CN115101192A - Symptom recommendation method, device and equipment based on prescription and storage medium - Google Patents
Symptom recommendation method, device and equipment based on prescription and storage medium Download PDFInfo
- Publication number
- CN115101192A CN115101192A CN202210710939.1A CN202210710939A CN115101192A CN 115101192 A CN115101192 A CN 115101192A CN 202210710939 A CN202210710939 A CN 202210710939A CN 115101192 A CN115101192 A CN 115101192A
- Authority
- CN
- China
- Prior art keywords
- prescription
- symptoms
- symptom
- user
- preset
- 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.)
- Granted
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
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 symptom recommendation method, device, equipment and storage medium based on the prescription can intelligently recommend symptoms to a patient user, so that the patient user can further improve the discomfort information of the patient user based on a recommendation result, repeated intervention of a doctor is not needed, and diagnosis and treatment efficiency is improved; in addition, because the target prescription is a prescription capable of treating the user symptoms, recommended symptoms related to the input user symptoms can be determined according to the target prescription, namely, symptoms meeting the current body discomfort condition of the user can be deduced for the user to check, the recommended result is reliable, more comprehensive symptom information can be collected, and the accuracy of diagnosis and treatment results can be improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a symptom recommendation method, device, equipment and storage medium based on prescriptions.
Background
The inquiry of the patient is an important work of the doctor, and the doctor can only take the medicine according to symptoms if all symptoms of the patient are accurately acquired. With the vigorous development of big data and artificial intelligence technology, big data platforms have advanced to the actual operation stage. The method is a technical mode suitable for the current big data service, and is expected to provide a solution for the problem of the traditional Chinese and western medical inquiry at present.
During the inquiry process, patients sometimes have difficulty in accurately describing their symptoms, or may miss some symptoms that are less uncomfortable. For example, when a patient initiates an inquiry request through an online inquiry platform, the patient may miss some symptoms with less discomfort because the patient expresses the symptoms with higher discomfort, which may affect the diagnosis and treatment of the doctor. If the doctor actively makes an inquiry, a large amount of medical time is occupied, and a better online diagnosis and treatment experience cannot be provided for the doctor user and the patient user. Therefore, it is necessary to intelligently recommend symptoms to a patient in order to prompt the patient for symptoms.
Disclosure of Invention
An object of the embodiments of the present application is to provide a new prescription-based symptom recommendation method, apparatus, device, and storage medium, so as to solve the problem in the prior art that diagnosis and treatment efficiency is low due to the fact that a user cannot be intelligently recommended symptoms.
The embodiment of the application provides a symptom recommendation method based on prescriptions, which comprises the following steps:
acquiring user information; the user information comprises user symptoms input by a user;
identifying a target formula for treating the user's symptoms;
determining recommended symptoms based on the target formula;
recommending the recommended symptom to the user.
In the implementation process, the symptom recommendation can be intelligently carried out on the patient user, so that the patient user can further improve the discomfort information of the patient user based on the recommendation result, a doctor does not need to intervene for many times, and the diagnosis and treatment efficiency is improved; in addition, because the target prescription is a prescription capable of treating the symptoms of the user, the recommended symptoms related to the input symptoms of the user can be determined according to the target prescription, namely, the symptoms meeting the current body discomfort condition of the user can be pushed out for the user to self-check, the recommended result is reliable, so that more comprehensive symptom information can be collected, and the accuracy of the diagnosis and treatment result can be improved.
Further, the target prescriptions identified to treat the user's symptoms include:
and determining a target prescription capable of treating the symptoms of the user based on the trained prescription recommendation model.
In the implementation process, the target prescription is determined according to the trained prescription recommendation model, so that the reliability of the determined target prescription can be improved, and the determined target prescription can treat the user symptoms.
Further, the prescription recommendation model is a linear model obtained by training based on a plurality of training sample data; each training sample data comprises information of a plurality of user symptoms and information of prescriptions for treating the plurality of user symptoms.
In the implementation process, the target formula is determined through the linear model, the model training mode is simple, and the output result of the model is reliable.
Further, the linear model is: p is j ＝W j0 +W j1 S 1 +W j2 S 2 +W j3 S 3 +…+W jn S n ；
Wherein, W ji Represents the correlation coefficient between the jth preset prescription and the ith preset symptom, S i Indicates the ith predetermined symptom, P j Represents the evaluation score of the jth preset prescription, n represents the total number of the preset symptoms, m represents the total number of the preset prescriptions, W j0 Representing the preset intercept of a linear equation corresponding to the jth preset prescription, wherein the target prescription is a prescription in a prescription set consisting of all the preset prescriptions;
the method for determining a target prescription capable of treating the user symptoms according to the user symptoms and the trained prescription recommendation model comprises the following steps:
inputting the user symptoms into the linear model to obtain evaluation scores corresponding to the preset prescriptions respectively;
and determining a target prescription from the prescription set according to the evaluation score.
In the implementation process, each preset prescription is used as a dependent variable of the linear model, each preset symptom is used as an independent variable of the linear model, the evaluation score corresponding to each preset prescription can be obtained according to the input user symptom, the target prescription is determined from the preset prescriptions according to the evaluation score, namely, the target prescription can be further screened according to the output result of the linear model, and the reliability of the finally determined target prescription is improved.
Further, the determining recommended symptoms according to the target prescription includes:
determining a correlation coefficient between each of the target prescriptions and each of the preset symptoms;
and determining recommended symptoms from a symptom set consisting of the preset symptoms according to the correlation coefficient.
In the implementation process, the recommended symptom is determined from the preset symptoms according to the correlation coefficient between the target prescription and each preset symptom, so that the determined recommended symptom is related to the target prescription as far as possible, the recommended symptom is further related to the user symptom input by the user, the recommended symptom is more consistent with the current body discomfort condition of the user, and the symptom prompting accuracy is improved.
Further, the determining a correlation coefficient between each target prescription and each preset symptom comprises:
and obtaining a correlation coefficient between each target prescription and each preset symptom from the linear model.
In the implementation process, the target prescription is determined based on the linear model, and then the recommended symptom related to the target prescription is determined based on the correlation coefficient in the linear model, and the target prescription is determined based on the same linear model, so that the recommended symptom is determined, and the obtained recommended result is more accurate; in addition, since the correlation coefficient can be directly obtained from the linear model, other resource storage or calculation of the correlation coefficient is not required.
Further, the determining, according to the correlation coefficient, a recommended symptom from a symptom set composed of each of the preset symptoms includes:
and aiming at each target prescription, according to the sequence of the correlation coefficient between the target prescription and each preset symptom from large to small, screening out symptoms meeting the preset number from the symptom set, and determining recommended symptoms from the screened symptoms.
In the implementation process, because the recommended symptoms are selected from the screened symptoms, each determined recommended symptom has high relevance with the corresponding target prescription, so that the recommended symptoms have high relevance with the input user symptoms, and the reliability of the recommended result is further improved.
The embodiment of the application also provides a symptom recommendation device based on a prescription, which comprises:
the acquisition module is used for acquiring user information; the user information comprises user symptoms input by a user;
a first determination module for determining a target formula for treating the user's symptoms;
a second determination module for determining recommended symptoms based on the target prescription;
and the recommending module is used for recommending the recommended symptom to the user.
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.
An embodiment of the present application further provides 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
In order 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 flow chart of a method for prescription-based symptom recommendation in accordance with an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a user symptom recommendation according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a symptom recommendation device based on prescriptions provided in the second embodiment of the present application;
fig. 4 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 described in further 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 do not limit the invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to 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 such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory 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 in detail a prescription-based symptom recommendation method, apparatus, device, and storage medium.
The first embodiment is as follows:
in order to solve the problem that diagnosis and treatment accuracy is affected due to incomplete description of symptoms of a patient in the prior art, embodiments of the present application provide a method for recommending symptoms based on a prescription.
Referring to fig. 1, a method provided in an embodiment of the present application may include the following steps:
s101: acquiring user information; the user information includes user symptoms entered by the user.
The user in steps S101-S104 is typically a patient user, for example, the patient himself or herself, or a person who is familiar with the condition of the patient, such as a family member of the patient. The user can input user information through an application program on the electronic equipment according to the actual situation of the user. The user information includes user symptoms, and may also include information that can assist a doctor in diagnosis and treatment, such as age and sex of the user.
S102: a target formula is determined that can treat the user's symptoms.
In step S102, a target formula for treating the symptom of the user may be determined based on the trained formula recommendation model.
The prescription recommendation model in the embodiment of the application is a model obtained by training based on a plurality of training sample data. Each training sample data can comprise user information and information of prescriptions for treating a plurality of user symptoms in the user information, the user information is used as the input of a model, and the information of the prescriptions is used as the output of the model. The prescription recommendation model can be a model obtained by training based on a random forest model, an XGboost model and other nonlinear models or other linear models.
In a first alternative embodiment, the obtained user information is input into the prescription recommendation model, which may directly output a target prescription for the user information that may treat the corresponding user symptom.
In a second optional implementation manner, the obtained user information is input into the prescription recommendation model, the model may output corresponding evaluation scores for each preset prescription, and at this time, a target prescription may be screened from a prescription set composed of preset prescriptions according to the evaluation scores respectively corresponding to the preset prescriptions.
The second alternative embodiment described above will be described in detail below.
The linear model in this embodiment may be:
P j ＝W j0 +W j1 S 1 +W j2 S 2 +W j3 S 3 +…+W jn S n 。
wherein, W ji Represents the correlation coefficient between the jth preset prescription and the ith preset symptom, S i Indicates the ith predetermined symptom, P j Represents the evaluation score of the j-th preset prescription, i is 1,2 … n, j is 1 … m, n represents the total number of preset symptoms, m represents the total number of preset prescriptions, W j0 And the preset intercept of the linear equation corresponding to the jth preset prescription is shown, and the target prescription is a prescription in a prescription set consisting of all the preset prescriptions.
At this time, in step S102, the obtained user symptoms may be input into the linear model to obtain evaluation scores corresponding to the preset prescriptions, and then the target prescription may be determined from the prescription set according to the evaluation scores. The evaluation score in the embodiment of the application represents the relevance between the corresponding prescription and the user symptom input by the user, so that a preset number of prescriptions can be screened out from the prescription set as target prescriptions according to the sequence of the evaluation score from high to low, for example, the prescriptions ranked in the top five can be screened out as target prescriptions. Prescriptions with an evaluation score greater than or equal to a preset evaluation score threshold value can also be screened out as target prescriptions.
In the process of training the linear model, a loss function may be determined based on a least square method, and the loss function may be:
wherein the content of the first and second substances,
represents the true value, P, of the jth predetermined prescription j The linear regression value of the jth preset prescription calculated by the model, i.e., the evaluation score, is represented.
S103: the recommended symptoms are determined according to the target formula.
In a first alternative embodiment, in step S103, a correlation coefficient between each target formula and each preset symptom may be determined, and then a recommended symptom may be determined from a symptom set consisting of each preset symptom according to the correlation coefficient.
In this embodiment, for each target prescription, according to the order of the correlation coefficient between the target prescription and each preset symptom from large to small, symptoms satisfying a preset number are screened from the symptom set, and a recommended symptom is determined from the screened symptoms. Specifically, the selected symptoms may be filtered to obtain the final recommended symptoms. For example, the user symptoms that the user has input may be filtered, the symptoms that are mutually exclusive with the user symptoms that the user has input may be filtered, the symptoms that do not belong to the age group in which the user is located may be filtered, the symptoms that do not belong to the gender of the user may be filtered, and the positive symptoms corresponding to the negative symptoms among the user symptoms that have been input may be filtered.
In this embodiment, corresponding weight values may be assigned to the target prescriptions according to the descending order of the evaluation scores, and the numbers of the symptoms to be screened for recommendation corresponding to different weight values are different, that is, the preset number values corresponding to different weight values are different. For example, the target formula ranked first in the evaluation score has a high correlation with the user symptom input by the user, and the corresponding preset quantitative value may be larger than the preset quantitative values corresponding to other target formulas.
In the first example of the first alternative embodiment, the correlation coefficient between each target prescription and each preset symptom may be directly obtained from the linear model. For example, it can be directly selected fromObtaining corresponding W from the linear model ji As a correlation coefficient between the target formula and the predetermined symptoms.
According to the scheme provided by the example, the linear model is used twice, the target prescription is determined based on the linear model, and then the recommended symptom related to the target prescription is determined based on the correlation coefficient in the linear model; in addition, since the correlation coefficient can be directly obtained from the linear model, other resource storage or calculation of the correlation coefficient is not needed, and resource consumption in the electronic equipment can be saved.
In a second example of the first alternative embodiment, the recommended symptom corresponding to the target formula may be determined according to the target formula and the trained symptom recommendation model. The symptom recommendation model is a model obtained by training based on a plurality of training sample data. Each training sample data may include information about a plurality of prescriptions and symptoms to which the prescriptions are directed. Training sample data can be obtained from a medical record database, the medical record database comprises a large number of medical record documents, and each medical record document records the symptoms of a user and a prescription for treating the symptoms of the user. When the model is trained, the prescription is used as the model input, and the symptom is used as the model output. The symptom recommendation model in this example may be a model obtained by training using a different basic model from the prescription recommendation model, for example, the prescription recommendation model is obtained by training using a linear model, and the non-linear model may be used for training to obtain the symptom recommendation model, that is, a target prescription is obtained based on the prescription recommendation model, then the recommended symptom related to the target prescription is determined based on the symptom recommendation model, and the final recommended symptom is output through a diversified model, so that the obtained result is more accurate, reliable and comprehensive.
In a second alternative embodiment, the target formula may be regarded as a target formula set in step S103, and then for each preset symptom, a correlation coefficient between the target formula and the target formula set is determined, and then a recommended symptom is determined from a symptom set consisting of the preset symptoms according to the correlation coefficient. Specifically, the target prescription may be input into a symptom recommendation linear model obtained through training, where the symptom recommendation linear model is a model obtained through training based on a linear model. The target prescription is input into the symptom recommendation linear model to obtain evaluation scores corresponding to the preset symptoms respectively, the evaluation scores are used as correlation coefficients between the corresponding preset symptoms and the target prescription set, and the recommended symptoms are determined from the symptom set consisting of the preset symptoms according to the correlation coefficients. For example, symptoms satisfying a predetermined number may be screened out in the order of high to low correlation coefficients, and recommended symptoms may be determined from the screened-out symptoms.
S104: recommending the recommended symptom to the user.
After recommending the recommended symptom to the user, a new user symptom re-input by the user based on the recommended symptom may be received, and then the symptom information confirmed by the user may be transmitted to another user. For example, the information may be pushed to a doctor through an application program, and the doctor may make a diagnosis according to the information input by the user.
It should be noted that some doctors with less skilled business skills, such as practice stage doctors, may not be skilled in guiding patients to describe all their symptoms during the course of making a diagnosis. Therefore, in step S104, the recommended symptom may be recommended to the doctor user, and the doctor may inquire about the patient according to the recommended symptom, thereby improving the diagnosis efficiency of the doctor.
After the recommended symptoms needing to be recommended to the user are determined, the recommended symptoms can be randomly sampled, and the recommended symptoms are divided into two groups according to whether the sampled recommended symptoms are sign information or not. One group of labels is named "associated signs" and contains all the sign symptoms in the recommended symptoms, and the other group of labels is named "associated symptoms" and contains all the non-sign symptoms in the symptoms. When recommending to the user, the labels of "relevant signs" and "relevant symptoms" and their respective symptoms are pushed out, and in particular, see fig. 2.
The physical sign symptoms in the embodiment of the application refer to symptoms which can be objectively detected by others, are objectively existing symptoms and do not change along 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 an examination means by an indirect inquiry such as the naked eye or touch. For example, for symptoms related to tongue, face, pulse, and the like, a developer may set a corresponding label for a preset symptom, for example, a "sign" label may be set for a symptom related to body type to indicate that the symptom belongs to a sign symptom, and after determining the recommended symptom, it may be determined whether the corresponding recommended symptom is a sign symptom or a non-sign symptom according to a label condition corresponding to the recommended symptom.
According to the prescription-based symptom recommendation method provided by the embodiment of the application, the symptoms with high relevance to the recommendation result of the prescription recommendation model can be recommended to the user, the user can be guided to confirm whether the recommended symptoms exist, the comprehensiveness of the collected symptoms can be improved, and the accuracy of diagnosis and treatment results can be further improved.
The second embodiment:
the present application provides a symptom recommendation device based on a prescription, as shown in fig. 3, including:
an obtaining module 301, configured to obtain user information; the user information includes user symptoms entered by the user.
A first determination module 302 for determining a target formula that can treat the user's symptoms.
A second determination module 303 for determining recommended symptoms based on the target formula.
And a recommending module 304 for recommending the recommended symptom to the user.
In an exemplary embodiment, the prescription recommendation model is a linear model trained based on a plurality of training sample data; each training sample data includes information of a plurality of user symptoms and information of prescriptions for treating the plurality of user symptoms.
In an exemplary embodiment, the linear model is:
P j ＝W j0 +W j1 S 1 +W j2 S 2 +W j3 S 3 +…+W jn S n ；
wherein, W ji Represents the correlation coefficient between the jth preset prescription and the ith preset symptom, S i Indicates the ith predetermined symptom, P j Denotes an evaluation score of the jth preset prescription, i is 1,2 … n, j is 1 … m, n denotes the total number of preset symptoms, m denotes the total number of preset prescriptions, W denotes the total number of preset prescriptions j0 The preset intercept of the linear equation corresponding to the jth preset prescription is shown, and the target prescription is a prescription in a prescription set consisting of the preset prescriptions.
The first determining module 302 is configured to input the user symptoms into the linear model to obtain evaluation scores corresponding to the predetermined prescriptions respectively; and determining a target prescription from the prescription set according to the evaluation score.
In an exemplary embodiment, the second determining module 303 is configured to determine a correlation coefficient between each target formula and each preset symptom, and determine a recommended symptom from a symptom set composed of each preset symptom according to the correlation coefficient.
In the exemplary embodiment, second determination module 303 is configured to obtain the correlation coefficient between each target formula and each preset symptom from the linear model.
In an exemplary embodiment, the second determining module 303 is configured to, for each target prescription, screen out symptoms satisfying a preset number from the symptom set according to a descending order of a correlation coefficient between the target prescription and each preset symptom, and determine a recommended symptom from the screened symptoms.
In the exemplary embodiment, the second determining module 303 is configured to treat the target formula as a target formula set, determine a correlation coefficient between the target formula set and each preset symptom, and determine a recommended symptom from a symptom set consisting of the preset symptoms according to the correlation coefficient.
It should be understood that, for the sake of brevity, the contents described in some embodiments are not repeated in this embodiment.
Example three:
based on the same inventive concept, an electronic device provided in the embodiments of the present application is shown in fig. 4, and includes a processor 401 and a memory 402, where the memory 402 stores a computer program, and the processor 401 executes the computer program to implement the steps of the method in the first embodiment, which are not described herein again.
It will be appreciated that the configuration shown in fig. 4 is merely illustrative and that the apparatus may also include more or fewer components than shown in fig. 4, or have a different configuration than shown in fig. 4.
The processor 401 may be an integrated circuit chip having signal processing capabilities. The processor 401 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 the embodiments of the present application.
The memory 402 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 in the computer-readable storage medium, 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 is 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 prescription-based symptom recommendation method, comprising:
acquiring user information; the user information comprises user symptoms input by a user;
identifying a target formula for treating the user's symptoms;
determining recommended symptoms based on the target formula;
recommending the recommended symptom to the user.
2. The prescription-based symptom recommendation method of claim 1, wherein the identifying a target prescription that can treat the symptom of the user comprises:
and determining a target prescription capable of treating the symptoms of the user based on the trained prescription recommendation model.
3. The prescription-based symptom recommendation method of claim 2, wherein the prescription recommendation model is a linear model trained based on a plurality of training sample data; each training sample data comprises information of a plurality of user symptoms and information of prescriptions for treating the plurality of user symptoms.
4. The prescription-based symptom recommendation method of claim 3, wherein the linear model is: p j ＝W j0 +W j1 S 1 +W j2 S 2 +W j3 S 3 +…+W jn S n ；
Wherein, W ji Represents the correlation coefficient between the jth preset prescription and the ith preset symptom, S i Indicates the ith predetermined symptom, P j Denotes an evaluation score of the jth preset prescription, i is 1,2 … n, j is 1 … m, n denotes the total number of the preset symptoms, m denotes the total number of the preset prescriptions, W denotes the total number of the preset prescriptions j0 Representing the preset intercept of a linear equation corresponding to the jth preset prescription, wherein the target prescription is a prescription in a prescription set consisting of all the preset prescriptions;
the target prescriptions that can treat the user's symptoms are determined based on the trained prescription recommendation model, including:
inputting the user symptoms into the linear model to obtain evaluation scores corresponding to the preset prescriptions respectively;
and determining a target prescription from the prescription set according to the evaluation score.
5. The prescription-based symptom recommendation method of claim 4, wherein said determining recommended symptoms based on the target prescription comprises:
determining a correlation coefficient between each of the target prescriptions and each of the predetermined symptoms;
and determining recommended symptoms from a symptom set consisting of each preset symptom according to the association coefficient.
6. The prescription-based symptom recommendation method of claim 5, wherein said determining a correlation coefficient between each of said target prescriptions and each of said predetermined symptoms comprises:
and obtaining a correlation coefficient between each target prescription and each preset symptom from the linear model.
7. A prescription-based symptom recommendation method as claimed in claim 5, wherein said determining recommended symptoms from a set of symptoms consisting of each of said predetermined symptoms according to said correlation coefficients comprises:
and aiming at each target prescription, screening symptoms meeting a preset number from the symptom set according to the sequence of the correlation coefficient between each target prescription and each preset symptom from large to small, and determining recommended symptoms from the screened symptoms.
8. A prescription-based symptom recommendation device, comprising:
the acquisition module is used for acquiring user information; the user information comprises user symptoms input by a user;
a first determination module for determining a target formula for treating the user's symptoms;
a second determination module for determining recommended symptoms based on the target prescription;
and the recommending module is used for recommending the recommended symptom to the user.
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 1-7.
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 of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210710939.1A CN115101192B (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method, device, equipment and storage medium based on prescription |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210710939.1A CN115101192B (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method, device, equipment and storage medium based on prescription |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115101192A true CN115101192A (en) | 2022-09-23 |
| CN115101192B CN115101192B (en) | 2023-09-01 |
Family
ID=83292804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210710939.1A Active CN115101192B (en) | 2022-06-22 | 2022-06-22 | Symptom recommendation method, device, equipment and storage medium based on prescription |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115101192B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200069A (en) * | 2014-08-13 | 2014-12-10 | 周晋 | Drug use recommendation system and method based on symptom analysis and machine learning |
| CN112015917A (en) * | 2020-09-07 | 2020-12-01 | 平安科技（深圳）有限公司 | Data processing method and device based on knowledge graph and computer equipment |
| CN112863694A (en) * | 2021-02-08 | 2021-05-28 | 浙江中医药大学 | Information recommendation method and device |
| CN113096797A (en) * | 2021-04-16 | 2021-07-09 | 杭州卓健信息科技有限公司 | Intelligent terminal based inquiry system |
| CN113268511A (en) * | 2021-04-21 | 2021-08-17 | 广东易生活信息科技有限公司 | Ancient book and ancient prescription based traditional Chinese medicine prescription recommendation method and system |
| CN113488157A (en) * | 2021-07-30 | 2021-10-08 | 卫宁健康科技集团股份有限公司 | Intelligent diagnosis guide processing method and device, electronic equipment and storage medium |
| CN114416967A (en) * | 2022-01-26 | 2022-04-29 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for intelligently recommending doctors and storage medium |
-
2022
- 2022-06-22 CN CN202210710939.1A patent/CN115101192B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200069A (en) * | 2014-08-13 | 2014-12-10 | 周晋 | Drug use recommendation system and method based on symptom analysis and machine learning |
| CN112015917A (en) * | 2020-09-07 | 2020-12-01 | 平安科技（深圳）有限公司 | Data processing method and device based on knowledge graph and computer equipment |
| CN112863694A (en) * | 2021-02-08 | 2021-05-28 | 浙江中医药大学 | Information recommendation method and device |
| CN113096797A (en) * | 2021-04-16 | 2021-07-09 | 杭州卓健信息科技有限公司 | Intelligent terminal based inquiry system |
| CN113268511A (en) * | 2021-04-21 | 2021-08-17 | 广东易生活信息科技有限公司 | Ancient book and ancient prescription based traditional Chinese medicine prescription recommendation method and system |
| CN113488157A (en) * | 2021-07-30 | 2021-10-08 | 卫宁健康科技集团股份有限公司 | Intelligent diagnosis guide processing method and device, electronic equipment and storage medium |
| CN114416967A (en) * | 2022-01-26 | 2022-04-29 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for intelligently recommending doctors and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115101192B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11626195B2 (en) | Labeling medical scans via prompt decision trees | |
| US8073713B2 (en) | Method and system for managing medical professionals | |
| KR102237449B1 (en) | Method, server and program of learning a patient diagnosis | |
| US11923094B2 (en) | Monitoring predictive models | |
| KR20170061222A (en) | The method for prediction health data value through generation of health data pattern and the apparatus thereof | |
| US20170316180A1 (en) | Behavior prediction apparatus, behavior prediction apparatus controlling method, and behavior prediction apparatus controlling program | |
| CN112216361A (en) | Follow-up plan list generation method, device, terminal and medium based on artificial intelligence | |
| Halldorsson et al. | A clinical decision support system for the diagnosis, fracture risks and treatment of osteoporosis | |
| CN111933237A (en) | Chronic disease processing method and device and related equipment | |
| CN108492886B (en) | Minimally invasive surgery similar case recommendation method, device, equipment and medium | |
| CN113707253A (en) | Medical scheme recommendation method, device, equipment and medium | |
| US20200286599A1 (en) | Experience Engine-Method and Apparatus of Learning from Similar Patients | |
| CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN111192691A (en) | Method and device for determining medical evaluation table, readable medium and electronic equipment | |
| CN112435745A (en) | Consultation strategy recommendation method and device, electronic equipment and storage medium | |
| CN115101193A (en) | Symptom recommendation method and device and computer-readable storage medium | |
| CN115101192B (en) | Symptom recommendation method, device, equipment and storage medium based on prescription | |
| CN115346634A (en) | Physical examination report interpretation prediction method and system, electronic equipment and storage medium | |
| CN114420257A (en) | Traditional Chinese medicine auxiliary diagnosis and treatment method, system, equipment and storage medium | |
| Cheema et al. | The effectiveness of post‐professional physical therapist training in the treatment of chronic low back pain using a propensity score approach with machine learning | |
| US20230253100A1 (en) | Machine learning model to evaluate healthcare facilities | |
| CN115101194A (en) | Symptom pushing method, device and equipment with label and storage medium | |
| EP2685407A1 (en) | Computer system, method and program to quantify quality of service provision | |
| Eguia et al. | Using Natural Language and Health Ontologies in Hope Recommender System: Evaluation of Use in Primary 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |