CN115101193A - Symptom recommendation method and device and computer-readable storage medium - Google Patents
Symptom recommendation method and device and computer-readable storage medium Download PDFInfo
- Publication number
- CN115101193A CN115101193A CN202210712343.5A CN202210712343A CN115101193A CN 115101193 A CN115101193 A CN 115101193A CN 202210712343 A CN202210712343 A CN 202210712343A CN 115101193 A CN115101193 A CN 115101193A
- Authority
- CN
- China
- Prior art keywords
- symptom
- preset
- symptoms
- candidate
- user
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a symptom recommendation method, a device and a computer-readable storage medium, comprising: the method comprises the steps of obtaining user information including user symptoms input by a user, determining candidate symptoms according to the user symptoms, determining a correlation coefficient between the candidate symptoms and each preset symptom, determining target symptoms from the preset symptoms according to the correlation coefficient, and recommending the symptoms according to the target symptoms.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a symptom recommendation method, device, and computer-readable storage medium.
Background
At present, both in the process of self-diagnosis by a patient using an application program and in the process of inquiry of the patient by a doctor based on the application program, the user experience is highly dependent, so that a scheme capable of recommending symptoms to the user is urgently needed to reduce the dependence on the user experience in the self-diagnosis or inquiry process.
Disclosure of Invention
An object of the embodiments of the present application is to provide a symptom recommendation method, apparatus, device and storage medium, so as to solve the above technical problems.
The embodiment of the application provides a symptom recommendation method, which comprises the following steps:
acquiring user information; the user information comprises user symptoms input by a user;
determining candidate symptoms according to the user symptoms;
determining a correlation coefficient between the candidate symptom and each preset symptom; the correlation coefficient is obtained by performing singular value decomposition on the correlation degree matrix to obtain characteristic vector matrixes corresponding to the preset symptoms respectively and calculating based on the characteristic vector matrixes; each element in the association degree matrix represents the association degree between the corresponding preset symptom and the corresponding preset prescription;
determining a target symptom from the preset symptoms according to the correlation coefficient;
and recommending symptoms according to the target symptoms.
In the implementation process, the user can be recommended according to the target symptoms, so that the dependence on the user experience in the self-diagnosis or inquiry process can be reduced.
Further, the target symptoms include sign symptoms.
In the implementation process, the method and the device are suitable for a scene of physical sign and symptom recommendation for the user, and the universality of the scheme is improved.
Further, the candidate symptom comprises a first candidate symptom; the determining candidate symptoms from the user symptoms comprises:
determining a chief complaint symptom corresponding to the user symptom, and taking the chief complaint symptom as the first candidate symptom;
or the like, or, alternatively,
and taking the last input symptom of the user symptoms as the first candidate symptom.
In the implementation process, the chief complaint symptom is taken as the first candidate symptom, or the last symptom input in the user symptoms is taken as the first candidate symptom, so that the candidate symptom is the main or important symptom of the patient, and therefore, the target symptom determined based on the candidate symptom is the symptom with high correlation degree with the focus, and the reliability and the accuracy of the recommendation result are improved.
Further, the candidate symptom further comprises a second candidate symptom; the determining candidate symptoms from the user symptoms comprises:
a second candidate symptom associated with the first candidate symptom is determined.
In the implementation process, the target symptom can be determined based on a plurality of candidate symptoms, namely the first candidate symptom and the second candidate symptom associated with the first candidate symptom, so that the recommended target symptom is related to the focus and accords with the physical actual condition of the patient, and the accuracy of the recommendation result is further improved.
Further, the determining a correlation coefficient between the candidate symptom and each preset symptom includes:
determining a first correlation coefficient between the first candidate symptom and each of the preset symptoms, and determining a second correlation coefficient between the second candidate symptom and each of the preset symptoms
The determining the sign symptoms needing to be recommended from the preset symptoms according to the correlation coefficient comprises the following steps:
for each preset symptom, determining a third association coefficient between the preset symptom and a candidate symptom group according to the corresponding first association coefficient and the second association coefficient; the candidate symptom group is a symptom group consisting of the first candidate symptom and the second candidate symptom;
and screening out the physical sign symptoms needing to be recommended from the preset symptoms according to the third correlation coefficient.
In the implementation process, the first candidate symptom and the second candidate symptom are used as a candidate symptom group, and the target symptom with high relevance to the user symptom is determined from the preset symptoms according to the third correlation coefficient of each preset symptom and the candidate symptom group, so that the accuracy of the recommendation result is improved.
Further, the determining a second candidate symptom associated with the first candidate symptom comprises:
determining a fourth correlation coefficient between the first candidate symptom and each of the user symptoms other than the first candidate symptom;
determining symptoms corresponding to a fourth correlation coefficient which is greater than or equal to a preset correlation coefficient threshold value as candidate symptoms to be determined;
and screening out the candidate symptom to be determined corresponding to the maximum value of the fourth correlation coefficient from the candidate symptoms to be determined as a second candidate symptom.
In the implementation process, in the user symptoms input by the user, the symptom with the highest correlation degree with the first candidate symptom is taken as the second candidate symptom, so that the second candidate symptom is ensured to be the main uncomfortable symptom of the user, and the reliability of the final recommendation result can be improved.
Further, the determining a correlation coefficient between the candidate symptom and each preset symptom includes:
inquiring the correlation coefficient between the candidate symptom and each preset symptom from a preset correlation coefficient database; and the correlation coefficient database stores the correlation coefficient among the preset symptoms.
In the implementation process, the correlation coefficient is not required to be calculated, but the correlation coefficient can be directly inquired from a preset correlation coefficient database, so that the operation efficiency is improved.
Further, each element in the association degree matrix is the association degree of the preset symptom relative to the preset prescription calculated based on a preset medical record database; the medical record database comprises a plurality of medical record documents, and each medical record document comprises information of a plurality of preset symptoms and information of a preset prescription capable of treating the preset symptoms; the degree of correlation is expressed by formula
Calculating to obtain;
wherein R is si,pj Representing the values of corresponding elements at the ith row and jth column in the correlation degree matrix, si representing the ith preset symptom, pj representing the jth preset prescription, n ij Represents the number, sigma, of medical record documents which simultaneously contain the jth preset prescription and the ith preset symptom in the medical record database k n kj Represents the total number of occurrences or symptom category number, sigma of all preset symptoms in the same medical record document with the jth preset prescription in the medical record database k n ki The total occurrence times or the types of all the preset prescriptions in the medical record database, which appear in the same medical record document with the ith preset symptom, are represented, and D represents the total occurrence times or the types of all the preset prescriptions in the medical record database; e and Q are preset constants.
In the implementation process, a new mode of calculating the correlation coefficient among the preset symptoms is provided, the characteristic vectors corresponding to the preset symptoms are determined based on the correlation degree between the prescription and the symptoms, and the accuracy of the calculation result is improved.
An embodiment of the present application further provides an electronic device, which includes a processor and a memory, where the memory stores a computer program, and the processor executes the computer program to implement any one of the above methods.
Embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by at least one processor, the computer program implements any one of the above methods.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a symptom recommendation method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a user symptom recommendation according to an embodiment of the present application;
fig. 3 is a schematic flow chart of determining the correlation coefficient according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a symptom recommendation device according to a second embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the descriptions relating to "first", "second", etc. in the embodiments of the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In addition, technical solutions between the embodiments may be combined with each other, but must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
In the description of the present invention, it should be understood that the numerical references before the steps do not identify the sequence of executing the steps, but merely serve to facilitate the description of the present invention and to distinguish each step, and thus, should not be construed as limiting the present invention.
Various embodiments are provided below to describe a symptom recommendation method, apparatus, and computer-readable storage medium.
The first embodiment is as follows:
referring to fig. 1, an embodiment of the present application provides a symptom recommendation method, which may be applied to electronic devices, including but not limited to PCs (Personal computers), mobile phones, tablet computers, and notebook computers. The symptom recommendation method provided by the embodiment of the application can comprise the following steps:
s11: acquiring user information; the user information includes user symptoms entered by the user.
S12: candidate symptoms are determined based on the user symptoms.
S13: determining a correlation coefficient between the candidate symptom and each preset symptom; the correlation coefficient is a coefficient obtained by performing singular value decomposition on the correlation degree matrix to obtain a characteristic vector matrix corresponding to each preset symptom and calculating based on each characteristic vector matrix; each element in the association degree matrix represents the association degree between the corresponding preset symptom and the corresponding preset prescription.
S14: and determining the target symptom from the preset symptoms according to the correlation coefficient.
S15: and recommending symptoms according to the target symptoms.
The above steps are specifically described below.
It should be noted that, in the practical application, for step S15, the target symptom may be recommended to the target user, where the target user may be the user in step S11, or another user.
For example, the user in step S11 may be a patient user, for example, the patient himself or herself, or a person who is familiar with the disease condition of the patient, for example, a family member of the patient, in which case, in step S15, the target symptom may be recommended to the patient user to prompt the patient user to perform symptom self-examination, so that more comprehensive disease condition information may be collected at the patient side; of course, the target symptom may also be recommended to the doctor user, so that the doctor can ask the patient user for the recommended target symptom.
The user information in the embodiment of the application can include the user symptoms, and also can include information such as the age and the sex of the user, so that when the method is applied to a scene for assisting a doctor in inquiring, the doctor can be assisted in determining the cause of a disease, and diagnosis and treatment are completed.
The user can input user symptoms, such as cough, headache and the like, on the intelligent inquiry platform of the application program according to the actual physical condition.
The target symptoms in the embodiment of the application can include sign symptoms, and the sign symptoms refer to symptoms which can be objectively detected by others and are objectively existing symptoms and do not change with subjective consciousness of a patient. The other person may be anyone other than the patient, such as a doctor or a patient's attendant. The examination here refers to a means of examining the other person by an indirect inquiry such as the naked eye or touch.
The physical basic functional conditions of the patient, such as diet, sleep, defecation, menstruation and mental state, such as mental state, body form, facial state, tongue state, pulse state and the like, are not changed along with the subjective consciousness of the patient, and can be directly observed or detected by other people except the patient, therefore, the physical symptoms in the embodiment of the application can comprise at least one of symptoms related to body form, facial state, tongue state, pulse state, diet, sleep, mental state, menstruation and defecation. All the signs can be used to judge the cause of the disease, the severity and urgency of the disease, the occurrence mechanism of the disease, the location of the disease, and the physical condition, but the signs are easy to be ignored by the patient and usually need to be examined by a doctor.
The physical sign symptoms are recommended to the patient user, the patient user can be prompted to perform physical sign symptom self-examination according to the recommended result, relatively comprehensive symptom information can be collected without examining the symptoms by a doctor, and diagnosis and treatment efficiency can be improved.
In the embodiment of the present application, there may be one candidate symptom or a plurality of candidate symptoms.
In the first example of the present embodiment, in step S12, a chief complaint symptom corresponding to a symptom of the user may be determined, and the chief complaint symptom may be set as a first candidate symptom. Chief complaints refer to the chief complaints that most afflict the patient or cause his or her visit.
For example, when a patient user inputs user symptoms according to physical reality, a chief complaint label can be added to a chief complaint in the input user symptoms, and the electronic device can determine which one of the input user symptoms is the chief complaint symptom by recognizing the chief complaint label and then take the chief complaint symptom as a first candidate symptom of the current patient user.
In the second example of the embodiment, considering that the patient user does not know the pathological process, and the chief complaint is important in the diagnosis and treatment process of the disease, the user information including the user symptoms, the sex, and the age, which is input by the patient user, may be pushed to the doctor user, and the doctor user determines the chief complaint of the patient user from the user symptoms according to the user information, that is, the electronic device receives the chief complaint determined by the doctor user according to the user symptoms, and then takes the chief complaint as the first candidate symptom of the current patient user.
In the third example of the present embodiment, the user information input by the patient user may be input into the trained chief complaint symptom recommendation model to obtain chief complaint symptoms corresponding to the user symptoms. The chief complaint symptom recommendation model is a model obtained by training based on training sample data, and each training sample data comprises information of a plurality of user symptoms and information of corresponding chief complaint symptoms.
It should be noted that, when a plurality of determined chief complaints exist, one of the chief complaints may be randomly selected as the first candidate symptom. The corresponding weight value may also be set in advance for each preset symptom in the preset symptom database, the weight value corresponding to each preset symptom may be set according to the frequency of occurrence of each symptom in the medical record database, the higher the frequency of occurrence of a symptom, the higher the weight value corresponding to the symptom, and when a plurality of chief complaint symptoms are determined, the chief complaint symptom corresponding to the largest weight value is selected as the first candidate symptom.
In step S12, the last input symptom of the user symptoms may be used as the first candidate symptom. It should be noted that the manner in which the first candidate symptom is selected from the user symptoms input by the patient user may be flexibly set by the developer. For example, the chief complaint symptom may be preferentially used as the first candidate symptom, and when the chief complaint symptom cannot be determined, the last input symptom of the user symptoms may be used as the first candidate symptom.
Illustratively, a second candidate symptom associated with the first candidate symptom may be determined based on the first candidate symptom. The manner in which the second candidate symptom is determined is described below.
In some embodiments, when the determined first candidate symptom is a symptom of user symptoms input by the user, a fourth association coefficient between the first candidate symptom and each symptom of the user symptoms except the first candidate symptom may be determined, a symptom corresponding to the fourth association coefficient greater than or equal to a preset association coefficient threshold value is determined as a candidate symptom to be determined, and then the candidate symptom to be determined corresponding to the maximum value of the fourth association coefficient is screened out from each candidate symptom to be determined as a second candidate symptom. Of course, if the first candidate symptom is not a symptom of the user symptom, the fourth correlation coefficient between the first candidate symptom and each user symptom input by the user is determined, and the second candidate symptom may be determined by referring to the above method, which is not described herein again.
In some other embodiments, a correlation coefficient between the first candidate symptom and each preset symptom in the preset symptom database may be determined, and the preset symptom corresponding to the maximum value of the correlation coefficient may be used as the second candidate symptom.
It should be noted that a symptom database may be preset, a plurality of preset symptoms are stored in the database, the preset symptoms may be composed of preset sign symptoms and preset non-sign symptoms, and at this time, the candidate symptoms and the recommended symptoms mentioned in the embodiment of the present application all belong to the symptoms in the database.
It should be noted that, when the preset symptom database includes preset sign symptoms and preset non-sign symptoms, the preset sign symptoms and the preset non-sign symptoms can be distinguished by setting a label for the symptoms in advance. For example, an objective attribute tag can be set for a preset sign symptom to indicate that the sign symptom is the preset sign symptom, and a symptom without the objective attribute tag or with the subjective attribute tag is a preset non-sign symptom. Or a subjective attribute label can be set for the preset non-sign symptom, and the symptom without the subjective attribute label is the preset sign symptom.
It will be appreciated that when the determined candidate symptom comprises a first candidate symptom and a second candidate symptom, a first correlation coefficient between the first candidate symptom and each of the predetermined symptoms may be determined, and a second correlation coefficient between the second candidate symptom and each of the predetermined symptoms may be determined.
In an alternative embodiment, for each preset symptom in the symptom database, a third correlation coefficient between the preset symptom and a candidate symptom group is determined according to the corresponding first correlation coefficient and second correlation coefficient, wherein the candidate symptom group is a symptom group consisting of the first candidate symptom and the second candidate symptom; and screening out target symptoms needing to be recommended from the preset symptoms according to the third correlation coefficient. By associating the preset symptom with the candidate symptom group, comprehensiveness of the recommendation result can be improved. For example, the product between the first correlation coefficient and the corresponding preset weight may be added to the product between the second correlation coefficient and the corresponding preset weight to obtain a corresponding third correlation coefficient.
In another alternative embodiment, a first target symptom to be recommended may be directly screened from the preset symptoms according to the first correlation coefficient, and a second target symptom to be recommended may be directly screened from the preset symptoms according to the second correlation coefficient. The first and second target symptoms are then recommended to the patient user.
Of course, if the candidate symptom only includes the first candidate symptom, the target symptom to be recommended may be screened from the preset symptoms directly according to the first correlation coefficient between the first candidate symptom and each preset symptom.
It can be understood that a preset number of symptoms can be screened from preset symptoms according to the sequence of the correlation coefficients from high to low, if the screened symptoms include non-sign symptoms, the non-sign symptoms are filtered, and the obtained sign symptoms are recommended to a patient user as target symptoms.
In some embodiments, after recommending the target symptom to the user, the following steps may be further included:
and acquiring the user symptom re-input by the user aiming at the recommended target symptom.
The target symptom and the re-entered user symptom are transmitted to another user or a user who entered the user symptom.
In a practical application scenario, after the target symptom is recommended to the patient user, the user symptom re-input by the patient user for the recommended target symptom may be acquired, and then all the collected user symptoms input by the patient user are sent to the doctor user, so that the doctor user can diagnose the disease of the patient user.
In some embodiments, after target symptoms that need to be recommended to the user are obtained, the symptom category to which each target symptom belongs may be determined. Specifically, the target symptoms to be recommended to the user can be classified according to a clustering algorithm, and the label names of the classifications are determined according to the classification result. When recommending the user, please refer to fig. 2, the target symptom may be shown to the user under a column of the corresponding tag name.
In a first optional implementation manner, a correlation coefficient database may be pre-stored in the electronic device, where a correlation coefficient between preset symptoms is stored in the correlation database, and when the correlation coefficient between two symptoms needs to be determined, the correlation coefficient database may be queried, and the query and the retrieval of the correlation coefficient may be directly performed in the preset correlation coefficient database, so that the operation efficiency may be improved.
In a second alternative embodiment, the correlation coefficients between symptoms can be calculated in real time during the actual application process.
In any of the above embodiments, the correlation coefficient between two symptoms can be calculated in the following manner, and specific steps can be shown in fig. 3, including:
s31: and acquiring a correlation degree matrix.
Each element in the association degree matrix characterizes the association degree between the corresponding preset prescription and the corresponding preset symptom. For example, each row of the association matrix corresponds to a predetermined symptom, each column of the association matrix corresponds to a predetermined formula, and each element of the matrix can represent the association between the corresponding predetermined formula and the corresponding predetermined symptom.
Illustratively, each element in the association degree matrix is the association degree of a preset symptom relative to a preset prescription, which is calculated based on a preset medical record database; the medical record database comprises a plurality of medical record documents, and each medical record document comprises information of a plurality of preset symptoms and information of a preset prescription capable of treating the plurality of preset symptoms; the degree of association can be formulated
And (4) calculating.
The meaning of the parameters in the above formula is presented below.
R si,pj And the value of the corresponding element at the ith row and jth column position in the relevance degree matrix is represented.
si represents the ith pre-set symptom, pj represents the jth pre-set prescription.
n ij The number of medical record documents which simultaneously contain the jth preset prescription and the ith preset symptom in the medical record database is shown.
∑ k n kj And the total occurrence times or symptom category number of all preset symptoms in the same medical record document with the jth preset prescription in the medical record database is represented. For example, if the preset prescription X appears in only 2 medical record documents, and the 2 medical record documents respectively include a preset symptoms and b preset symptoms, and c overlapped preset symptoms exist between the 2 medical record documents, the total number of occurrences of all preset symptoms appearing in the same medical record document with the preset prescription X is a + b, and all preset symptoms appearing in the same medical record document with the preset prescription X appear in the same medical record document with the preset prescription XThe number of symptom categories of the preset symptoms is a + b-c.
∑ k n ki And the total occurrence times or the types of all the preset prescriptions in the medical record database, which are in the same medical record document with the ith preset symptom, are represented.
D represents the total occurrence frequency or the category number of all the preset prescriptions in the medical record database. The number of prescriptions is essentially the number of prescriptions that are preset.
e and Q are preset constants, e is a preset smoothing coefficient, and Q is a preset adjusting coefficient.
Illustratively, e may take the value 2 and Q may take the value 1.
After the degree of association between each predetermined prescription and each predetermined symptom is obtained, the degree of association matrix can be obtained.
S32: and performing singular value decomposition on the correlation degree matrix to obtain a characteristic vector matrix corresponding to each preset symptom.
Step S32 can be as follows
And carrying out singular value decomposition on the correlation degree matrix.
Wherein R is m*n And d represents the vector dimension of the decomposed prescription and the preset symptom, and the specific size of d can be set by a developer according to experience, such as 100. U shape m*d D-dimensional prescription eigenvector matrix, V, representing m prescriptions n*d A d-dimensional eigenvector matrix representing n preset symptoms. Matrix V n*d Each row vector of (a) represents a feature vector matrix corresponding to a predetermined symptom.
S33: and calculating the correlation coefficient between the preset symptoms according to the characteristic vector matrixes.
In step S33, the correlation coefficient between the preset symptoms may be calculated according to the cosine distance between the feature vector matrices, for example, the correlation coefficient between the preset symptoms may be calculated according to the following formula:
therein, Dis ij Represents a correlation coefficient, V, between the ith and jth preset symptoms ik A value, V, of a k-dimension of a eigenvector matrix corresponding to the ith preset symptom jk And representing the value of the feature vector matrix corresponding to the jth preset symptom in the kth dimension.
In some embodiments, after obtaining the correlation coefficient between the preset symptoms through step S33, the correlation coefficient may be stored in the correlation coefficient database.
Example two:
an embodiment of the present application provides a symptom recommendation device, please refer to fig. 4, including:
an obtaining module 501, configured to obtain user information; the user information includes user symptoms input by the user.
A first determination module 502 for determining candidate symptoms based on the user symptoms.
A second determining module 503, configured to determine a correlation coefficient between the candidate symptom and each preset symptom; the correlation coefficient is a coefficient obtained by performing singular value decomposition on the correlation degree matrix to obtain a characteristic vector matrix corresponding to each preset symptom and calculating based on each characteristic vector matrix; each element in the association degree matrix represents the association degree between the corresponding preset symptom and the corresponding preset prescription.
And a third determining module 504, which determines the target symptom from the preset symptoms according to the correlation coefficient.
And a recommending module 505 for recommending symptoms according to the target symptoms.
In an exemplary embodiment, the target symptom includes a sign symptom. The sign symptoms include at least one of symptoms related to body type, face condition, tongue condition, pulse condition, diet, sleep, spirit, menstrual discharge and defecation.
In an exemplary embodiment, the first determining module 502 is configured to determine a chief complaint symptom corresponding to a symptom of the user and to use the chief complaint symptom as the first candidate symptom; or, the last input symptom of the user symptoms is taken as the first candidate symptom.
In an exemplary embodiment, the first determination module 502 is configured to determine a second candidate symptom associated with the first candidate symptom.
In an exemplary embodiment, the first determining module 502 is configured to determine a fourth association coefficient between the first candidate symptom and each symptom of the user symptom except the first candidate symptom, determine a symptom corresponding to the fourth association coefficient that is greater than or equal to a preset association coefficient threshold as the candidate symptom to be determined, and filter out the candidate symptom to be determined corresponding to a maximum value of the fourth association coefficient from the candidate symptom to be determined as the second candidate symptom.
In an exemplary embodiment, the second determining module 503 is configured to determine a first correlation coefficient between the first candidate symptom and each preset symptom, determine a second correlation coefficient between the second candidate symptom and each preset symptom, and determine, for each preset symptom, a third correlation coefficient between the corresponding first correlation coefficient and the second correlation coefficient and the candidate symptom group; and the candidate symptom group is a symptom group consisting of a first candidate symptom and a second candidate symptom, and the target symptom to be recommended is screened from the preset symptoms according to the third correlation coefficient.
In an exemplary embodiment, the second determining module 503 is configured to query a preset association coefficient database for association coefficients between the candidate symptom and each preset symptom; the correlation coefficient database stores the correlation coefficients among the preset symptoms.
In an exemplary embodiment, the symptom recommendation apparatus may further include a calculation module, configured to obtain a correlation degree matrix, perform singular value decomposition on the correlation degree matrix to obtain a feature vector matrix corresponding to each preset symptom, perform calculation based on each feature vector matrix to obtain a correlation coefficient between each preset symptom, and store the correlation coefficient in a correlation coefficient database.
Each element in the association degree matrix is the association degree of the preset symptom relative to the preset prescription, which is calculated based on a preset medical record database; the medical record database comprises a plurality of medical record documents, and each medical record documentThe case file comprises information of a plurality of preset symptoms and information of preset prescriptions capable of treating the plurality of preset symptoms; the degree of association can be expressed by a formula
Calculating to obtain;
wherein R is si,pj Representing the values of corresponding elements at the ith row and jth column in the correlation degree matrix, si representing the ith preset symptom, pj representing the jth preset prescription, n ij Represents the number of medical record documents which simultaneously contain the jth preset prescription and the ith preset symptom in the medical record database, sigma k n kj Represents the total occurrence times or symptom category numbers of all preset symptoms appearing in the same medical record document with the jth preset prescription in the medical record database k n ki The total occurrence times or the types of all the preset prescriptions in the medical record database, which appear in the same medical record document with the ith preset symptom, are represented, and D represents the total occurrence times or the types of all the preset prescriptions in the medical record database; e and Q are preset constants.
In an exemplary embodiment, the obtaining module 501 is further configured to obtain the user symptom re-input by the user for the recommended target symptom after the recommending module recommends the target symptom to the user, and the target symptom recommending apparatus may further include a sending module configured to send all the user symptoms input by the user to another user.
It should be understood that, for the sake of brevity, the description of some embodiments is not repeated in this embodiment.
Example three:
based on the same inventive concept, an electronic device provided in an embodiment of the present application is shown in fig. 5, and includes a processor 501 and a memory 502, where a computer program is stored in the memory 502, and the processor 501 executes the computer program to implement the steps of the method in the first embodiment, which are not described again here.
It will be appreciated that the configuration shown in fig. 5 is merely illustrative and that the apparatus may also include more or fewer components than shown in fig. 5 or have a different configuration than shown in fig. 5.
The processor 501 may be an integrated circuit chip having signal processing capabilities. The processor 501 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. Which may implement or perform the various methods, steps, and logic blocks disclosed in embodiments of the present application.
The memory 502 may include, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read Only Memory (PROM), erasable read only memory (EPROM), electrically erasable read only memory (EEPROM), and the like.
The present embodiment further provides a computer-readable storage medium, such as a floppy disk, an optical disk, a hard disk, a flash memory, a U-disk, a Secure Digital (SD) card, a multimedia data (MMC) card, etc., where one or more programs for implementing the above steps are stored, and the one or more programs can be executed by one or more processors to implement the steps of the method in the above embodiments, which are not described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method of symptom recommendation, comprising:
acquiring user information; the user information comprises user symptoms input by a user;
determining candidate symptoms according to the user symptoms;
determining a correlation coefficient between the candidate symptom and each preset symptom; the correlation coefficient is a coefficient obtained by performing singular value decomposition on the correlation degree matrix to obtain a characteristic vector matrix corresponding to each preset symptom and calculating based on each characteristic vector matrix; each element in the association degree matrix represents the association degree between the corresponding preset symptom and the corresponding preset prescription;
determining a target symptom from the preset symptoms according to the correlation coefficient;
and recommending symptoms according to the target symptoms.
2. The symptom recommendation method of claim 1, wherein the target symptom comprises a sign symptom.
3. The symptom recommendation method of claim 1, wherein the candidate symptom comprises a first candidate symptom; the determining candidate symptoms from the user symptoms comprises:
determining a chief complaint symptom corresponding to the user symptom, and taking the chief complaint symptom as the first candidate symptom;
or the like, or, alternatively,
and taking the last input symptom of the user symptoms as the first candidate symptom.
4. The symptom recommendation method of claim 3, wherein the candidate symptom further comprises a second candidate symptom; the determining candidate symptoms from the user symptoms comprises:
a second candidate symptom associated with the first candidate symptom is determined.
5. The symptom recommendation method of claim 4, wherein the determining the correlation coefficient between the candidate symptom and each preset symptom comprises:
determining a first correlation coefficient between the first candidate symptom and each of the preset symptoms, and determining a second correlation coefficient between the second candidate symptom and each of the preset symptoms;
the determining of the target symptom to be recommended from the preset symptoms according to the association coefficient includes:
for each preset symptom, determining a third association coefficient between the preset symptom and a candidate symptom group according to the corresponding first association coefficient and the second association coefficient; the candidate symptom group is a symptom group consisting of the first candidate symptom and the second candidate symptom;
and screening out target symptoms needing to be recommended from the preset symptoms according to the third correlation coefficient.
6. The symptom recommendation method of claim 4, wherein said determining a second candidate symptom associated with the first candidate symptom comprises:
determining a fourth correlation coefficient between the first candidate symptom and each of the user symptoms other than the first candidate symptom;
determining symptoms corresponding to a fourth correlation coefficient which is greater than or equal to a preset correlation coefficient threshold value as candidate symptoms to be determined;
and screening out the candidate symptom to be determined corresponding to the maximum value of the fourth correlation coefficient from the candidate symptoms to be determined as a second candidate symptom.
7. The symptom recommendation method of claim 1, wherein the determining the correlation coefficient between the candidate symptom and each preset symptom comprises:
inquiring the association coefficient between the candidate symptom and each preset symptom from a preset association coefficient database; and the correlation coefficient database stores the correlation coefficient among the preset symptoms.
8. The symptom recommendation method according to any one of claims 1 to 7, wherein each element in the correlation degree matrix is a correlation degree of the preset symptom with respect to the preset prescription calculated based on a preset medical record database; the medical record database comprises a plurality of medical record documents, and each medical record document comprises information of a plurality of preset symptoms and information of a preset prescription capable of treating the preset symptoms; the degree of association is expressed by a formula
Calculating to obtain;
wherein R is si,pj Representing the values of corresponding elements at the ith row and jth column in the correlation degree matrix, si representing the ith preset symptom, pj representing the jth preset prescription, n ij Represents the number of medical record documents which simultaneously contain the jth preset prescription and the ith preset symptom in the medical record database, sigma k n kj Represents the total occurrence times or symptom category numbers of all preset symptoms appearing in the same medical record document with the jth preset prescription in the medical record database k n ki The total occurrence times or the types of all the preset prescriptions in the medical record database, which appear in the same medical record document with the ith preset symptom, are represented, and D represents the total occurrence times or the types of all the preset prescriptions in the medical record database; e and Q are preset constants.
9. An electronic device, comprising a processor and a memory, the memory having stored therein a computer program, the processor executing the computer program to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by at least one processor, implements the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210712343.5A CN115101193A (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method and device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210712343.5A CN115101193A (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method and device and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115101193A true CN115101193A (en) | 2022-09-23 |
Family
ID=83292369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210712343.5A Pending CN115101193A (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method and device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115101193A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115719640A (en) * | 2022-11-02 | 2023-02-28 | 联仁健康医疗大数据科技股份有限公司 | System, device, electronic equipment and storage medium for recognizing primary and secondary symptoms of traditional Chinese medicine |
-
2022
- 2022-06-22 CN CN202210712343.5A patent/CN115101193A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115719640A (en) * | 2022-11-02 | 2023-02-28 | 联仁健康医疗大数据科技股份有限公司 | System, device, electronic equipment and storage medium for recognizing primary and secondary symptoms of traditional Chinese medicine |
| CN115719640B (en) * | 2022-11-02 | 2023-08-08 | 联仁健康医疗大数据科技股份有限公司 | Chinese medicine primary and secondary symptom recognition system, device, electronic equipment and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110910976A (en) | Medical record detection method, device, equipment and storage medium | |
| CN112037880A (en) | Medication recommendation method, device, equipment and storage medium | |
| CN110880361A (en) | Personalized accurate medication recommendation method and device | |
| CN110299209B (en) | Similar medical record searching method, device and equipment and readable storage medium | |
| CN113724848A (en) | Medical resource recommendation method, device, server and medium based on artificial intelligence | |
| CN112259245B (en) | Method, device, equipment and computer readable storage medium for determining items to be checked | |
| CN116386869B (en) | Disease critical degree assessment method based on multiple variables | |
| CN109840280B (en) | Text classification method and device and computer readable storage medium | |
| CN112151141A (en) | Medical data processing method, device, computer equipment and storage medium | |
| CN108492886B (en) | Minimally invasive surgery similar case recommendation method, device, equipment and medium | |
| CN114065856B (en) | Doctor recommendation method, device and equipment based on doctor portrait and storage medium | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| CN114783580B (en) | Medical data quality evaluation method and system | |
| CN113724858A (en) | Artificial intelligence-based disease examination item recommendation device, method and apparatus | |
| CN115101193A (en) | Symptom recommendation method and device and computer-readable storage medium | |
| CN115512817A (en) | Doctor recommendation method and device based on child telemedicine | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN109509102B (en) | Claims settlement decision method, device, computer equipment and storage medium | |
| CN113241193A (en) | Drug recommendation model training method, recommendation method, device, equipment and medium | |
| Viscaino et al. | Computer-aided ear diagnosis system based on CNN-LSTM hybrid learning framework for video otoscopy examination | |
| CN110648754A (en) | Department recommendation method, device and equipment | |
| US20110218823A1 (en) | Method and System for Determining Precursors of Health Abnormalities from Processing Medical Records | |
| Ketpupong et al. | Applying text mining for classifying disease from symptoms | |
| CN113436746B (en) | Medication recommendation method, device, equipment and storage medium based on sorting algorithm |
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 |