CN111914174A - Medical information recommendation method and system - Google Patents
Medical information recommendation method and system Download PDFInfo
- Publication number
- CN111914174A CN111914174A CN202010787111.7A CN202010787111A CN111914174A CN 111914174 A CN111914174 A CN 111914174A CN 202010787111 A CN202010787111 A CN 202010787111A CN 111914174 A CN111914174 A CN 111914174A
- Authority
- CN
- China
- Prior art keywords
- medical
- user
- data
- grade
- information
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The application discloses a medical information recommendation method and system, wherein the recommendation method comprises the following steps: acquiring medical information data to be recommended; determining a medical category and a grade of the medical information data; searching a matched target user according to the medical category and the grade of the medical information data; recommending the medical information data to the matched target user. According to the method and the device, the data information of the medical categories of the corresponding levels can be recommended according to the cognitive level of the user in each medical category, so that the medical information recommendation with high accuracy and high fitting degree is realized.
Description
Technical Field
The present application relates to the field of information recommendation, and in particular, to a method and a system for recommending medical information.
Background
In a medical professional website, we can browse a large variety of categories of medical information. Since medical information data is professional-type data information, the medical information data is not the same as ordinary entertainment news, the medical information often relates to medical professional terms, or research and development tests in a certain medical field, so the medical information data is not always popular and easy to understand, and many professional types are included in the medical field, even if different medical information data in the same professional field are different in difficulty, and similarly, the cognitive level of audiences of medical websites is uneven, if recommendation is performed only according to the interests and hobbies of users, the medical information recommended to the users cannot be understood and unknown by the users, so that the user experience is greatly influenced, and the medical information is not beneficial to the progress and learning of the users in the aspect.
Disclosure of Invention
In order to solve the technical problem, the application provides a medical information recommendation method and system, which can perform accurate recommendation according to the cognitive level of a user. Specifically, the technical scheme of the application is as follows:
in one aspect, the application discloses a medical information recommendation method, including: acquiring medical information data to be recommended; determining a medical category and a grade of the medical information data; searching a matched target user according to the medical category and the grade of the medical information data; recommending the medical information data to the matched target user.
Preferably, the medical information recommendation method further includes: acquiring medical categories and corresponding levels in which users are interested; the method specifically comprises the following steps: defining a cognitive grade type of a user; acquiring basic information, historical behavior data and research data of a user; establishing a grade analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field; and acquiring the medical categories and corresponding cognitive levels of the users interested by the users through the level analysis model according to the basic information, the historical behavior data and the research data of the users.
Preferably, the medical categories and corresponding cognitive levels of the users interested are obtained through the level analysis model according to the basic information, the historical behavior data and the research data of the users; the method specifically comprises the following steps: determining medical categories which are interested by the user according to historical behavior data and/or basic information of the user, and taking the medical categories as target medical categories; calling medical research and assessment data of the target medical category, and sending the medical research and assessment data to the user; receiving the medical research and assessment data fed back by the user, and determining assessment scores of the user according to the medical research and assessment data fed back by the user; acquiring medical data information read by the user and related to the target medical category; determining the difficulty of the acquired medical data; counting the number of the medical data respectively corresponding to the difficulty, the middle and the ease; and inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and easy respectively to obtain the cognitive grade of the user in the target medical category.
Preferably, the grade analysis model comprises an ordered regression model; the medical information recommendation method further comprises the following steps: analyzing the fitting relation between the cognitive grade of the user and each input factor through an ordered regression model; the method specifically comprises the following steps: obtaining an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category; taking the cognitive grade of the sample user as a dependent variable in the ordered regression model; taking gender and specialty in the basic information of the sample user as first type independent variables in the ordered regression model; taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model; processing the first type of independent variable into a virtual variable; the virtual variables are quantitative data; carrying out parallelism test and likelihood ratio detection on the ordered regression model; after the parallelism test and the likelihood ratio detection are carried out, the ordered regression model is used for analyzing, and the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty and easiness distribution component of the medical data information of the user is obtained.
Preferably, the step of searching for a matched target user according to the medical category and the grade of the medical information data; the method specifically comprises the following steps: according to the medical category of the medical information data, combining the historical behavior labels and/or the basic information of the user; determining a user interested in the medical information data; and searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data.
Preferably, the medical information recommendation method further includes: and updating the grade of the user in each medical category through the grade analysis model periodically or in real time.
On the other hand, the application also discloses a medical information recommendation system, which comprises: the data acquisition module is used for acquiring medical information data to be recommended; the data grade determining module is used for determining the medical category and grade of the medical information data; the searching matching module is used for searching matched target users according to the medical categories and the grades of the medical information data; and the information recommendation module is used for recommending the medical information data to the matched target user.
Preferably, the medical information recommendation system further comprises: the user grade determining module is used for acquiring the medical categories which are interested by the user and the corresponding cognitive grades; the user level determination module specifically includes: the definition submodule is used for defining the cognitive grade type of the user; the information acquisition submodule is used for acquiring basic information, historical behavior data and research data of a user; the system establishing submodule is used for establishing a level analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field; and the analysis processing submodule is used for acquiring the medical categories which are interested by the user and the corresponding cognitive levels through the level analysis model according to the basic information, the historical behavior data and the research data of the user.
Preferably, the analysis processing sub-module specifically includes: the target medical category determining unit is used for determining the medical category which is interested by the user according to the historical behavior data of the user and/or the basic information of the user and taking the medical category as the target medical category; the retrieval unit is used for retrieving the medical research and assessment data of the target medical category and sending the data to the user; the assessment unit is used for receiving the medical research assessment data fed back by the user and determining assessment scores of the user according to the medical research assessment data fed back by the user; the information acquisition submodule is also used for acquiring medical data information read by the user and related to the target medical category; a difficulty level determination unit for determining a difficulty level of the acquired medical data; the statistical unit is used for counting the number of the medical data respectively corresponding to the difficulty, the medium and the easy; and the model processing unit is used for inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and ease respectively to obtain the cognitive grade of the user in the target medical category.
Preferably, the medical information recommendation system further comprises: the regression analysis module is used for analyzing the fitting relation between the cognitive grade of the user and each input factor through an ordered regression model; the regression analysis module specifically comprises: the sample acquisition submodule is used for acquiring an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category; the variable setting submodule is used for taking the cognitive grade of the sample user as a dependent variable in the ordered regression model; taking gender and specialty in the basic information of the sample user as first type independent variables in the ordered regression model; taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model; the variable conversion submodule is used for processing the first type of independent variable into a virtual variable; the virtual variables are quantitative data; the detection submodule is used for carrying out parallelism detection and likelihood ratio detection on the ordered regression model; and the regression analysis submodule is used for analyzing through the ordered regression model after the parallelism test and the likelihood ratio detection are carried out, and acquiring the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty degree distribution component of the medical data information of the user.
Preferably, the searching and matching module specifically includes: the user locking sub-module is used for combining the historical behavior labels and/or the basic information of the user according to the medical category of the medical information data; determining a user interested in the medical information data; and the user searching sub-module is used for searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data.
Preferably, the analysis processing sub-module further includes: the label obtaining unit is used for analyzing the historical behavior data of the user to obtain a label of the user; the label is used to indicate a medical category of interest to the user.
The application at least comprises the following technical effects:
(1) when the medical information data is recommended, the recommendation is performed according to the medical category and the corresponding level of the medical information data and the cognitive level of the user in the medical category actually, so that the recommended data information can be more fit with the requirement of the user, and the user is more helped to refine in the professional category.
(2) The method adopts an ordered regression model to analyze the main factors influencing the cognitive grade of the user and the fitting relation between the main factors and each influencing factor; through the comprehensive analysis, the finally predicted cognitive grade of the user is more accurate.
(3) Because the user is continuously studying and progressing, the cognitive grade of the user in each medical category is not constant, and the cognitive grade of the user in each medical category can be updated regularly or in real time in the embodiment, so that the medical information data which accord with the current cognitive grade is synchronously recommended along with the improvement of the cognitive grade of the user, and the study and the progress of the user are facilitated.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of an embodiment of a medical information recommendation method of the present application;
FIG. 2 is a flow chart of one implementation of user level determination in the present application;
FIG. 3 is a flow chart of another implementation of user level determination in the present application;
FIG. 4 is a block diagram of an embodiment of a medical information recommendation system of the present application;
fig. 5 is a block diagram of another embodiment of the medical information recommendation system of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present application, and they do not represent the actual structure of the product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically depicted, or only one of them is labeled. In this document, "one" means not only "only one" but also a case of "more than one".
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
In addition, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to indicate or imply relative importance.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the present application, and that for a person skilled in the art, other drawings and other embodiments can be obtained from these drawings without inventive effort.
In an embodiment of the present application, as shown in fig. 1, a medical information recommendation method of the present embodiment includes:
s100, acquiring medical information data to be recommended;
s200, determining the medical category and grade of the medical information data;
specifically, since medical information data is professional-type data information, it is different from ordinary entertainment news, and its audience is often people engaged in or interested in the medical industry, and because it may relate to medical professional terms, or research and development tests in a certain medical field, it is not necessarily popular and easy to understand, and there are many professional types included in the medical field, even if different medical information data in the same professional field are different in difficulty, a user with weak cognition may prefer to see simpler medical information data in the field, and as the cognitive level of the user is enhanced, the difficulty of the medical information of interest may be enhanced simultaneously, and more deep viewing may be achieved, and deeper medical information may be researched in this respect. Therefore, in the present application, after the medical information data to be recommended is acquired, the category and the level (difficulty in understanding or cognition) to which the medical information data belongs are determined according to the content of the medical information data.
S300, searching a matched target user according to the medical category and the grade of the medical information data;
specifically, after the medical category and the grade of the medical information data to be recommended are determined, the corresponding user, namely the target user, is matched according to the category and the grade. The target user not only needs to be interested in the medical information of the category, but also the cognitive level (cognitive level/level) of the user needs to reach the level of the medical information data, so that the recommended data information is more targeted and distinguished, and accurate recommendation according to the cognitive level (level) of the user is realized.
And S400, recommending the medical information data to the matched target user.
And finally, after the target user matched with the grade and the category of the medical information data is found, recommending the medical information data to the user.
In the embodiment of the application, since the cognitive levels of the medical information of the user are different, if the existing hotspot recommendation is adopted or the recommendation is only carried out according to the interested categories of the user, the cognitive level of the user may not reach the grade of the recommended medical information data, so that the user cannot know the cognitive level, does not know the cognitive level, and finishes watching the fog after the cognitive level is changed. And only if recommendation is carried out according to the cognitive level of the user in the category, the requirements of the user can be better met, and the user is more helpful to refine the professional category.
In another embodiment of the present application, on the basis of the above embodiment, a step of determining a user level is added; specifically, the medical information recommendation method further includes:
s000, acquiring medical categories and corresponding grades which are interesting to the user;
specifically, since the recommendation needs to be performed by matching the user according to the medical category and the level of the medical information data, it is also necessary to determine which type of medical information data the user is interested in before the recommendation, and the cognitive level of the user in the category. This facilitates subsequent category and level matching.
Further, the step S000 specifically includes:
s010, defining the cognitive grade type of the user;
specifically, for example, defining the cognitive grade type of the user according to the cognitive degree of the user includes: low, medium and high.
S020, acquiring basic information, historical behavior data and research data of a user;
specifically, how the cognition degree of the user is, it needs to be comprehensively judged through some behavior data, basic information condition and calling data of the user. Further, the level of awareness for the user is not necessarily a comprehensive level, but may be rated individually according to medical categories. There is a special interest in the art, and some users are experts in this domain (medical category) a, but are not necessarily professional in domain (medical category) B, so that the cognitive level in domain a is higher, and the cognitive level in domain B is lower.
S030, establishing a grade analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field;
specifically, a grade analysis model is established, and the grade analysis model is used for analyzing the cognitive level grade corresponding to each category of the user.
And S040, acquiring the medical categories which are interested by the user and the corresponding cognitive levels through the level analysis model according to the basic information, the historical behavior data and the investigation data of the user.
Preferably, in step S040, the medical category in which the user is interested and the corresponding cognitive level are obtained through the level analysis model according to the basic information, the historical behavior data, and the research data of the user; the method specifically comprises the following steps:
s041, determining medical categories which are interested by the user according to historical behavior data and/or basic information of the user, and taking the medical categories as target medical categories;
specifically, the historical behavior data includes historical browsing data and historical query data, based on which we can roughly analyze which categories of medical data information are interested by the user, and in addition, the basic information of the user includes information such as a user name, an age, a professional category, and the like, such as a professional category learned by the user, or a department in which the user works. Since the present application is a medical information recommendation, the users that are facing are mostly persons who are or will be in the medical industry, such as medical school students, medical care personnel, medical research and development personnel, and the like. Of course, it may be a person who is not working on this aspect, but who is interested in and has knowledge of this aspect. From historical behavior data or professional information in the basic information of the user, the target medical category in which the user is interested can be obtained. Of course, the target medical categories may also be obtained by combining the two aspects, and the number of the target medical categories may be one or more, and the present embodiment does not limit the number of the target medical categories of each user.
S042, retrieving the medical research and assessment data of the target medical category and sending the data to the user;
specifically, after the target medical category is determined, corresponding investigation and examination data can be retrieved and sent to the user for investigation and examination. The research assessment data is used to assess a user's preliminary level in the target medical category. The assessment score is used as a reference factor for subsequently determining the cognitive grade of the user.
S043, receiving the medical research and assessment data fed back by the user, and determining assessment scores of the user according to the medical research and assessment data fed back by the user;
specifically, in this embodiment, the user may select whether to update or determine the cognitive level of the user according to the own requirements, and if so, fill in a corresponding investigation and assessment questionnaire according to the own actual conditions, and then feed back the questionnaire. After medical investigation and assessment data fed back by a user are obtained, the medical investigation and assessment data can be scored and assessed based on a built-in assessment standard.
S044, acquiring medical data information read by the user and related to the target medical category;
specifically, for example, if the determined target medical category is a cardiovascular category, all data information related to the cardiovascular and cerebrovascular is extracted from the medical data information historically viewed by the user.
S045, determining the difficulty level of the acquired medical data;
and acquiring all data information related to the cardiovascular and cerebrovascular historically browsed by the user, and then acquiring the difficulty of the medical data information. The more difficult medical data information has higher requirement on the cognition degree of the user, and the user with the matched grade can understand the content of the medical data information more. Specifically, when each piece of medical data information in the medical website is released, the difficulty level of each piece of medical data information is evaluated through a background difficulty level evaluation system, so that the difficulty level corresponding to each piece of historical reading data information can be quickly obtained after the historical reading data information of the user is obtained subsequently. Certainly, the difficulty evaluation system comprises a difficulty evaluation standard; different medical categories can also correspond to different evaluation standards of the difficulty level.
S046, counting the number of the medical data respectively corresponding to difficulty, medium and easy;
specifically, for example, after the difficulty levels of all the medical data information related to the cardiovascular and cerebrovascular vessels, which are read by the user in history, are obtained, statistical analysis is performed on the obtained medical data information, and how many pieces of medical data information of the cardiovascular and cerebrovascular vessels exist in each difficulty level are obtained.
And S047, inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and easy respectively, and obtaining the cognitive grade of the user in the target medical category.
And finally, inputting the basic information of the user, the examination scores of the research and examination and the medical data information of the cardiovascular and cerebrovascular of each difficulty level as reference factors into a level analysis model, and analyzing the data through the level analysis model to obtain the cognitive level of the user in the aspect of the cardiovascular and cerebrovascular. For example, if the user is a doctor in the aspect of cardiovascular and cerebrovascular diseases, and the user reads most of the cardiovascular and cerebrovascular disease data information from the historical reading data, which belongs to difficult medical information, and the research and assessment score on the aspect of cardiovascular and cerebrovascular diseases is relatively high, the user can basically determine that the cognitive grade of the user in the aspect of cardiovascular and cerebrovascular diseases is high. Of course, each reference factor is considered as an aspect, and the weight of each reference factor is different. And the reference factors are combined to carry out consideration of multiple dimensions, so that the determined cognitive grade of the user is more accurate.
In another embodiment of the present invention, based on the above embodiment, the rank analysis model includes an ordered regression model, and the medical information recommendation method further includes the steps of:
s015, analyzing a fitting relation between the cognitive grade of the user and each input factor through an ordered regression model; the step S015 specifically includes:
s015-1, obtaining an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category;
in particular, to determine the factor pairs
S015-2, taking the cognitive grade of the sample user as a dependent variable in the ordered regression model;
s015-3, using the gender and the specialty in the basic information of the sample user as first type independent variables in the ordered regression model;
s015-4, taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model;
s015-5, processing the first type independent variable into a virtual variable; the virtual variables are quantitative data;
s015-6, carrying out parallelism test and likelihood ratio detection on the ordered regression model;
and S015-7, after the parallelism test and the likelihood ratio detection are carried out, analyzing through the ordered regression model, and obtaining the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty degree distribution component of the medical data information of the user.
Specifically, the order regression (ordnalregression) is mainly used for performing regression prediction analysis, and regression prediction means that a certain relationship exists between a dependent variable and a plurality of independent variables, and is expressed by a function, and the relationship is fitted by using the order regression to be used as a prediction model of the cognitive level of a user.
In the ordered logistic regression, the independent variable X may be quantitative data (the value is a specific number, such as age, score, distribution number of medical data information at difficult, medium, easy levels, etc.), or may be categorical data (the value is not a number, such as gender, specialty, etc.). However, if the classified data is included in the model, it needs to be set as a dummy variable, i.e., a virtual variable. And (4) carrying out parallelism test, namely testing whether the influence of each value level of the independent variable on the dependent variable is the same in each regression equation. The original hypothesis of the parallelism test is that the model satisfies the parallelism, so if the P value is greater than 0.05, the model is accepted by the original hypothesis, namely the parallelism test is met. Otherwise, if the P value is less than 0.05, the model rejects the original hypothesis, and the model does not meet the parallelism test. Parallelism is a prerequisite for ordered Logit regression. And the likelihood ratio test is used for analyzing the overall effectiveness of the model. The original assumption is that all the regression coefficients of the model are 0, so if the P value is less than 0.05, the original assumption is rejected, namely the model is effective; on the other hand, if the P value is larger than 0.05, the former assumption is accepted, namely the model regression coefficients are all 0, and the model is meaningless. And finally, after the test of parallelism and the test of likelihood ratio, analyzing according to the ordered regression model, obtaining main factors (independent variables) influencing the cognitive grade of the user, and fitting the fitting relation (equation) between the cognitive grade of the user and each main factor. Subsequently, the cognitive grade of the user can be analyzed through the ordered analysis model, that is, after the fitting function (relationship) of the dependent variable and the independent variable is determined, when the cognitive grade of the user in the medical category a is predicted, only main influence factor parameters, such as basic information of the user, investigation and assessment scores of the user in the medical category a and difficulty degree distribution of historical medical information data read by the user in the medical category a, need to be input, and the cognitive grade of the user in the medical category a can be output through the ordered regression analysis model.
Another embodiment of the method of the present invention, as shown, comprises:
s100, acquiring medical information data to be recommended;
s200, determining the medical category and grade of the medical information data;
s310, combining historical behavior labels and/or user basic information of the user according to the medical category of the medical information data; determining a user interested in the medical information data;
s320, searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data;
and S400, recommending the medical information data to the matched target user.
And S500, updating the grade of the user in each medical category through the grade analysis model regularly or in real time.
Specifically, in this embodiment, first, the medical category and the grade of each piece of medical information data to be recommended on the medical website need to be acquired; and then, finding out users interested in the medical category according to the medical category of the medical information data to be recommended, specifically, selecting the users according to the historical browsing condition of the users or the professional category in the basic information registered by the users, primarily locking the user group, and then finding out the target users matched with the user group from the locked user group according to the grade of the medical information data to be recommended. And finally, recommending the medical information data to the matched target user, thereby realizing high-fit recommendation of the medical information.
In addition, as the user learns and progresses continuously, the cognitive level of the user in each medical category is not constant, and the cognitive level of the user in each medical category can be updated regularly or in real time in the embodiment, so that the medical information data conforming to the current cognitive level is recommended synchronously along with the improvement of the cognitive level of the user, and the learning and the progress of the user are facilitated.
Based on the same technical concept, the application also discloses a medical information recommendation system, and the medical information recommendation system can recommend the medical information to be recommended to the matched user by adopting the recommendation method of any one of the embodiments. Specifically, an embodiment of the medical information recommendation system of the present application, as shown in fig. 4, includes:
a data obtaining module 100, configured to obtain medical information data to be recommended;
a data grade determination module 200 for determining the medical category and grade of the medical information data;
the searching and matching module 300 is used for searching matched target users according to the medical categories and the grades of the medical information data;
and the information recommending module 400 is used for recommending the medical information data to the matched target user.
In the embodiment of the system, since the cognitive levels of the medical information of the users are different, if the existing hot spot recommendation is adopted or the recommendation is only carried out according to the interested categories of the users, the cognitive level of the users can not reach the grade of the recommended medical information data, so that the users can not understand the cognitive level. And only if recommendation is carried out according to the cognitive level of the user in the category, the requirements of the user can be better met, and the user is more helpful to refine the professional category.
In another embodiment of the medical information recommendation system of the present application, as shown in fig. 5, on the basis of the previous medical information recommendation system, the medical information recommendation system further includes:
a user level determination module 500, configured to obtain a medical category in which the user is interested and a corresponding cognitive level;
the user level determining module 500 specifically includes:
a definition sub-module 510 for defining a user's cognitive grade type;
the information acquisition submodule 520 is used for acquiring basic information, historical behavior data and research data of a user;
the system establishing submodule 530 is used for establishing a level analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field;
and the analysis processing sub-module 540 is configured to obtain, according to the basic information, the historical behavior data, and the research data of the user, the medical category in which the user is interested and the corresponding cognitive level through the level analysis model.
On the basis of the system embodiment, the user grade determining module is added for carrying out grade judgment on the vast users. Specifically, in this embodiment, the determination of the cognitive level of the user in each medical category is a result of comprehensively considering the basic information, the historical behavior data and the research data of the user, and since the consideration is comprehensive, the final analysis result is more accurate.
In another embodiment of the system of the present application, on the basis of the above embodiment, the analysis processing sub-module 540 specifically includes:
the target medical category determining unit is used for determining the medical category which is interested by the user according to the historical behavior data of the user and/or the basic information of the user and taking the medical category as the target medical category;
the retrieval unit is used for retrieving the medical research and assessment data of the target medical category and sending the data to the user;
the assessment unit is used for receiving the medical research assessment data fed back by the user and determining assessment scores of the user according to the medical research assessment data fed back by the user;
the information acquisition submodule is also used for acquiring medical data information read by the user and related to the target medical category;
a difficulty level determination unit for determining a difficulty level of the acquired medical data;
the statistical unit is used for counting the number of the medical data respectively corresponding to the difficulty, the medium and the easy;
and the model processing unit is used for inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and ease respectively to obtain the cognitive grade of the user in the target medical category.
Preferably, the medical information recommendation system further comprises: the regression analysis module is used for analyzing the fitting relation between the cognitive grade of the user and each input factor through an ordered regression model; specifically, the regression analysis module includes:
the sample acquisition submodule is used for acquiring an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category;
the variable setting submodule is used for taking the cognitive grade of the sample user as a dependent variable in the ordered regression model; taking gender and specialty in the basic information of the sample user as first type independent variables in the ordered regression model; taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model;
the variable conversion submodule is used for processing the first type of independent variable into a virtual variable; the virtual variables are quantitative data;
the detection submodule is used for carrying out parallelism detection and likelihood ratio detection on the ordered regression model;
and the regression analysis submodule is used for analyzing through the ordered regression model after the parallelism test and the likelihood ratio detection are carried out, and acquiring the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty degree distribution component of the medical data information of the user.
On the basis of any of the above embodiments, the matching searching module specifically includes:
the user locking sub-module is used for combining the historical behavior labels and/or the basic information of the user according to the medical category of the medical information data; determining a user interested in the medical information data;
and the user searching sub-module is used for searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data.
Further, the analysis processing sub-module further includes: the label obtaining unit is used for analyzing the historical behavior data of the user to obtain a label of the user; the label is used to indicate a medical category of interest to the user.
Specifically, in this embodiment, first, the medical category and the grade of each piece of medical information data to be recommended on the medical website need to be acquired; and then, finding out users interested in the medical category according to the medical category of the medical information data to be recommended, specifically, selecting the users according to the historical browsing condition of the users or the professional category in the basic information registered by the users, primarily locking the user group, and then finding out the target users matched with the user group from the locked user group according to the grade of the medical information data to be recommended. And finally, recommending the medical information data to the matched target user, thereby realizing high-fit recommendation of the medical information.
In addition, as the user learns and progresses continuously, the cognitive level of the user in each medical category is not constant, and the cognitive level of the user in each medical category can be updated regularly or in real time in the embodiment, so that the medical information data conforming to the current cognitive level is recommended synchronously along with the improvement of the cognitive level of the user, and the learning and the progress of the user are facilitated.
The system embodiment of the present application corresponds to the method embodiment, and the technical details of the method embodiment of the present application are also applicable to the system embodiment of the present application, and are not described again to reduce repetition.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (12)
1. A medical information recommendation method, comprising:
acquiring medical information data to be recommended;
determining a medical category and a grade of the medical information data;
searching a matched target user according to the medical category and the grade of the medical information data;
recommending the medical information data to the matched target user.
2. The medical information recommendation method according to claim 1, further comprising:
acquiring medical categories and corresponding levels in which users are interested; the method specifically comprises the following steps:
defining a cognitive grade type of a user;
acquiring basic information, historical behavior data and research data of a user;
establishing a grade analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field;
and acquiring the medical categories and corresponding cognitive levels of the users interested by the users through the level analysis model according to the basic information, the historical behavior data and the research data of the users.
3. The method according to claim 2, wherein the medical categories and corresponding cognitive levels of interest to the user are obtained through the level analysis model according to the basic information, historical behavior data and research data of the user; the method specifically comprises the following steps:
determining medical categories which are interested by the user according to historical behavior data and/or basic information of the user, and taking the medical categories as target medical categories;
calling medical research and assessment data of the target medical category, and sending the medical research and assessment data to the user;
receiving the medical research and assessment data fed back by the user, and determining assessment scores of the user according to the medical research and assessment data fed back by the user;
acquiring medical data information read by the user and related to the target medical category;
determining the difficulty of the acquired medical data;
counting the number of the medical data respectively corresponding to the difficulty, the middle and the ease;
and inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and easy respectively to obtain the cognitive grade of the user in the target medical category.
4. The method of claim 3, wherein the ranking model comprises an ordered regression model, and the method further comprises:
analyzing the fitting relation between the cognitive grade of the user and each input factor through an ordered regression model; the method specifically comprises the following steps:
obtaining an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category;
taking the cognitive grade of the sample user as a dependent variable in the ordered regression model;
taking gender and specialty in the basic information of the sample user as first type independent variables in the ordered regression model;
taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model;
processing the first type of independent variable into a virtual variable; the virtual variables are quantitative data;
carrying out parallelism test and likelihood ratio detection on the ordered regression model;
after the parallelism test and the likelihood ratio detection are carried out, the ordered regression model is used for analyzing, and the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty and easiness distribution component of the medical data information of the user is obtained.
5. The medical information recommendation method according to claim 2, wherein the matching target user is searched according to the medical category and the grade of the medical information data; the method specifically comprises the following steps:
according to the medical category of the medical information data, combining the historical behavior labels and/or the basic information of the user; determining a user interested in the medical information data;
and searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data.
6. A medical information recommendation method according to any one of claims 2-5, comprising:
and updating the grade of the user in each medical category through the grade analysis model periodically or in real time.
7. A medical information recommendation system, comprising:
the data acquisition module is used for acquiring medical information data to be recommended;
the data grade determining module is used for determining the medical category and grade of the medical information data;
the searching matching module is used for searching matched target users according to the medical categories and the grades of the medical information data;
and the information recommendation module is used for recommending the medical information data to the matched target user.
8. A medical information recommendation system according to claim 7, further comprising:
the user grade determining module is used for acquiring the medical categories which are interested by the user and the corresponding cognitive grades;
the user level determination module specifically includes:
the definition submodule is used for defining the cognitive grade type of the user;
the information acquisition submodule is used for acquiring basic information, historical behavior data and research data of a user;
the system establishing submodule is used for establishing a level analysis model; the ranking analysis model is used for analyzing the cognitive ranking of the user in a specific category of a medical field;
and the analysis processing submodule is used for acquiring the medical categories which are interested by the user and the corresponding cognitive levels through the level analysis model according to the basic information, the historical behavior data and the research data of the user.
9. The medical information recommendation system according to claim 8, wherein the analysis processing sub-module specifically comprises:
the target medical category determining unit is used for determining the medical category which is interested by the user according to the historical behavior data of the user and/or the basic information of the user and taking the medical category as the target medical category;
the retrieval unit is used for retrieving the medical research and assessment data of the target medical category and sending the data to the user;
the assessment unit is used for receiving the medical research assessment data fed back by the user and determining assessment scores of the user according to the medical research assessment data fed back by the user;
the information acquisition submodule is also used for acquiring medical data information read by the user and related to the target medical category;
a difficulty level determination unit for determining a difficulty level of the acquired medical data;
the statistical unit is used for counting the number of the medical data respectively corresponding to the difficulty, the medium and the easy;
and the model processing unit is used for inputting the basic information, the assessment scores and the medical data of the user into the grade analysis model according to the corresponding quantity of difficulty, medium and ease respectively to obtain the cognitive grade of the user in the target medical category.
10. A medical information recommendation system according to claim 9, further comprising: the regression analysis module is used for analyzing the fitting relation between the cognitive grade of the user and each input factor through an ordered regression model;
the regression analysis module includes:
the sample acquisition submodule is used for acquiring an analysis sample; the analysis sample comprises basic information of a sample user, assessment scores and difficulty degree distribution components of medical data information of a target medical category; and a cognitive grade of the sample user in the target medical category;
the variable setting submodule is used for taking the cognitive grade of the sample user as a dependent variable in the ordered regression model; taking gender and specialty in the basic information of the sample user as first type independent variables in the ordered regression model; taking the age, the assessment score and the difficulty degree distribution component of the medical data of the target medical category in the basic information of the sample user as a second type of independent variable in the ordered regression model;
the variable conversion submodule is used for processing the first type of independent variable into a virtual variable; the virtual variables are quantitative data;
the detection submodule is used for carrying out parallelism detection and likelihood ratio detection on the ordered regression model;
and the regression analysis submodule is used for analyzing through the ordered regression model after the parallelism test and the likelihood ratio detection are carried out, and acquiring the fitting relation between the cognitive grade of the sample user in the target medical category and the basic information, the assessment score and the difficulty degree distribution component of the medical data information of the user.
11. The medical information recommendation system according to any one of claims 8-10, wherein the lookup matching module specifically comprises:
the user locking sub-module is used for combining the historical behavior labels and/or the basic information of the user according to the medical category of the medical information data; determining a user interested in the medical information data;
and the user searching sub-module is used for searching a target user with the user grade matched with the grade of the medical information data from the determined users according to the grade of the medical information data.
12. The medical information recommendation method according to claim 8, wherein the analysis processing sub-module further comprises:
the label obtaining unit is used for analyzing the historical behavior data of the user to obtain a label of the user; the label is used to indicate a medical category of interest to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010787111.7A CN111914174B (en) | 2020-08-07 | 2020-08-07 | Medical information recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010787111.7A CN111914174B (en) | 2020-08-07 | 2020-08-07 | Medical information recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111914174A true CN111914174A (en) | 2020-11-10 |
| CN111914174B CN111914174B (en) | 2021-07-02 |
Family
ID=73287352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010787111.7A Active CN111914174B (en) | 2020-08-07 | 2020-08-07 | Medical information recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914174B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408985A (en) * | 2014-12-17 | 2015-03-11 | 李莎 | Cloud-network-based answering learning method and system |
| US20160063596A1 (en) * | 2014-08-27 | 2016-03-03 | Kobo Incorporated | Automatically generating reading recommendations based on linguistic difficulty |
| WO2016114790A1 (en) * | 2015-01-16 | 2016-07-21 | Hewlett-Packard Development Company, L. P. | Reading difficulty level based resource recommendation |
| CN106097200A (en) * | 2016-06-12 | 2016-11-09 | 深圳市悦好教育科技有限公司 | A kind of method carrying out primary grades read books classification based on vocabulary accounting |
| CN109977408A (en) * | 2019-03-27 | 2019-07-05 | 西安电子科技大学 | The implementation method of English Reading classification and reading matter recommender system based on deep learning |
-
2020
- 2020-08-07 CN CN202010787111.7A patent/CN111914174B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160063596A1 (en) * | 2014-08-27 | 2016-03-03 | Kobo Incorporated | Automatically generating reading recommendations based on linguistic difficulty |
| CN104408985A (en) * | 2014-12-17 | 2015-03-11 | 李莎 | Cloud-network-based answering learning method and system |
| WO2016114790A1 (en) * | 2015-01-16 | 2016-07-21 | Hewlett-Packard Development Company, L. P. | Reading difficulty level based resource recommendation |
| CN106097200A (en) * | 2016-06-12 | 2016-11-09 | 深圳市悦好教育科技有限公司 | A kind of method carrying out primary grades read books classification based on vocabulary accounting |
| CN109977408A (en) * | 2019-03-27 | 2019-07-05 | 西安电子科技大学 | The implementation method of English Reading classification and reading matter recommender system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| CHIH-MING CHEN等: "Personalized e-learning system using Item Response Theory", 《COMPUTERS & EDUCATION》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111914174B (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hamby et al. | Survey satisficing inflates reliability and validity measures: An experimental comparison of college and Amazon Mechanical Turk samples | |
| CN106920129B (en) | Eye tracking-based network advertisement effect evaluation system and method | |
| Bittermann et al. | How to identify hot topics in psychology using topic modeling | |
| Zhou et al. | Roles of review numerical and textual characteristics on review helpfulness across three different types of reviews | |
| CN111898031B (en) | Method and device for obtaining user portrait | |
| US11922300B2 (en) | Automated commentary for online content | |
| CA2959835A1 (en) | Sentiment rating system and method | |
| CN110019943B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| Ziegler et al. | The vocabulary and overclaiming test (VOC-T) | |
| CN103455522A (en) | Recommendation method and system of application extension tools | |
| US8838435B2 (en) | Communication processing | |
| CN115577185B (en) | Muting course recommendation method and device based on mixed reasoning and mesopic group decision | |
| Ishiyama et al. | Relationship between public attitudes toward genomic studies related to medicine and their level of genomic literacy in Japan | |
| CN116109373A (en) | Recommendation method and device for financial products, electronic equipment and medium | |
| Ng et al. | CrsRecs: a personalized course recommendation system for college students | |
| CN108280081B (en) | Method and device for generating webpage | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| Neve et al. | Hybrid reciprocal recommender systems: Integrating item-to-user principles in reciprocal recommendation | |
| CN112052297A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| Guan et al. | When images backfire: The effect of customer-generated images on product rating dynamics | |
| KR20110052114A (en) | Recommendation searching system using internet and method thereof | |
| CN111177564B (en) | Product recommendation method and device | |
| CN111914174B (en) | Medical information recommendation method and system | |
| Medlin et al. | Political orientation and belief in science in a US college sample | |
| CN116153496A (en) | Neural network model training method and depression emotion detection method |
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 |