CN115083602A - Mental disease auxiliary diagnosis method, device, equipment, storage medium and system - Google Patents
Mental disease auxiliary diagnosis method, device, equipment, storage medium and system Download PDFInfo
- Publication number
- CN115083602A CN115083602A CN202210981728.1A CN202210981728A CN115083602A CN 115083602 A CN115083602 A CN 115083602A CN 202210981728 A CN202210981728 A CN 202210981728A CN 115083602 A CN115083602 A CN 115083602A
- Authority
- CN
- China
- Prior art keywords
- diagnosed
- historical
- information
- answering system
- diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The disclosure relates to a mental disease auxiliary diagnosis method, a device, equipment, a storage medium and a system. According to the method, the target information corresponding to the constructed content is extracted from the first historical dialogue between the object to be diagnosed and the intelligent question-answering system through the constructed content of the knowledge spectrogram. And updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed, and generating a diagnosis index aiming at the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed. And when the conversation is finished, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the latest current information and the diagnosis index of the object to be diagnosed. In the conversation process, the symptoms of the patient can be completely collected, and the state of illness and the mind of the patient can be completely depicted, so that the auxiliary diagnosis information can completely and accurately depict the state of the patient, and a doctor can be accurately assisted to diagnose mental diseases.
Description
Technical Field
The present disclosure relates to the field of information technology, and in particular, to a method, an apparatus, a device, a storage medium, and a system for aided diagnosis of mental diseases.
Background
At present, the disease rate of mental diseases is higher and higher, but the inventor of the application finds that the diagnosis of the mental diseases by the current psychiatrist has certain subjectivity, so that the misdiagnosis rate of the mental diseases is higher. Therefore, there is a need in the art for a method that can assist a physician in diagnosing psychiatric disorders.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the present disclosure provides a mental disease auxiliary diagnosis method, apparatus, device, storage medium, and system, so that auxiliary diagnosis information can completely and accurately depict the current condition of a patient, thereby accurately assisting a doctor in diagnosing mental diseases.
In a first aspect, an embodiment of the present disclosure provides a method for aided diagnosis of a mental disease, including:
acquiring a first historical dialogue between an object to be diagnosed and an intelligent question-answering system;
extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram;
updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed;
generating a diagnosis index for the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed;
and generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the conversation between the object to be diagnosed and the intelligent question-answering system is finished.
In a second aspect, an embodiment of the present disclosure provides a diagnostic apparatus for aiding mental illness, including:
the acquisition module is used for acquiring a first history dialogue between the object to be diagnosed and the intelligent question-answering system;
the extraction module is used for extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram;
the updating module is used for updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed;
a first generation module, configured to generate a diagnosis index for the object to be diagnosed according to a historical speech of the object to be diagnosed in the first historical dialog and current information of the object to be diagnosed;
and the second generation module is used for generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the conversation between the object to be diagnosed and the intelligent question-answering system is finished.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.
In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method of the first aspect.
In a fifth aspect, an embodiment of the present disclosure provides a diagnosis assisting system for mental illness, including: a terminal and a server;
the object to be diagnosed carries out dialogue with the intelligent question-answering system through the terminal;
the server is adapted to perform the method according to the first aspect.
According to the mental disease auxiliary diagnosis method, the mental disease auxiliary diagnosis device, the mental disease auxiliary diagnosis equipment, the mental disease auxiliary diagnosis storage medium and the mental disease auxiliary diagnosis system, the first history dialogue of the object to be diagnosed and the intelligent question-answering system is obtained, and target information corresponding to the constructed content is extracted from the first history dialogue according to the constructed content of the knowledge spectrogram. Further, the historical information of the object to be diagnosed is updated according to the target information to obtain the current information of the object to be diagnosed, and a diagnosis index for the object to be diagnosed is generated according to the historical statement of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed. And when the conversation is finished, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the latest current information and the diagnosis index of the object to be diagnosed. In the conversation process, the symptoms of the patient can be completely collected, and the state of illness and the mind of the patient can be completely depicted, so that the auxiliary diagnosis information can more completely and accurately depict the current condition of the patient, and a doctor can be accurately assisted to diagnose mental diseases.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a diagnosis assisting method for mental illness according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a dialog provided by an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a knowledge-graph structure provided by an embodiment of the present disclosure;
FIG. 5 is a flowchart of a diagnosis assisting method for mental illness according to another embodiment of the present disclosure;
FIG. 6 is a flowchart of a diagnosis assisting method for mental illness according to another embodiment of the present disclosure;
FIG. 7 is a flowchart of a diagnosis assisting method for mental illness according to another embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a diagnosis assisting apparatus for mental illness according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an embodiment of an electronic device provided in the embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
The diagnosis of mental diseases by psychiatrists has certain subjectivity, so that the misdiagnosis rate of mental diseases is high. Therefore, there is a need in the art for a method that can assist a physician in diagnosing psychiatric disorders. In view of this problem, the embodiments of the present disclosure provide a diagnostic method for aiding mental diseases, which is described below with reference to specific embodiments.
Fig. 1 is a flowchart of a diagnosis assisting method for mental illness according to an embodiment of the disclosure. The method can be executed by a mental disease auxiliary diagnosis device, which can be implemented in a software and/or hardware manner, and the device can be configured in an electronic device, such as a server or a terminal, where the terminal specifically includes a mobile phone, a computer, or a tablet computer. In addition, the auxiliary diagnostic method for mental diseases according to the embodiment can be applied to the application scenario shown in fig. 2. As shown in fig. 2, the application scenario includes a terminal 21 and a server 22, where the terminal 21 may be a terminal used by a subject to be diagnosed, for example, the subject to be diagnosed may be a patient with a mental disease, or may be a normal person, and the subject to be diagnosed has a conversation with the smart question-answering system through the terminal 21. The server 22 may perform an auxiliary diagnosis on the mental state of the subject to be diagnosed according to a dialog between the subject to be diagnosed and the intelligent question-answering system, that is, the server 22 outputs auxiliary diagnosis information after performing the auxiliary diagnosis, and the auxiliary diagnosis information may be output to a doctor or a specialist, so as to assist the doctor or the specialist in performing a final diagnosis on the mental state of the subject to be diagnosed or performing a mental or physical intervention on the subject to be diagnosed. The method is described in detail below with reference to fig. 2, and as shown in fig. 1, the method includes the following specific steps:
s101, obtaining a first history dialogue between the object to be diagnosed and the intelligent question-answering system.
For example, the intelligent question-answering system can be integrated in the server 22, and when the terminal 21 and the server 22 establish connection, the object to be diagnosed carries out dialogue interaction with the intelligent question-answering system. The dialog interaction between the object to be diagnosed and the intelligent question-answering system is normal artificial intelligence dialog interaction. The present embodiment is not limited to the form of the dialog, and for example, the server 22 may transmit a question in the form of text to the terminal 21, and the subject to be diagnosed answers the question in the form of text, thereby forming a dialog text. Alternatively, the server 22 may transmit the question to the terminal 21 in the form of voice, and the subject to be diagnosed answers the question in the form of voice, thereby forming a dialogue voice, and further, may convert the dialogue voice into a dialogue text through an Automatic Speech Recognition (ASR) technique.
It can be understood that the number of dialog turns is continuously increased during the dialog process between the subject to be diagnosed and the intelligent question-and-answer system, as shown in fig. 3, one question-and-answer can be regarded as one dialog turn, 31 represents the first dialog turn, and 32 represents the second dialog turn. In this embodiment, all conversations that have occurred before the current time may be denoted as the first historical conversation, or the previous round or rounds of conversations before the current time may be denoted as the first historical conversation, that is, the first historical conversation may be one round of conversation or multiple rounds of conversation.
S102, extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram.
In this embodiment, the server 22 may also be configured with a knowledge spectrogram, and the content of the knowledge spectrogram includes names of diseases, symptoms, events, personal backgrounds, medications, and the like. The event may be an event related to the object to be diagnosed, such as the absence of an referee or family. It is understood that during the dialog of the subject to be diagnosed with the intelligent question-and-answer system, the intelligent question-and-answer system may ask the subject for a disease or a current condition, symptoms, recent occurrences, personal background, a medication or a current condition, etc. Therefore, when the server 22 acquires the first history dialogue, the target information corresponding to the constructed content can be extracted from the first history dialogue according to the constructed content of the knowledge spectrogram. For example, if the subject to be diagnosed shows that he or she has a depression, frequent insomnia, a company officer, a famous school graduation, and takes a hypnotic drug in the first history session, the server 22 extracts target information corresponding to the disease name from the first history session, that is, depression, that is, frequent insomnia, that is, target information corresponding to symptoms, that is, an event, that is, a company officer, that is, target information corresponding to a personal background, and that is, hypnotic drug, as shown in table 1. It is understood that the knowledge spectrogram not only includes the constructed content, but also includes the association relationship between different constructed contents, and in particular, the association relationship may be a causal relationship. For example, as shown in fig. 4, the disease name, symptom, event, personal context, and medication may correspond to a node, and the node corresponding to the disease name may point to the node corresponding to the symptom through a line segment with an arrow, so as to indicate that the disease corresponding to the disease name may cause the symptom. In addition, events can also lead to disease, and medications can also lead to disease.
TABLE 1
| Building content | Name of disease | Symptoms and signs | Event(s) | Personal background | Administration of drugs |
| Object information | Depression | Frequent insomnia | Is refereed by company | Famous brand school graduation | Hypnotic medicine |
Additionally, in other embodiments, the target information may be recorded as a user representation, or a knowledge spectrogram with added target information may be recorded as a user representation.
S103, updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed.
In the present embodiment, the server 22 has the capability of integrating the history of the subject to be diagnosed, thereby understanding the background of the subject to be diagnosed. For example, the history may be stored on a third party platform, and the server 22 may integrate the history on the third party platform about the subject to be diagnosed into the server 22. Alternatively, the server 22 may be a hospital-deployed server, the history is stored on other servers of the hospital, and the server 22 may integrate the history about the subject to be diagnosed stored on other servers into the server 22. Alternatively, the history of the subject to be diagnosed may be stored in the server 22 in advance, and in this case, the server 22 may directly perform the integration.
In a possible implementation manner, when obtaining the history record of the object to be diagnosed, the server 22 may extract, according to the constructed content of the knowledge spectrogram, history information corresponding to the constructed content from the history record, and a specific extraction process may be similar to the extraction process shown in table 1, and is not described herein again. The history information can be recorded as the history information of the object to be diagnosed. When the server 22 acquires the target information as shown in table 1, the history information of the object to be diagnosed may be updated according to the target information, where the update may include addition, deletion, modification, and the like. For example, the symptoms shown in table 1 do not have corresponding history information, and when the server 22 acquires the target information shown in table 1, the target information corresponding to the symptoms may be added. And obtaining the latest information of the object to be diagnosed after updating, wherein the latest information of the object to be diagnosed can be recorded as the current information of the object to be diagnosed.
It is understood that as the number of dialog turns increases, the current information of the subject to be diagnosed may be updated continuously, that is, the current information of the subject to be diagnosed obtained at time t1 may become historical information at the next time, that is, at time t 2. Therefore, in another possible implementation manner, the history information of the subject to be diagnosed may be the latest information of the subject to be diagnosed obtained at the last time. If the server 22 acquires the target information shown in table 1 at the current time, the latest information of the object to be diagnosed, which is acquired at the previous time, may be updated according to the target information, so as to acquire the latest information of the object to be diagnosed at the current time. The latest information of the object to be diagnosed can be recorded as the latest user portrait, and the current information of the object to be diagnosed can be recorded as the current user portrait.
S104, generating a diagnosis index aiming at the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed.
As shown in fig. 3, it is assumed that the first-round dialog 31 and the second-round dialog 32 constitute a first historical dialog, "YYYY" and "MMM" are historical utterances of the subject to be diagnosed in the first historical dialog. According to the historical statement and the current information of the object to be diagnosed, a diagnosis index aiming at the object to be diagnosed can be generated. Optionally, the diagnosis index comprises a symptom index, a linguistic index, an emotion index and a topic index.
For example, the current symptom of the subject to be diagnosed can be determined according to the historical utterance and the current information of the subject to be diagnosed, and can be one or more symptoms, for example. Further, it is screened according to traditional culture which symptoms are medical symptoms and which symptoms are not medical symptoms. Therefore, a score is calculated according to each symptom left after screening and the number of the left symptoms, and the score is marked as a symptom index. Similarly, whether the semantics of the object to be diagnosed are coherent, the grammar, the syntax, the lexical method are correct, the logic is reasonable and the like can be determined according to the historical utterances and the current information of the object to be diagnosed, a score is calculated, and the score is recorded as a linguistic index. According to the historical speech and the current information of the object to be diagnosed, the emotion classification of the object to be diagnosed in the conversation process can be determined, for example, the emotion classification can be divided into different emotions such as depression, low-fall, injury, distraction and the like, different emotions correspond to different scores, and the scores can be recorded as emotion indexes. And determining whether the topic skipping and question answering of the object to be diagnosed occur in the conversation process according to the historical utterance and the current information of the object to be diagnosed, and calculating a score, wherein the score is marked as a topic index.
And S105, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the dialogue between the object to be diagnosed and the intelligent question-answering system is finished.
Optionally, the current information of the object to be diagnosed and the diagnosis index change with the increase of the number of dialog turns respectively.
It is understood that as the number of dialog turns increases, the current information of the subject to be diagnosed is continuously updated, and the diagnosis index as described above is also continuously updated. When the conversation between the object to be diagnosed and the intelligent question-answering system is finished, the latest current information and the latest diagnosis index of the object to be diagnosed can be obtained. At this time, the server 22 may generate auxiliary diagnostic information for the subject to be diagnosed, based on the latest current information and the latest diagnostic index of the subject to be diagnosed. Specifically, the auxiliary diagnosis information may include latest current information and latest diagnosis index of the subject to be diagnosed. Alternatively, the server 22 may generate a structured inquiry result according to the latest current information of the subject to be diagnosed, for example, the structured inquiry result may include information of disease name, symptom, severity, time length of having suffered from disease, event, and the like. The server 22 may also generate a quantitative result, which may be a calculated value such as the cumulative sum or weighted sum of the symptom index, the linguistic index, the emotion index, and the topic index as described above, based on the latest diagnosis index of the subject to be diagnosed. Such that the auxiliary diagnostic information generated by the server 22 may include the structured interrogation results and the quantified results. Further, the server 22 may output the auxiliary diagnosis information to the doctor, and at the same time, the server 22 may also output the complete dialog between the subject to be diagnosed and the intelligent question-answering system to the doctor, so that the doctor can diagnose and/or intervene on the subject to be diagnosed according to the complete dialog and the auxiliary diagnosis information. That is, the complete dialog and the auxiliary diagnostic information are the basis for the diagnosis and/or intervention of the doctor. It will be appreciated that the auxiliary diagnostic information output by the server 22 may include not only that described above, but other information relating to diagnosis and/or intervention.
According to the method and the device, the first historical dialogue of the object to be diagnosed and the intelligent question answering system is obtained, and the target information corresponding to the constructed content is extracted from the first historical dialogue according to the constructed content of the knowledge spectrogram. Further, the historical information of the object to be diagnosed is updated according to the target information to obtain the current information of the object to be diagnosed, and a diagnosis index for the object to be diagnosed is generated according to the historical statement of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed. And when the conversation is finished, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the latest current information and the diagnosis index of the object to be diagnosed. In the conversation process, the symptoms of the patient can be completely collected, and the state of illness and the mind of the patient can be completely depicted, so that the auxiliary diagnosis information can more completely and accurately depict the current condition of the patient, and a doctor can be accurately assisted to diagnose mental diseases.
Fig. 5 is a flowchart of a diagnosis assisting method for mental illness according to another embodiment of the disclosure. In this embodiment, the method specifically includes the following steps:
s501, obtaining a first history dialogue between the object to be diagnosed and the intelligent question answering system.
Specifically, the implementation manner and specific principle of S501 and S101 are consistent, and are not described herein again.
S502, extracting target information corresponding to the constructed content from the first history dialogue according to the constructed content of the knowledge spectrogram.
Specifically, the implementation manner of S502 and S102 is consistent with a specific principle, and is not described herein again.
S503, updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed.
Specifically, the implementation manner of S503 and S103 is consistent with a specific principle, and is not described herein again.
S504, generating a diagnosis index aiming at the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed.
Specifically, the implementation manner of S504 and S104 is consistent with specific principles, and is not described herein again.
And S505, generating a first speech of the intelligent question-answering system in the next round of conversation according to the current information of the object to be diagnosed.
In this embodiment, in order to completely collect the symptoms of the patient, the question sentence generated by the intelligent question-answering system each time the patient is asked can be generated adaptively. For example, based on the current information of the patient, a first utterance of the intelligent question-and-answer system in the next pair of dialogs is generated, which may be a question sentence asked for the patient. Or generating the first speech of the intelligent question-answering system in the next pair of conversations according to the description of the patient in the historical conversation process.
S506, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the dialogue between the object to be diagnosed and the intelligent question-answering system is finished.
Specifically, the implementation manner of S506 and S105 is consistent with specific principles, and is not described herein again.
According to the embodiment, the first statement of the intelligent question-answering system in the next round of conversation is generated according to the current information of the object to be diagnosed, so that the first statement can be relatively fit with the actual situation of the object to be diagnosed, the conversation efficiency is improved, and the relevant information of the object to be diagnosed can be conveniently collected from the conversation.
Fig. 6 is a flowchart of a diagnosis assisting method for mental illness according to another embodiment of the disclosure. In this embodiment, the method specifically includes the following steps:
s601, obtaining the history of the object to be diagnosed.
For example, the server 22 has the capability of integrating a history of the subject to be diagnosed, which may be external information of the subject to be diagnosed, which may be information recorded in a third party platform. Specifically, the server 22 may integrate the external information of the subject to be diagnosed according to the authorization information of the subject to be diagnosed. This external information is shown in fig. 7.
S602, according to the construction content of the knowledge spectrogram, extracting historical information corresponding to the construction content from the historical record, and recording the historical information in the knowledge spectrogram.
For example, when the server 22 acquires the history of the object to be diagnosed, the history information corresponding to the constructed content may be extracted from the history according to the constructed content of the knowledge spectrogram, and a specific extraction process may be similar to the extraction process shown in table 1. Further, the server 22 may also record the history information in the knowledge spectrogram.
S603, obtaining a first history dialogue between the object to be diagnosed and the intelligent question-answering system.
Specifically, the implementation manner of S603 and S101 is consistent with a specific principle, and is not described herein again.
Optionally, the first historical dialogue includes dialogue text and dialogue speech. That is, in the present embodiment, the first historical dialog is a multi-modal signal, i.e., includes information of a plurality of different modalities simultaneously. In other embodiments, the first historical dialog may be a single modal signal, such as dialog text. As shown in FIG. 7, the present embodiment can input dialog text and dialog speech into a multimodal dialog engine. Or in other embodiments, the dialog text may be entered into a single modality dialog engine. A multimodal dialog engine or a single modality dialog engine may be deployed in the server 22. As shown in FIG. 7, the multi-modal or single-modal dialog engine includes the following capabilities: the method comprises the steps of multi-mode signal alignment processing, symptom phrase extraction and normalization, generation of diagnosis indexes of an object to be diagnosed based on culture, generation of system question sentences in the next round of conversation and generation of system common-case sentences in the next round of conversation. Each capability is described below.
And S604, aligning the dialog text and the dialog voice in a time dimension.
For example, when the multimodal dialog engine receives a multimodal signal, the multimodal dialog engine can perform an alignment process on the multimodal dialog engine to align information of different modalities. For example, the alignment process may be performed on dialog text and dialog speech in the time dimension.
S605, extracting target information corresponding to the constructed content from the first history dialogue according to the constructed content of the knowledge spectrogram.
For example, the server 22 may need to collect the patient's symptoms completely, and thus, in multiple rounds of conversations or in historical conversations, the ability to "extract and normalize" the symptom phrases or medical terms spoken by the patient to classify the symptoms or medical terms into symptoms or medical nouns is needed.
S606, updating the historical information in the knowledge spectrogram according to the target information to obtain the current information of the object to be diagnosed.
Specifically, the implementation manner of S606 and S103 is consistent with a specific principle, and is not described herein again.
S607, generating a diagnosis index for the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed.
In order to implement a normative psychiatric interview and to improve the accuracy of diagnosis and intervention decisions, the server 22 may provide structured interview results to physicians, as well as provide quantitative indicators. And the quantitative index is changed along with the difference of culture, so the multi-modal dialog engine has the capability of generating the diagnosis index of the object to be diagnosed based on the culture. Optionally, the diagnosis index comprises a symptom index, a linguistic index, an emotion index and a topic index.
And S608, generating a second statement of the intelligent question-answering system in the next round of dialogue according to a second historical dialogue between the object to be diagnosed and the intelligent question-answering system, the emotion of the object to be diagnosed in the second historical dialogue, and symptoms obtained according to the second historical dialogue, wherein the second statement is a statement of the intelligent question-answering system, and the first statement is a question of the object to be diagnosed asked by the intelligent question-answering system.
Because each speaking of the intelligent question-answering system may be a question of the object to be diagnosed during the conversation process, and for the patient with poor mental state, the question is asked continuously or the system is asked too much, which is extremely easy to cause fluctuation or dissatisfaction in the mood of the patient. Therefore, in order to solve the problem, in this embodiment, a second utterance of the smart question-and-answer system in the next round of dialog may be generated according to a second historical dialog of the subject to be diagnosed with the smart question-and-answer system, an emotion of the subject to be diagnosed in the second historical dialog, and a symptom obtained according to the second historical dialog, where the second utterance is an utterance of the smart question-and-answer system in common. Specifically, the second history session may be the same as or different from the first history session described above. For example, in a different case, the second historical dialog may be the first 5 rounds of dialog before the current time. That is, the second utterance may be a common-emotion statement of the system in the next round of conversation, and the common-emotion statement may be a statement sentence for stating the understanding of the system to the patient.
And S609, generating a first speech of the intelligent question-answering system in the next round of conversation according to the current information of the object to be diagnosed.
Specifically, the implementation manner of S609 and S505 is consistent with a specific principle, and is not described herein again. Specifically, the first utterance may be a question, and the second utterance may be located before the first utterance, so that the patient feels self-understanding, and the patient may respond to the first utterance in more detail, thereby better collecting symptoms of the patient and information related to diagnosis.
As shown in fig. 7, in the next session, the server 22 may collect the dialog text and the dialog voice and input the dialog text and the dialog voice into the multimodal dialog engine, which may again perform the above-described capabilities, thereby forming a loop for each session. Optionally, the current information of the object to be diagnosed and the diagnosis index change with the increase of the number of dialog turns respectively.
S610, generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the dialogue between the object to be diagnosed and the intelligent question-answering system is finished.
Specifically, the implementation manner of S610 and S105 is consistent with specific principles, and is not described herein again. In addition, it is understood that the end of the dialog between the subject to be diagnosed and the intelligent question-answering system may be the end of the dialog caused after the intelligent question-answering system has asked all questions, or may be the result of the dialog caused by the patient stopping answering.
By integrating the external information of the patient, the embodiment can better understand the background information or the historical information of the patient, thereby comprehensively evaluating the mental aspect of the patient and improving the accuracy of evaluation. In addition, because the system can output the auxiliary diagnosis information after the patient has a complete conversation with the intelligent question-answering system every time, the patient can compare the currently output auxiliary diagnosis information with the auxiliary diagnosis information output historically, so that the patient can know the change of the mental state of the patient, such as whether the patient has progress or severity. Alternatively, the system may send the change result of the auxiliary diagnostic information corresponding to the patient to the terminal of the patient so that the patient can know the change result. In addition, the auxiliary diagnostic information, as well as the results of changes in the auxiliary diagnostic information, can be used to manage the patient's disease history, thereby affecting subsequent follow-up and intervention strategies. In addition, the embodiment does not aim at a certain therapy, but describes the illness state and psychological picture of the patient from a lower layer to enable the application (therapy) of the upper layer, thereby enabling the application of the upper layer to be more accurate. Because the patient can know and track the self mental state and the illness state on line and can acquire intervention strategies (such as doctor suggestions or system suggestions) on line, the patient can be effectively ensured to obtain instant intervention and treatment under the epidemic situation or the condition that the doctor resources are not available.
Fig. 8 is a schematic structural diagram of an auxiliary diagnostic apparatus for mental illness according to an embodiment of the present disclosure. The diagnostic apparatus for aiding mental diseases provided by the embodiment of the present disclosure may execute the processing procedure provided by the diagnostic method for aiding mental diseases, as shown in fig. 8, the diagnostic apparatus 80 for aiding mental diseases includes:
the acquisition module 81 is used for acquiring a first history dialogue between the object to be diagnosed and the intelligent question-answering system;
an extraction module 82, configured to extract, according to a constructed content of a knowledge spectrogram, target information corresponding to the constructed content from the first history session;
the updating module 83 is configured to update the historical information of the object to be diagnosed according to the target information, so as to obtain current information of the object to be diagnosed;
a first generating module 84, configured to generate a diagnosis index for the object to be diagnosed according to a historical speech of the object to be diagnosed in the first historical dialog and current information of the object to be diagnosed;
and a second generating module 85, configured to generate auxiliary diagnostic information for the object to be diagnosed according to the current information and the diagnostic index of the object to be diagnosed when the session between the object to be diagnosed and the intelligent question-answering system is ended.
Optionally, the diagnosis index comprises a symptom index, a linguistic index, an emotion index and a topic index.
Optionally, the diagnosis assisting apparatus 80 for mental illness further includes: a third generating module 86, configured to, after the first generating module 84 generates a diagnosis index for the subject to be diagnosed according to the historical speech of the subject to be diagnosed in the first historical dialog and the current information of the subject to be diagnosed, generate a first speech of the intelligent question and answer system in a next round of dialog according to the current information of the subject to be diagnosed.
Optionally, the third generating module 86 is further configured to: before generating a first speech of the intelligent question-answering system in the next round of conversation according to the current information of the object to be diagnosed, generating a second speech of the intelligent question-answering system in the next round of conversation according to a second historical conversation of the object to be diagnosed and the intelligent question-answering system, the emotion of the object to be diagnosed in the second historical conversation, and the symptom obtained according to the second historical conversation, wherein the second speech is the speech of the intelligent question-answering system in the same situation as the intelligent question-answering system, and the first speech is the question of the intelligent question-answering system to the object to be diagnosed.
Optionally, the obtaining module 81 is further configured to: before a first history dialogue between an object to be diagnosed and an intelligent question-answering system is obtained, acquiring a history record of the object to be diagnosed; the extraction module 82 is further configured to: extracting historical information corresponding to the constructed content from the historical record according to the constructed content of the knowledge spectrogram, and recording the historical information in the knowledge spectrogram; the updating module 83 is specifically configured to, when updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed: and updating the historical information in the knowledge spectrogram according to the target information to obtain the current information of the object to be diagnosed.
Optionally, the first historical dialogue includes dialogue text and dialogue voice; the diagnostic device for aiding mental disease 80 further includes: and the alignment processing module 87 is configured to, after the obtaining module 81 obtains the first historical dialog between the object to be diagnosed and the smart question-answering system, perform alignment processing on the dialog text and the dialog voice in a time dimension.
Optionally, the current information of the object to be diagnosed and the diagnosis index change with the increase of the number of dialog turns respectively.
The diagnosis assisting apparatus for mental diseases in the embodiment shown in fig. 8 can be used for implementing the technical solutions of the above method embodiments, and the implementation principle and technical effects are similar, which are not described herein again.
The internal functions and structure of the mental disease auxiliary diagnosis apparatus, which can be implemented as one kind of electronic device, are described above. Fig. 9 is a schematic structural diagram of an embodiment of an electronic device provided in the embodiment of the present disclosure. As shown in fig. 9, the electronic device includes a memory 91 and a processor 92.
The memory 91 is used to store programs. In addition to the above-described programs, the memory 91 may also be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phonebook data, messages, pictures, videos, and so forth.
The memory 91 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The processor 92 is coupled to the memory 91 and executes the programs stored in the memory 91 for:
acquiring a first historical dialogue between an object to be diagnosed and an intelligent question-answering system;
extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram;
updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed;
generating a diagnosis index for the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed;
and generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the conversation between the object to be diagnosed and the intelligent question-answering system is finished.
Further, as shown in fig. 9, the electronic device may further include: communication components 93, power components 94, audio components 95, a display 96, and other components. Only some of the components are schematically shown in fig. 9, and the electronic device is not meant to include only the components shown in fig. 9.
The communication component 93 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 93 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 93 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
A power supply assembly 94 provides power to the various components of the electronic device. The power components 94 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic devices.
The audio component 95 is configured to output and/or input audio signals. For example, the audio assembly 95 includes a Microphone (MIC) configured to receive external audio signals when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 91 or transmitted via the communication component 93. In some embodiments, audio assembly 95 also includes a speaker for outputting audio signals.
The display 96 includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
In addition, the embodiment of the present disclosure also provides a computer readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the mental illness auxiliary diagnosis method described in the above embodiment.
In addition, the embodiment of the present disclosure also provides a diagnosis system for aiding mental illness, which includes: a terminal and a server; as shown in fig. 2, specifically, the object to be diagnosed has a dialogue with the intelligent question-answering system through the terminal; the server is used for executing the mental disease auxiliary diagnosis method in the embodiment.
Optionally, the system further includes: a third party platform for storing a history of the object to be diagnosed; the server is used for acquiring the history of the object to be diagnosed from the third-party platform.
Optionally, the server includes the intelligent question-answering system. For example, the intelligent question and answer system may be integrated in the server, or the intelligent question and answer system may be integrated in another server, which is not limited herein.
In addition, the server may further include a multi-modal dialog engine as shown in fig. 7, so as to implement the mental disease auxiliary diagnosis method as shown in fig. 7.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (13)
1. A method for aided diagnosis of a psychiatric disorder, wherein the method comprises:
acquiring a first historical dialogue between an object to be diagnosed and an intelligent question-answering system;
extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram;
updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed;
generating a diagnosis index for the object to be diagnosed according to the historical speech of the object to be diagnosed in the first historical dialogue and the current information of the object to be diagnosed;
and generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the conversation between the object to be diagnosed and the intelligent question-answering system is finished.
2. The method of claim 1, wherein the diagnostic indicators include a symptom indicator, a linguistic indicator, an emotion indicator, and a topic indicator.
3. The method according to claim 1, wherein after generating a diagnosis index for the subject to be diagnosed according to the historical speech of the subject to be diagnosed in the first historical dialogue and the current information of the subject to be diagnosed, the method further comprises:
and generating a first speech of the intelligent question-answering system in the next round of conversation according to the current information of the object to be diagnosed.
4. The method according to claim 3, wherein before generating the first utterance of the intelligent question answering system in the next dialog according to the current information of the subject to be diagnosed, the method further comprises:
and generating a second speech of the intelligent question-answering system in the next round of conversation according to a second history conversation of the object to be diagnosed and the intelligent question-answering system, the emotion of the object to be diagnosed in the second history conversation and symptoms obtained according to the second history conversation, wherein the second speech is a speech of the common emotion of the intelligent question-answering system, and the first speech is a question asked by the intelligent question-answering system to the object to be diagnosed.
5. The method of claim 1, wherein prior to obtaining a first historical dialogue of the subject to be diagnosed with the smart question-and-answer system, the method further comprises:
acquiring a history record of the object to be diagnosed;
extracting historical information corresponding to the constructed content from the historical record according to the constructed content of the knowledge spectrogram, and recording the historical information in the knowledge spectrogram;
correspondingly, updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed, including:
and updating the historical information in the knowledge spectrogram according to the target information to obtain the current information of the object to be diagnosed.
6. The method of claim 1, wherein the first historical dialog comprises dialog text and dialog speech;
correspondingly, after the first historical dialogue between the object to be diagnosed and the intelligent question-answering system is obtained, the method further comprises the following steps:
and aligning the dialog text and the dialog voice in a time dimension.
7. The method according to claim 1, wherein the current information of the object to be diagnosed and the diagnosis index are respectively changed as the number of conversation turns increases.
8. An auxiliary diagnostic device for mental diseases, which comprises:
the acquisition module is used for acquiring a first history dialogue between the object to be diagnosed and the intelligent question-answering system;
the extraction module is used for extracting target information corresponding to the constructed content from the first historical dialogue according to the constructed content of the knowledge spectrogram;
the updating module is used for updating the historical information of the object to be diagnosed according to the target information to obtain the current information of the object to be diagnosed;
a first generation module, configured to generate a diagnosis index for the object to be diagnosed according to a historical speech of the object to be diagnosed in the first historical dialog and current information of the object to be diagnosed;
and the second generation module is used for generating auxiliary diagnosis information aiming at the object to be diagnosed according to the current information and the diagnosis index of the object to be diagnosed when the conversation between the object to be diagnosed and the intelligent question-answering system is finished.
9. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method of any one of claims 1-7.
11. A diagnostic aid system for mental disorders, wherein the system comprises: a terminal and a server;
the object to be diagnosed carries out dialogue with the intelligent question-answering system through the terminal;
the server is configured to perform the method of any one of claims 1-7.
12. The system of claim 11, wherein the system further comprises: a third party platform for storing a history of the object to be diagnosed;
the server is used for acquiring the history of the object to be diagnosed from the third-party platform.
13. The system of claim 11, wherein the server comprises the smart question-answering system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210981728.1A CN115083602A (en) | 2022-08-16 | 2022-08-16 | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210981728.1A CN115083602A (en) | 2022-08-16 | 2022-08-16 | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115083602A true CN115083602A (en) | 2022-09-20 |
Family
ID=83244830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210981728.1A Pending CN115083602A (en) | 2022-08-16 | 2022-08-16 | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115083602A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119474259A (en) * | 2024-09-09 | 2025-02-18 | 人工智能与数字经济广东省实验室(广州) | A quantitative diagnosis method, device and equipment for abnormal psychological diseases |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170277855A1 (en) * | 2016-03-24 | 2017-09-28 | Fujitsu Limited | System and a method for assessing patient risk using open data and clinician input |
| US20170277857A1 (en) * | 2016-03-24 | 2017-09-28 | Fujitsu Limited | System and a method for assessing patient treatment risk using open data and clinician input |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| CN109243605A (en) * | 2018-09-20 | 2019-01-18 | 段新 | A kind of phrenoblabia diagnoses and treatment system based on artificial intelligence |
| US20190311807A1 (en) * | 2018-04-06 | 2019-10-10 | Curai, Inc. | Systems and methods for responding to healthcare inquiries |
| WO2020201389A1 (en) * | 2019-04-04 | 2020-10-08 | Koninklijke Philips N.V. | Method and system for medical diagnosis assistance |
| CN112700831A (en) * | 2021-01-06 | 2021-04-23 | 北京左医科技有限公司 | Doctor auxiliary diagnosis method and system based on patient medical record information |
| CN113571184A (en) * | 2021-07-20 | 2021-10-29 | 武汉情智感知科技有限公司 | A dialogue interaction design method and system for mental health assessment |
| CN113707299A (en) * | 2021-08-27 | 2021-11-26 | 平安科技（深圳）有限公司 | Auxiliary diagnosis method and device based on inquiry session and computer equipment |
| CN114283912A (en) * | 2021-12-17 | 2022-04-05 | 陈彦方 | Medical record filing method based on RTHD and artificial intelligence and cloud platform system |
| CN114334163A (en) * | 2022-01-25 | 2022-04-12 | 思必驰科技股份有限公司 | Depression diagnosis dialogue dataset generation method, electronic device and storage medium |
-
2022
- 2022-08-16 CN CN202210981728.1A patent/CN115083602A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170277855A1 (en) * | 2016-03-24 | 2017-09-28 | Fujitsu Limited | System and a method for assessing patient risk using open data and clinician input |
| US20170277857A1 (en) * | 2016-03-24 | 2017-09-28 | Fujitsu Limited | System and a method for assessing patient treatment risk using open data and clinician input |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| US20190311807A1 (en) * | 2018-04-06 | 2019-10-10 | Curai, Inc. | Systems and methods for responding to healthcare inquiries |
| CN109243605A (en) * | 2018-09-20 | 2019-01-18 | 段新 | A kind of phrenoblabia diagnoses and treatment system based on artificial intelligence |
| WO2020201389A1 (en) * | 2019-04-04 | 2020-10-08 | Koninklijke Philips N.V. | Method and system for medical diagnosis assistance |
| CN112700831A (en) * | 2021-01-06 | 2021-04-23 | 北京左医科技有限公司 | Doctor auxiliary diagnosis method and system based on patient medical record information |
| CN113571184A (en) * | 2021-07-20 | 2021-10-29 | 武汉情智感知科技有限公司 | A dialogue interaction design method and system for mental health assessment |
| CN113707299A (en) * | 2021-08-27 | 2021-11-26 | 平安科技（深圳）有限公司 | Auxiliary diagnosis method and device based on inquiry session and computer equipment |
| CN114283912A (en) * | 2021-12-17 | 2022-04-05 | 陈彦方 | Medical record filing method based on RTHD and artificial intelligence and cloud platform system |
| CN114334163A (en) * | 2022-01-25 | 2022-04-12 | 思必驰科技股份有限公司 | Depression diagnosis dialogue dataset generation method, electronic device and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| 张靓等: "基于知识图谱的自闭症谱系障碍研究主题分析", 《中国卫生产业》 * |
| 田迎等: "基于知识图谱的抑郁症自动问答系统研究", 《湖北大学学报(自然科学版)》 * |
| 秦帅波: "中医知识智能诊断系统的研究", 《计算机产品与流通》 * |
| 袁璠等: "人工智能技术在抑郁及自杀管理中的应用", 《中国全科医学》 * |
| 袁钦湄等: "人工智能在精神疾病中的应用", 《国际精神病学杂志》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119474259A (en) * | 2024-09-09 | 2025-02-18 | 人工智能与数字经济广东省实验室(广州) | A quantitative diagnosis method, device and equipment for abnormal psychological diseases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12230369B2 (en) | Systems and methods for mental health assessment | |
| US11120895B2 (en) | Systems and methods for mental health assessment | |
| US11881302B2 (en) | Virtual medical assistant methods and apparatus | |
| US20200152304A1 (en) | Systems And Methods For Intelligent Voice-Based Journaling And Therapies | |
| US20090326937A1 (en) | Using personalized health information to improve speech recognition | |
| CN113689951B (en) | Intelligent diagnosis guidance method, system and computer-readable storage medium | |
| CN102149319A (en) | Alzheimer's cognitive enabler | |
| CN107845422A (en) | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue | |
| US12226221B2 (en) | Dynamic neuropsychological assessment tool | |
| KR20200080290A (en) | Machine-assisted conversation systems and devices and methods for interrogating medical conditions | |
| Griol et al. | Modeling the user state for context-aware spoken interaction in ambient assisted living | |
| US11547345B2 (en) | Dynamic neuropsychological assessment tool | |
| CN116913450B (en) | Method and device for generating medical records in real time | |
| JP2022022129A (en) | Guidance support equipment, guidance support systems, and programs | |
| Kocabiyikoglu et al. | A spoken drug prescription dataset in french for spoken language understanding | |
| CN115083602A (en) | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system | |
| CN111241238A (en) | User evaluation method and device, electronic equipment and storage medium | |
| CN118888156A (en) | Clinical trial project matching method, device and electronic device based on patient dialogue | |
| CN112836059B (en) | Medical map establishing method and device and medical map inquiring method and device | |
| CN116994723A (en) | Online triage method, device and equipment based on medical knowledge and deep learning | |
| US20250226066A1 (en) | Systems and methods for mental health assessment | |
| CN115035994B (en) | Medical service guidance method, device, electronic device and storage medium | |
| CN119811647B (en) | A urology consultation method and device based on LLM context embedding assistance | |
| JP2025084090A (en) | Information processing system, information processing method, information processing device, and program | |
| Gryspeerdt | I am not my self: Reconceiving identity in rehabilitation care |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220920 |