generates the diagnosis guidance information of the diagnosing user according to the semantics of the second voice signal and the semantics of the third voice signal.

Exemplarily, the step S205 includes:

step S401, responding to the received ending signal, and generating a diagnosis guiding text according to the query information and the semantics of the third voice signal;

and step S402, generating the diagnosis guide information of the diagnosis seeking user according to the diagnosis guide text.

In this exemplary embodiment, the second speech corresponds to query information, the query information corresponds to query text, the semantics of the third speech signal are also converted into corresponding text, and a guide text is generated according to a dialog text formed by the query text and the semantics of the third speech, and the guide text can be the dialog text directly or a text for organizing the content of the entity, such as a text which includes: symptoms, duration, notes, etc.

In step S402, the referral information is generated according to the referral text, and the referral information may be a formatted text with a certain format, and the required information in the referral information is extracted from the referral text to generate the referral information. In this embodiment, for example, after the diagnosis guide text is generated, the diagnosis guide text is displayed to the diagnosis seeking user through a display device, the diagnosis seeking user confirms whether the diagnosis guide text has an error or missing information, and if the diagnosis guide text has an error or missing information, the diagnosis guide text is modified, where the modification may be performed through various human-computer interaction devices, for example, a user directly modifies the text through a text input device, or modifies the text through a voice input device, and so on, which is not described herein again. And after the user confirms the diagnosis guide text, generating diagnosis guide information according to the diagnosis guide text.

Exemplarily, the step S205 includes:

In this exemplary embodiment, upon receiving an end signal, a memo interface is further generated for display to the referring user so that the referring user may input some information other than the question asked by the second voice signal. For example, for the disease of a department, the questions presented by the interactive model may all surround a certain disease, but the user may have other diseases or want to ask a doctor, and the collected information does not include the information, so after receiving the end signal, a memo interface is provided to allow the user to input some memo information, when the memo interface is generated, the user is prompted to input any information desired to be input by voice, and if a seventh voice signal of the user is received, the seventh voice signal is also used as a part of the generated guide information, and the guide information of the user is generated together with the second voice signal and the third voice signal. Similarly, the second voice signal, the third voice signal and the seventh voice signal may be converted into a guide text, and the final guide information may be generated according to the guide text, similarly to the above steps.

After the information of the medical consultation is obtained, the interactive module can judge whether the user needs to go further to the outpatient service to make a manual diagnosis through a doctor through the information of the medical consultation, if not, a case and a diagnosis book can be directly generated and sent to the terminal equipment 103, so that the user is prompted to take medicine or rest according to the medical advice in the diagnosis book, and the like.

Optionally, after step S205, the method further includes: and storing the diagnosis guide information into a server. The server is used for storing information of the diagnosis user, including registration information, identity information, physical characteristic information, diagnosis guide information, cases, diagnosis books and the like of the user. In this embodiment, the referral information is saved to a server for subsequent queries. Illustratively, the diagnosis guide information is stored in the server according to the information of the diagnosis user and the generation time of the diagnosis guide information, wherein the diagnosis guide information is stored in the sequence of the generation time. Typically, the information of the consulting user includes registration information and the like, and the consultation guide information is stored in the registration information of the consulting user on the server in the order of the generation time.

Optionally, in some cases, the diagnosis guide information of the diagnosis seeking user is relatively limited or the diagnosis of the diagnosis seeking user cannot be confirmed directly through the diagnosis guide information, and the user needs to be further guided to an outpatient service to receive further examination of a doctor. The on-line examination can be divided into an on-line examination and an off-line examination, and the on-line examination can be communicated with a clinic doctor through video or audio; offline examination may be accomplished by asking for the user's current location, instructing the user on the way to the clinic, so that the user arrives at the clinic for face-to-face communication with the physician. Whether the inspection is carried out on line or off line, the inspection needs to be communicated with the inspection already carried out.

Optionally, the method for guiding a doctor further comprises:

step S501, acquiring a fourth voice signal of the doctor user;

step S502, responding to the fourth voice signal of the doctor user and including the information of the diagnosis user, and acquiring the diagnosis guide information of the diagnosis user;

step S503, selecting a case generation model according to the information of the diagnosis user and the diagnosis guide information;

step S504, acquiring a fifth voice signal of a doctor user and a sixth voice signal of the diagnosis user;

and step S505, generating a case document of the diagnosis user according to the fifth voice signal and the sixth voice signal through the case generation model.

In step S501, a fourth voice signal of the doctor user 102 is acquired through the terminal device 106, where the fourth voice signal is a diagnosis guide trigger voice signal of the doctor user side, and includes a target voice, where the target voice is information of a diagnosis user.

Optionally, the step S502 further includes: responding to the fourth voice of the doctor user and including the registration information of the diagnosis seeking user, and acquiring the diagnosis guide information of the diagnosis seeking user from the server according to the registration information. If the fourth voice signal of the doctor user includes the information of the doctor seeking user, for example, the registration number of the doctor seeking user, the referral information corresponding to the registration number is obtained, and as described above, the referral information exists in the information of the doctor seeking user according to the generation time sequence, so that the referral information under the registration number at the current date can be obtained according to the registration number and the current date.

Optionally, the step S503 further includes: and selecting a corresponding case generation model according to the registration information of the diagnosis seeking user and the disease information in the diagnosis guide information, wherein the case generation model comprises a semantic analysis model corresponding to the registration information and the disease information. In this step, a corresponding case generation model is selected, which includes a semantic analysis model trained from the department and corpus of corresponding disorders, and which can accurately generate cases and diagnosis books for the current department and disorders.

Optionally, the step S505 further includes: parsing semantics in the fifth and sixth speech signals through the case generation model; and filling the preset items of the case document according to the semantics to obtain the case document of the diagnosis user. The dialogue voice signals of the diagnosis user and the doctor user are collected and converted into dialogue texts through step S504, and then the entity contents identified from the dialogue voices of the diagnosis user and the doctor user are filled into preset items of the case document through step S505 to obtain the case document and/or the diagnosis book of the diagnosis user.

The items in the case document may include: after identifying the semantics, the entity content in the semantics, such as "the severity of my cough", can be extracted, and the entity content is "cough". The semantics are classified into one of the items through a multi-classification model so that the case document can be filled in later, and the case document can be classified into symptoms, for example, cough. In addition, the dialog between the doctor user and the consulting user may not belong to any item, and at this time, another category may be set to correspond to the dialog content not belonging to the item. In step S505, each sentence in the dialog text may be input into a multi-classification model of entity content trained in advance to determine the type of the entity content of each sentence, where the multi-classification model may use any existing model and is not described herein again, and the training data of the model may use synthetic data or real data, which is labeled data for a specific item of the case document.

Optionally, after obtaining the semantic entity content, the entity content may be further converted into corresponding standard entity content, such as "dry cough" may be converted into "cough", "left chest pain" may be converted into "left chest pain", and so on, so that the spoken language may be converted into written language or professional vocabulary, which is more suitable for the requirement of case document.

Further, since the filling of the entity content by the category of the sentence assists in determining, in order to make the filled content more accurate, whether the entity content corresponding to the sentence needs to be added to the corresponding item may be determined using the category of the sentence. Therefore, optionally, the filling the preset items of the case document according to the semantics to obtain the case document of the consulting user further includes: and filling the entity content into corresponding items according to the category of the sentence in which the semantics are positioned and the category of the entity content to generate the case document. The following explains a processing method for each sentence type.

Further, the filling the entity content into the corresponding item according to the category of the sentence in which the semantic is located and the category of the entity content to generate the case document includes: and in response to the statement category being a statement sentence, adding the entity content of the statement sentence to an item in the case document corresponding to the entity content category of the statement sentence. In this step, if the statement is judged to be a statement sentence and the category of the entity content of the statement sentence is X, the entity content of the statement sentence is added to the item corresponding to the category X. Further, it may also be set that each item only allows adding one content, at this time, a flag match may be set for each category, when the category is empty, the match is set to 0, and when the category is added with a content, the match is set to 1. Or, each item allows adding a plurality of contents, at this time, in order to prevent the same content from being repeatedly added, it may be determined whether the content has been added in the category at the time of addition, and if the content has been added, a deduplication operation is performed to determine whether the entity content needs to be added to the item corresponding to the category. For example, "fever" and "cough" have been added to the symptomatic item, and if there is a "diarrhea" that is an entity content of the category, they may be added directly, or if "cough" occurs again, they are not added again after the past heavy operation.

Further, the filling the entity content into the corresponding item according to the category of the sentence in which the semantic is located and the category of the entity content to generate the case document includes: responding to the statement type as an inquiry statement, caching the inquiry statement until the entity content of the statement sentence with the same type as the entity content of the inquiry statement is obtained; and adding the entity content of the statement sentence into an item corresponding to the entity content category of the statement sentence in the case document. In the case that a sentence is a query sentence, since it needs a statement sentence to answer the query, the entity content of the sentence cannot be directly added to the item, and from the characteristic of the dialog, the answer of the query sentence should be followed within a certain range after the query sentence, typically, the next sentence of the query sentence is usually the statement sentence for the answer of the query sentence, at this time, the query sentence is cached to indicate that the entity content related to the query sentence is not yet added, a statement sentence of the same type as the entity content is obtained after knowing the query sentence, and the entity content of the statement sentence is added to the corresponding item as the entity content to be added, and the addition rule of the entity content of the statement sentence is the same as the description of the statement sentence, and is not repeated here.

Further, the filling the entity content into the corresponding item according to the category of the sentence in which the semantic is located and the category of the entity content to generate the case document includes: responding to the sentence type as a confirmation sentence, caching the confirmation sentence until a reply sentence of the confirmation sentence is obtained; in response to the answer sentence being a positive sentence, adding the entity content of the positive sentence to an item in the case document corresponding to the entity content category of the positive sentence; and in response to the answer sentence being a negative sentence and the case document including the entity content of the confirmation sentence, deleting the entity content of the confirmation sentence from the case document. When the sentence type is a confirmation sentence, the entity content is in the confirmation sentence, the confirmation sentence or the entity content of the confirmation sentence can be cached in a state to be confirmed, a reply sentence of the confirmation sentence after waiting is similar to the inquiry sentence, and the reply of the confirmation sentence generally follows the confirmation sentence; if the reply sentence is a positive sentence, adding the entity content of the confirmation sentence into the corresponding item, and adding the entity content according to the same rule as the statement sentence during adding, which is not described herein again; if the answer sentence is a negative sentence, it is first determined whether the corresponding item in the structure language text already includes the same content as the entity content of the confirmation sentence, if so, the entity content in the item is deleted, and further if only one entity content in the item can be filled, the flag bit is further set to 0 at this time.

Through the steps, a case document with preset filling items can be generated through the voice signals, so that a doctor user can be more concentrated on communication of a diagnosis seeking user, and information does not need to be recorded manually.

Further, after generating the case document, the method further includes: displaying the case document; a modification command is received to generate a new case document.

In this embodiment, the text may continue to be modified based on the generated case document. It can be understood that, in the case document generated in the above steps, some entity contents with inaccurate identification and errors added are inevitably generated, and at this time, the generated case document may be displayed on the display device of the terminal device 106, and the user inputs a modification command through the text input device to modify the contents of the case document to generate a new case document. Further, after a new case document is generated, a printing command can be received to print the new case document to form a paper file.

In an exemplary application scenario of the present disclosure, the doctor seeking user performs a medical consultation through the terminal device 103 to generate pre-medical consultation information, and then the doctor seeking user communicates with the doctor user at an outpatient service, at this time, the doctor user invokes the medical consultation information through the voice of the terminal device 106, and then communicates with the doctor seeking user, and the consultation system records a conversation between the doctor seeking user and the doctor user, and generates a case document.

Fig. 6 is a schematic view of a diagnostic system provided in an embodiment of the present disclosure. As shown in fig. 6, the diagnosis guidance system includes: a first voice acquisition device 601, a user information acquisition device 602 and an interaction device 603; the first voice acquisition device is used for acquiring a first voice signal of a diagnosis user; the user information acquisition device is used for acquiring the information of the user seeking a diagnosis; the interaction means is for: selecting an interactive model according to the information of the diagnosis user; sending a second voice signal to the diagnosis user through the interactive model; analyzing a third voice signal sent by the diagnosis user through the interactive model; and responding to the received ending signal, and generating the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal.

Further, the system for guiding a doctor further comprises: and the server 604 is configured to store the referral information of the referring user.

Further, the system for guiding a doctor further comprises: a second voice collecting device 605 and a case generating device 606; the second voice acquisition device is used for acquiring a fourth voice signal of the doctor user; the case generation apparatus is configured to: responding to the fourth voice signal of the doctor user and the information of the diagnosis seeking user, and acquiring the diagnosis guide information of the diagnosis seeking user; selecting a case generation model according to the information of the diagnosis seeking user and the diagnosis guide information; acquiring a fifth voice signal of a doctor user and a sixth voice signal of the diagnosis user; and generating a case document of the diagnosis user according to the fifth voice signal and the sixth voice signal through the case generation model.

The diagnosis guiding system executes the diagnosis guiding method through the first voice collecting device 601, the user information collecting device 602, the interacting device 603, the server 604, the second voice collecting device 605 and the case generating device 606, and reference may be made to the related description of the embodiment shown in fig. 2 to 5 for a part not described in detail in this embodiment. The implementation process and technical effect of the technical solution are described in the embodiments shown in fig. 2 to 5, and are not described herein again.

In the above, although the steps in the above method embodiments are described in the above sequence, it should be clear to those skilled in the art that the steps in the embodiments of the present disclosure are not necessarily performed in the above sequence, and may also be performed in other sequences such as reverse, parallel, and cross, and further, on the basis of the above steps, other steps may also be added by those skilled in the art, and these obvious modifications or equivalents should also be included in the protection scope of the present disclosure, and are not described herein again.

Fig. 7 is a schematic structural diagram of an embodiment of a diagnosis guide apparatus provided in an embodiment of the present disclosure, and as shown in fig. 7, the apparatus 700 includes: the system comprises a consultation user information acquisition module 701, an interactive model selection module 702, a second voice signal sending module 703, a third voice signal analysis module 704 and a consultation guide information generation module 705. Wherein the content of the first and second substances,

the information acquisition module 701 for the user seeking diagnosis is used for responding to the received diagnosis guide triggering information and acquiring the information of the user seeking diagnosis;

an interaction model selection module 702, configured to select an interaction model according to the information of the diagnosis user;

a second voice signal sending module 703, configured to send a second voice signal to the user for diagnosis through the interaction model;

a third voice signal analyzing module 704, configured to analyze, through the interaction model, a third voice signal sent by the user for diagnosis;

and a diagnosis guide information generating module 705, configured to generate, in response to receiving the end signal, diagnosis guide information of the diagnosis-seeking user according to the second voice signal and the third voice signal.

Further, the apparatus 700 further comprises:

and the storage module is used for storing the diagnosis guide information into a server.

Further, the apparatus 700 further comprises:

the fourth voice signal acquisition module is used for acquiring a fourth voice signal of the doctor user;

the diagnosis guide information acquisition module is used for responding to the fourth voice signal of the doctor user and including the information of the diagnosis seeking user, and acquiring the diagnosis guide information of the diagnosis seeking user;

the case generation model selection module is used for selecting a case generation model according to the information of the diagnosis seeking user and the diagnosis guide information;

the clinic voice signal acquisition module is used for acquiring a fifth voice signal of a doctor user and a sixth voice signal of the diagnosis user;

and the case document generation module is used for generating a case document of the diagnosis user according to the fifth voice signal and the sixth voice signal through the case generation model.

Further, the information obtaining module 701 of the user seeking diagnosis is further configured to:

acquiring a first voice signal of a user seeking diagnosis;

Further, the referral information generating module 705 is further configured to:

Further, the interaction model selection module 702 is further configured to:

Further, the second voice signal sending module 703 is further configured to:

synthesizing a second voice signal according to the inquiry information;

and sending the second voice signal to the diagnosis user.

Further, the saving module is further configured to:

Further, the diagnosis guide information obtaining module is further configured to:

Further, the case generation model selection module is further configured to:

Further, the case document generation module is further configured to:

The apparatus shown in fig. 7 can perform the method of the embodiment shown in fig. 2-5, and the detailed description of this embodiment can refer to the related description of the embodiment shown in fig. 2-5. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 2 to fig. 5, and are not described herein again.

Referring now to FIG. 8, shown is a schematic diagram of an electronic device 800 suitable for use in implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 8, an electronic device 800 may include a processing means (e.g., central processing unit, graphics processor, etc.) 801 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data necessary for the operation of the electronic apparatus 800 are also stored. The processing apparatus 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

Generally, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage 808 including, for example, magnetic tape, hard disk, etc.; and a communication device 809. The communication means 809 may allow the electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While fig. 8 illustrates an electronic device 800 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 809, or installed from the storage means 808, or installed from the ROM 802. The computer program, when executed by the processing apparatus 801, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having 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. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: responding to the received diagnosis guide triggering information, and acquiring information of a diagnosis seeking user; selecting an interactive model according to the information of the diagnosis user; sending a second voice signal to the diagnosis user through the interactive model; analyzing a third voice signal sent by the diagnosis user through the interactive model; and responding to the received ending signal, and generating the diagnosis guide information of the diagnosis seeking user according to the second voice signal and the third voice signal.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

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.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A method of medical lead, comprising:

2. The method of guiding a medical procedure of claim 1, wherein the method further comprises:

and storing the diagnosis guide information into a server.

3. The method of any of claims 2, wherein the method further comprises:

acquiring a fourth voice signal of the doctor user;

4. The method of claim 1, wherein said obtaining information of the referring user in response to receiving the referral trigger message comprises:

acquiring a first voice signal of a user seeking diagnosis;

5. The method of claim 1, wherein said generating, in response to receiving an end signal, the referral information of the referring user from the second speech signal and the third speech signal comprises:

6. The method of claim 4, wherein said obtaining information of said consulting user in response to detecting that said first speech signal includes a target speech comprises:

7. The method of referral of claim 6, wherein said selecting an interaction model based on said referral user's information comprises:

8. The method of guiding a medical procedure of claim 1, wherein said transmitting a second speech signal to said medical user through said interactive model comprises:

synthesizing a second voice signal according to the inquiry information;

and sending the second voice signal to the diagnosis user.

9. The method of claim 8, wherein said generating, in response to receiving an end signal, the referral information of the referring user from the second speech signal and the third speech signal comprises:

10. The method of referral of claim 2, wherein said storing the referral information into a server comprises:

11. The method of claim 3, wherein the obtaining the referral information of the referring user in response to the fourth voice signal of the physician user including the information of the referring user comprises:

12. The referral method of claim 3, wherein the selecting a case generation model based on the referrer user's information and the referral information comprises:

13. The referral method of claim 3, wherein the generating of the case document of the referring user from the fifth and sixth speech signals by the case generation model comprises:

14. A referral system, comprising:

the interaction means is for:

15. A diagnostic device, comprising:

16. An electronic device, comprising:

a memory for storing computer readable instructions; and

a processor for executing the computer readable instructions such that the processor when executed implements the method of referral according to any one of claims 1-13.

17. A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a computer, cause the computer to perform the method of conducting a medical procedure of any one of claims 1-13.