CN111079021A - Method, device, server and storage medium for recommending medical information content - Google Patents
Method, device, server and storage medium for recommending medical information content Download PDFInfo
- Publication number
- CN111079021A CN111079021A CN201911323623.1A CN201911323623A CN111079021A CN 111079021 A CN111079021 A CN 111079021A CN 201911323623 A CN201911323623 A CN 201911323623A CN 111079021 A CN111079021 A CN 111079021A
- Authority
- CN
- China
- Prior art keywords
- disease
- medical information
- determining
- target
- information content
- 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
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a method, a device, a server and a storage medium for recommending medical information content, and belongs to the technical field of information recommendation. The method comprises the following steps: determining a target condition input by a target account; determining at least one disease corresponding to the target disease based on the corresponding relation between the pre-stored disease and the disease; determining a target disease matched with the previous disease recorded in the historical disease information corresponding to the target account in at least one disease; and determining the content of the medical information to be recommended based on the target disease. By adopting the method and the device, the determined target disease has higher correlation with the target disease currently appearing by the user, and further the recommended medical information content determined based on the target disease has higher correlation with the target disease currently appearing by the user. The recommended medical information content can effectively aim at the diseases actually suffered by the user, and the recommendation effectiveness is high.
Description
Technical Field
The present disclosure relates to the field of information recommendation technologies, and in particular, to a method, an apparatus, a server, and a storage medium for recommending medical information content.
Background
With the development of science and technology and the popularization of the internet, when people feel uncomfortable, a relieving method can be searched in the network aiming at some self-occurring diseases. For example, when a user feels toothache, an inquiry application program may be opened, and "what is done with toothache" may be input in an information search field of the inquiry application program, at this time, the inquiry application program may extract a keyword "toothache" input by the user, search for medical information content related to "toothache" and recommend the medical information content to the user, and a manner of alleviating the "toothache" is generally provided in the medical information content related to "toothache".
In carrying out the present disclosure, the inventors found that at least the following problems exist:
different diseases may be associated with the same condition, and the relief of these different diseases is sometimes quite different. The medical information content is recommended only aiming at the specific disease input by the user, and the recommendation effectiveness is poor because the medical information content cannot be effectively aiming at the disease actually suffered by the user.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides the following technical solutions:
according to a first aspect of embodiments of the present disclosure, there is provided a method of recommending medical information content, the method including:
determining a target condition input by a target account;
determining at least one disease corresponding to the target disease based on the corresponding relation between the pre-stored disease and the pre-stored disease;
determining a target disease matched with the previous disease recorded in the historical disease information corresponding to the target account in the at least one disease;
and determining the medical information content to be recommended based on the target disease.
Optionally, the determining the medical information content to be recommended based on the target disease includes:
acquiring disease keywords included in each candidate medical information content;
and determining medical information contents to be recommended in the candidate medical information contents based on the target diseases and the disease keywords.
Optionally, the determining, based on the target disease and the disease keyword, a medical information content to be recommended in each candidate medical information content includes:
determining a disease characteristic corresponding to the target account based on the target disease;
determining content characteristics corresponding to the candidate medical information contents respectively based on the disease keywords;
determining the similarity between the diseased features and the content features respectively;
and determining a first preset number of medical information contents to be recommended with the highest similarity in the candidate medical information contents.
Optionally, the similarity comprises a euclidean distance, a manhattan distance, a minkowski distance, or a pearson correlation coefficient.
Optionally, the acquiring the disease keyword included in each candidate medical information content includes:
for each candidate medical information content, if the number of different disease identifiers included in the candidate medical information content is smaller than or equal to a preset threshold, determining the different disease identifiers as disease keywords, if the number of different disease identifiers included in the candidate medical information content is larger than the preset threshold, determining the occurrence times corresponding to the different disease identifiers respectively, and determining a second preset number of disease identifiers with the largest occurrence times as the disease keywords.
According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for recommending medical information content, the apparatus including:
a determination module for determining a target condition input by a target account;
the determining module is used for determining at least one disease corresponding to the target disease based on the corresponding relation between the pre-stored disease and the target disease;
the determining module is used for determining a target disease matched with the previous disease recorded in the historical disease information corresponding to the target account in the at least one disease;
and the recommending module is used for determining the medical information content to be recommended based on the target disease.
Optionally, the recommendation module is configured to:
acquiring disease keywords included in each candidate medical information content;
and determining medical information contents to be recommended in the candidate medical information contents based on the target diseases and the disease keywords.
Optionally, the recommendation module is configured to:
determining a disease characteristic corresponding to the target account based on the target disease;
determining content characteristics corresponding to the candidate medical information contents respectively based on the disease keywords;
determining the similarity between the diseased features and the content features respectively;
and determining a first preset number of medical information contents to be recommended with the highest similarity in the candidate medical information contents.
Optionally, the similarity comprises a euclidean distance, a manhattan distance, a minkowski distance, or a pearson correlation coefficient.
Optionally, the recommendation module is configured to:
for each candidate medical information content, if the number of different disease identifiers included in the candidate medical information content is smaller than or equal to a preset threshold, determining the different disease identifiers as disease keywords, if the number of different disease identifiers included in the candidate medical information content is larger than the preset threshold, determining the occurrence times corresponding to the different disease identifiers respectively, and determining a second preset number of disease identifiers with the largest occurrence times as the disease keywords.
According to a third aspect of embodiments of the present disclosure, there is provided a server comprising a processor, a communication interface, a memory, and a communication bus, wherein:
the processor, the communication interface and the memory complete mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is used for executing the program stored in the memory so as to realize the method for recommending the medical information content.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the above-mentioned method of recommending medical information content.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
even though different diseases may be accompanied by the same disease, the method provided by the embodiment of the disclosure can determine the target disease which is likely to relapse again currently based on the target disease input by the target account and the previous disease recorded in the historical disease information corresponding to the target account, and the relevance between the target disease and the target disease currently appearing by the user is higher, so that the relevance between the recommended medical information content determined based on the target disease and the target disease currently appearing by the user is higher. The recommended medical information content can effectively aim at the diseases actually suffered by the user, and the recommendation effectiveness is high.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. In the drawings:
FIG. 1 is a block diagram illustrating a system for recommending medical information content according to an exemplary embodiment;
FIG. 2 is a flow diagram illustrating a method of recommending medical information content according to an exemplary embodiment;
FIG. 3 is a schematic diagram illustrating a display interface of an interrogation application according to an exemplary embodiment;
FIG. 4 is a flow diagram illustrating a method of recommending medical information content in accordance with an exemplary embodiment;
FIG. 5 is a block diagram illustrating an apparatus for recommending medical information content according to an exemplary embodiment;
fig. 6 is a schematic diagram illustrating a configuration of a server according to an example embodiment.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The embodiment of the disclosure provides a method for recommending medical information content, which can be realized by a server and can be realized by the cooperation of a terminal. Fig. 1 is a schematic structural diagram of a system for recommending medical information content according to an embodiment of the disclosure. The terminal can be provided with an inquiry application program, when the user feels uncomfortable, the inquiry application program can be opened, specific symptoms can be input in an information search field of the inquiry application program, and the inquiry application program can interact with the server at the moment so as to search medical information contents related to the symptoms input by the user for recommendation.
An exemplary embodiment of the present disclosure provides a method for recommending medical information content, as shown in fig. 2, a process flow of the method may include the following steps:
step S201, determining the target symptoms input by the target account.
In implementation, the terminal can be provided with an inquiry application program, when the user feels that the body is not proper, the inquiry application program can be opened, and specific symptoms can be input in an information search field of the inquiry application program. When the inquiry application program is started, a pre-bound target account can be logged in by default, and after the terminal acquires the target disease condition input by the user, the account identifier of the target account and the target disease condition can be carried in the medical information content acquisition request and sent to the server. After receiving the medical information content acquisition request, the server can acquire the account identifier of the target account and the corresponding target symptoms carried in the medical information content acquisition request.
Step S202, at least one disease corresponding to the target disease is determined based on the corresponding relation between the pre-stored disease and the disease.
In practice, the correspondence between different disorders and various diseases may be established in advance, and theoretically, one disorder may correspond to a plurality of diseases. For example, the disease is toothache, and theoretically possible diseases may include caries, pulpitis, periapical periodontitis, tooth trauma, dentinal hypersensitivity, wedge defects, etc., which may cause toothache, and thus, depending on one disease alone, the actual disease cannot be accurately judged. For each possible disease of human body, the corresponding possible disease can be counted, and the corresponding disease and disease are stored. When the server obtains the target disease condition input by the target account, at least one disease matched with the target disease condition can be searched in the pre-stored corresponding relation.
For example, the target condition input to the target account is toothache, and diseases corresponding to the toothache including caries, pulpitis, periapical periodontitis, tooth trauma, dentinal hypersensitivity, and wedge defects can be determined based on the correspondence stored in advance. Alternatively, the target condition input by the target account is eye pain, and the disease corresponding to the eye pain may be determined to include glaucoma, uveitis, keratitis, supraorbital nerve pain, and optic papillitis, based on the correspondence stored in advance.
Step S203, in the at least one disease, a target disease matching the previous disease recorded in the history disease information corresponding to the target account is determined.
In implementation, historical disease information corresponding to the target account can be acquired, a user may use the target account to perform online inquiry for multiple times, and an online doctor can perform diagnosis operation on the user and input a diagnosis result into the historical disease information corresponding to the target account. The medical information content acquisition request can carry an account identifier of the target account, so that the server can search historical diseased information corresponding to the account identifier based on the account identifier of the target account, and the historical diseased information records the previous diseases of the user. After determining the at least one disease corresponding to the target condition, the same target disease as the previous disease may be determined among the at least one disease.
For example, the user has been suffering from pulpitis, and the condition is relieved after a certain period of treatment, but after a long period of time, the pulpitis that the user has suffered from recurs again, resulting in the user feeling toothache. In this case, as shown in fig. 3, the user may input "what is going to be done with toothache" in the inquiry application, extract the keyword "toothache" input by the user, and perform medical information content query using the toothache as a target disease. Because the quantity of medical information contents related to toothache is huge, the medical information contents are different according to specific diseases, and the medical information contents are recommended to users without screening, so that the recommendation effectiveness is low. Further, with the present disclosure, at least one possible disease corresponding to the toothache may be determined, and the target disease that the user has had is searched for among the at least one possible disease. In this way, since there is a high possibility that the user may relapse into one disease after the disease has once occurred, it can be determined that the user accompanied with toothache has once suffered from pulpitis, and the pulpitis of the user relapses again, and that the pulpitis can be determined as the target disease. If the user has other dental diseases in addition to pulpitis, the other dental diseases can be determined as the target diseases together. The number of target diseases is not unique and may be plural.
Step S204, based on the target disease, determining the content of the medical information to be recommended.
In implementation, based on the method, the target disease which is likely to relapse at present can be determined, the correlation between the target disease and the target disease which is present at present in the user is high, and the medical information content to be recommended can be determined based on the target disease.
Even though different diseases may be accompanied by the same disease, the method provided by the embodiment of the disclosure can determine the target disease which is likely to relapse again currently based on the target disease input by the target account and the previous disease recorded in the historical disease information corresponding to the target account, and the relevance between the target disease and the target disease currently appearing by the user is higher, so that the relevance between the recommended medical information content determined based on the target disease and the target disease currently appearing by the user is higher. The recommended medical information content can effectively aim at the diseases actually suffered by the user, and the recommendation effectiveness is high.
An exemplary embodiment of the present disclosure provides a method for recommending medical information content, as shown in fig. 4, a process flow of the method may include the following steps:
step S401, determining the target symptoms input by the target account.
In implementation, the terminal can be provided with an inquiry application program, when the user feels that the body is not proper, the inquiry application program can be opened, and specific symptoms can be input in an information search field of the inquiry application program. When the inquiry application program is started, a pre-bound target account can be logged in by default, and after the terminal acquires the target disease condition input by the user, the account identifier of the target account and the target disease condition can be carried in the medical information content acquisition request and sent to the server. After receiving the medical information content acquisition request, the server can acquire the account identifier of the target account and the corresponding target symptoms carried in the medical information content acquisition request.
Step S402, at least one disease corresponding to the target disease is determined based on the corresponding relation between the pre-stored disease and the disease.
In practice, the correspondence between different disorders and various diseases may be established in advance, and theoretically, one disorder may correspond to a plurality of diseases. For example, the disease is toothache, and theoretically possible diseases may include caries, pulpitis, periapical periodontitis, tooth trauma, dentinal hypersensitivity, wedge defects, etc., which may cause toothache, and thus, depending on one disease alone, the actual disease cannot be accurately judged. For each possible disease of human body, the corresponding possible disease can be counted, and the corresponding disease and disease are stored. When the server obtains the target disease condition input by the target account, at least one disease matched with the target disease condition can be searched in the pre-stored corresponding relation.
In step S403, among the at least one disease, a target disease matching the previous disease recorded in the history disease information corresponding to the target account is determined.
In implementation, historical disease information corresponding to the target account can be acquired, a user may use the target account to perform online inquiry for multiple times, and an online doctor can perform diagnosis operation on the user and input a diagnosis result into the historical disease information corresponding to the target account. The medical information content acquisition request can carry an account identifier of the target account, so that the server can search historical diseased information corresponding to the account identifier based on the account identifier of the target account, and the historical diseased information records the previous diseases of the user. After determining the at least one disease corresponding to the target condition, the same target disease as the previous disease may be determined among the at least one disease.
If the at least one disease does not exist, determining all the diseases in the at least one disease as the target disease, determining a disease vector based on the target disease, and performing matching processing on the medical information content.
Step S404, obtaining the disease keywords included in each candidate medical information content.
In implementation, for each candidate medical information content, if the number of different disease identifiers included in the candidate medical information content is less than or equal to a preset threshold, the different disease identifiers are determined as disease keywords, if the number of different disease identifiers included in the candidate medical information content is greater than the preset threshold, the occurrence times corresponding to the different disease identifiers respectively are determined, and the second preset number of disease identifiers with the largest occurrence times is determined as the disease keywords.
Before entering each candidate medical information content into the database, a disease name in each candidate medical information content may be extracted. For example, 10 different disease names are extracted from the candidate medical information content a, and 20 different disease names are extracted from the candidate medical information content B. After the disease names in each candidate medical information content are extracted, the number of different disease names appearing in each candidate medical information content may be determined, and if the number is less than or equal to a preset threshold, for example, 10, all the different disease names appearing in the candidate medical information content are determined as the disease keyword corresponding to the candidate medical information content. If the number of different disease names appearing in each candidate medical information content is larger than a preset threshold value, for example, 10, the number of times of appearance of each different disease name can be determined, the disease names are sorted according to the sequence of the number of times of appearance from high to low, a second preset number of disease names sorted before are selected, and a disease keyword corresponding to the candidate medical information content is obtained. Wherein the second preset number may be equal to the preset threshold.
Step S405, based on the target disease and the disease keywords, determining the content of the medical information to be recommended in each candidate medical resource content.
In implementation, based on the target disease that the user is likely to relapse at present, the corresponding diseased characteristic of the target account may be determined, and the diseased characteristic may be represented in a vector form. And determining content characteristics corresponding to the content of each candidate medical resource based on the disease keywords, wherein the content characteristics can also be represented in a vector form. Then, similarity or feature distance between the diseased feature and each content feature may be calculated, and in the embodiment of the present disclosure, the euclidean distance between the diseased feature and each content feature may be calculated, for example. The euclidean distance may also be referred to as a euclidean metric, and refers to the actual distance between two points in an n-dimensional space, or the natural length of a vector. In a two-dimensional or three-dimensional space, the euclidean distance is an actual distance between two points, and the calculation formula can be sequentially shown as formula 1 and formula 2.
Where ρ is a point (x)2，y2) To point (x)1，y1) The euclidean distance between them.
Where ρ is a point (x)2，y2，z2) To point (x)1，y1，z1) The euclidean distance between them.
In the n-dimensional space, the calculation formula of the euclidean distance can be shown in formula 3.
After calculating the feature distances between the diseased features and the content features, the first preset number of the to-be-recommended medical information contents with the minimum feature distance can be determined in the candidate medical resource contents.
In the above process, the diseased characteristic may be represented in the form of a vector, and the content characteristic may also be represented in the form of a vector, and the manner of determining the diseased characteristic or the content characteristic in the form of a vector is described below.
After determining at least one disease corresponding to the target condition based on the pre-stored correspondence of conditions and diseases, a sequence for the at least one disease may be obtained. For example, the target condition input to the target account is toothache, and the sequence of disease components corresponding to toothache may be determined to be caries, pulpitis, periapical periodontitis, tooth trauma, dentinal hypersensitivity, and wedge-like defects based on the correspondence stored in advance. The previous diseases recorded in the historical disease information corresponding to the target account, such as pulpitis and dentin hypersensitivity of the user, can be obtained. For example, the value at the position corresponding to the pulpitis and dentin hypersensitivity may be set to 1, and the obtained value sequence may be (0,1,0,0,1,0), and the value sequence may be expressed as a vector corresponding to the diseased feature. Then, each candidate medical information content can be obtained, a disease keyword corresponding to each candidate medical information content can be obtained, and for each candidate medical information content, if a disease in a sequence of disease components exists in the disease keyword corresponding to the candidate medical information content, a value 1 is set at a position corresponding to the existing disease, otherwise, a value 0 is set. For example, if the disease keyword corresponding to the candidate medical information content includes pulpitis and wedge-shaped defects, the numerical sequence corresponding to the candidate medical information content is (0,1,0,0,0,1), and the numerical sequence can be represented as a vector corresponding to the content feature. The vector corresponding to the diseased feature and the vector corresponding to the content feature can be substituted into formula 3, and the calculation result is 1.4.
And determining similarity based on the characteristic distance, and determining the medical information content to be recommended in each candidate medical information content based on the similarity. The highest value of the similarity is 1, and the feature distance can be converted into the similarity by formula 4.
Where d (x, y) is the characteristic distance.
After the feature distance is converted, the similarity value is a numerical value between 0 and 1, when the actual value of the similarity is closer to 1, the similarity between the diseased feature and the content feature is higher, and when the actual value of the similarity is closer to 0, the similarity between the diseased feature and the content feature is lower. If the characteristic distance is 1.4, the actual value of the similarity obtained by calculation is 0.42 after the characteristic distance is substituted into the formula 4.
The similarity between each of the diseased features and the plurality of content features can be calculated, and for the convenience of storing the result, the similarity can be stored by adopting a minimum heap with the size of a preset numerical value. Wherein the preset value may be 10. For example, a minimum heap of size 10 may be employed to preserve similarity. The content features may be acquired one by one, and the similarity between the currently acquired content feature and the diseased feature is calculated each time one content feature is acquired. For the first acquired content feature, the corresponding similarity is also first calculated and may be saved at the top of the heap. And for the acquired content features except the first acquired content feature, comparing the currently calculated similarity with the similarity of the heap top every time the similarity corresponding to one currently acquired content feature is calculated, and directly discarding the candidate medical information content corresponding to the currently calculated similarity if the currently calculated similarity is smaller than the similarity of the heap top. If the currently calculated similarity is greater than the similarity at the top of the heap, the medical information content of the current similarity can be inserted into the minimum heap. If the number of elements in the heap is greater than heap size 10, then the relevant information in the heap that is least similar (i.e., the element at the top of the heap) is deleted. Therefore, the medical information content with the highest similarity to the target disease vector, namely the medical information content of TOP10, in the medical information contents which are compared at present is always stored in the minimum heap.
By adopting the method and the system, the recommended medical information content is more in line with the actual illness condition of the user, and the method and the system can combine the historical illness information of the user to construct an illness portrait of the user. Then, the medical information content closest to the user is found out based on the diseased image of the user. The affected diseases are diagnosed by professional online doctors, the affected images can refer to the affected conditions recorded by historical affected information, and the accuracy of the comprehensive recommendation results is further improved.
The method adopts the Euclidean distance to calculate the similarity between the content characteristics of the diseased image and the medical information content of the user, quantifies the disease into numbers, and is convenient for comparing the similarity. Meanwhile, the similarity calculation mode provided by the disclosure is relatively simple and easy to use, and is convenient to build.
Besides the above way of recommending medical information content, it is also possible to find out patients with the same disease by using user-based collaborative filtering, and recommend medical information content that is liked by patients with the same disease to each other. In the present disclosure, in addition to the euclidean distance as the characteristic distance, the manhattan distance, the minkowski distance, the pearson correlation coefficient, and the like may be employed instead.
Even though different diseases may be accompanied by the same disease, the method provided by the embodiment of the disclosure can determine the target disease which is likely to relapse again currently based on the target disease input by the target account and the previous disease recorded in the historical disease information corresponding to the target account, and the relevance between the target disease and the target disease currently appearing by the user is higher, so that the relevance between the recommended medical information content determined based on the target disease and the target disease currently appearing by the user is higher. The recommended medical information content can effectively aim at the diseases actually suffered by the user, and the recommendation effectiveness is high.
Still another exemplary embodiment of the present disclosure provides an apparatus for recommending medical information content, as shown in fig. 5, the apparatus including:
a determining module 501, configured to determine a target condition input by a target account;
the determining module 501 is configured to determine at least one disease corresponding to the target disease based on a pre-stored correspondence between the disease and the disease;
the determining module 501 is configured to determine, among the at least one disease, a target disease that matches a previous disease recorded in the historical disease information corresponding to the target account;
and the recommending module 502 is used for determining the content of the medical information to be recommended based on the target disease.
Optionally, the recommending module 502 is configured to:
acquiring disease keywords included in each candidate medical information content;
and determining medical information contents to be recommended in the candidate medical information contents based on the target diseases and the disease keywords.
Optionally, the recommending module 502 is configured to:
determining a disease characteristic corresponding to the target account based on the target disease;
determining content characteristics corresponding to the candidate medical information contents respectively based on the disease keywords;
determining the similarity between the diseased features and the content features respectively;
and determining a first preset number of medical information contents to be recommended with the highest similarity in the candidate medical information contents.
Optionally, the similarity comprises a euclidean distance, a manhattan distance, a minkowski distance, or a pearson correlation coefficient.
Optionally, the recommending module 502 is configured to:
for each candidate medical information content, if the number of different disease identifiers included in the candidate medical information content is smaller than or equal to a preset threshold, determining the different disease identifiers as disease keywords, if the number of different disease identifiers included in the candidate medical information content is larger than the preset threshold, determining the occurrence times corresponding to the different disease identifiers respectively, and determining a second preset number of disease identifiers with the largest occurrence times as the disease keywords.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Even though different diseases may be accompanied by the same disease, the device provided by the embodiment of the disclosure can determine the target disease which is likely to relapse again currently based on the target disease input by the target account and the previous disease recorded in the historical disease information corresponding to the target account, the correlation between the target disease and the target disease currently appearing by the user is high, and further the correlation between the recommended medical information content determined based on the target disease and the target disease currently appearing by the user is high. The recommended medical information content can effectively aim at the diseases actually suffered by the user, and the recommendation effectiveness is high.
It should be noted that: in the device for recommending medical information content according to the above embodiment, when recommending medical information content, only the division of the above functional modules is taken as an example, in practical application, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the server is divided into different functional modules, so as to complete all or part of the above described functions. In addition, the apparatus for recommending medical information content and the method for recommending medical information content provided by the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiments and will not be described herein again.
Fig. 6 shows a schematic structural diagram of a server 1900 provided in an exemplary embodiment of the present disclosure. The server 1900 may have a large difference due to different configurations or performances, and may include one or more processors (CPUs) 1910 and one or more memories 1920. The memory 1920 stores at least one instruction, which is loaded and executed by the processor 1910 to implement the method for recommending medical information content according to the above embodiment.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for recommending medical information content, the method comprising:
determining a target condition input by a target account;
determining at least one disease corresponding to the target disease based on the corresponding relation between the pre-stored disease and the pre-stored disease;
determining a target disease matched with the previous disease recorded in the historical disease information corresponding to the target account in the at least one disease;
and determining the medical information content to be recommended based on the target disease.
2. The method of claim 1, wherein the determining the medical information content to be recommended based on the target disease comprises:
acquiring disease keywords included in each candidate medical information content;
and determining medical information contents to be recommended in the candidate medical information contents based on the target diseases and the disease keywords.
3. The method according to claim 2, wherein the determining of the medical information content to be recommended among the candidate medical information contents based on the target disease and the disease keyword comprises:
determining a disease characteristic corresponding to the target account based on the target disease;
determining content characteristics corresponding to the candidate medical information contents respectively based on the disease keywords;
determining the similarity between the diseased features and the content features respectively;
and determining a first preset number of medical information contents to be recommended with the highest similarity in the candidate medical information contents.
4. A method as claimed in claim 3, wherein said similarity comprises euclidean distance, manhattan distance, minkowski distance or pearson correlation coefficient.
5. The method of claim 2, wherein the obtaining of the disease keyword included in each candidate medical information content comprises:
for each candidate medical information content, if the number of different disease identifiers included in the candidate medical information content is smaller than or equal to a preset threshold, determining the different disease identifiers as disease keywords, if the number of different disease identifiers included in the candidate medical information content is larger than the preset threshold, determining the occurrence times corresponding to the different disease identifiers respectively, and determining a second preset number of disease identifiers with the largest occurrence times as the disease keywords.
6. An apparatus for recommending medical information content, the apparatus comprising:
a determination module for determining a target condition input by a target account;
the determining module is used for determining at least one disease corresponding to the target disease based on the corresponding relation between the pre-stored disease and the target disease;
the determining module is used for determining a target disease matched with the previous disease recorded in the historical disease information corresponding to the target account in the at least one disease;
and the recommending module is used for determining the medical information content to be recommended based on the target disease.
7. The apparatus of claim 6, wherein the recommendation module is configured to:
acquiring disease keywords included in each candidate medical information content;
and determining medical information contents to be recommended in the candidate medical information contents based on the target diseases and the disease keywords.
8. The apparatus of claim 7, wherein the recommendation module is configured to:
determining a disease characteristic corresponding to the target account based on the target disease;
determining content characteristics corresponding to the candidate medical information contents respectively based on the disease keywords;
determining the similarity between the diseased features and the content features respectively;
and determining a first preset number of medical information contents to be recommended with the highest similarity in the candidate medical information contents.
9. A server, comprising a processor, a communication interface, a memory, and a communication bus, wherein:
the processor, the communication interface and the memory complete mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute the program stored in the memory to implement the method steps of any of claims 1-5.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911323623.1A CN111079021B (en) | 2019-12-20 | 2019-12-20 | Method, device, server and storage medium for recommending medical information content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911323623.1A CN111079021B (en) | 2019-12-20 | 2019-12-20 | Method, device, server and storage medium for recommending medical information content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111079021A true CN111079021A (en) | 2020-04-28 |
| CN111079021B CN111079021B (en) | 2023-09-19 |
Family
ID=70316102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911323623.1A Active CN111079021B (en) | 2019-12-20 | 2019-12-20 | Method, device, server and storage medium for recommending medical information content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111079021B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102952A (en) * | 2020-08-24 | 2020-12-18 | 广州金域医学检验中心有限公司 | Method for identifying pathological category based on distance calculation method and related device |
| CN114242224A (en) * | 2021-12-28 | 2022-03-25 | 新瑞鹏宠物医疗集团有限公司 | Doctor recommendation method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129526A (en) * | 2011-04-02 | 2011-07-20 | 中国医学科学院医学信息研究所 | Public-oriented method and system for medical treatment guide-type self-help triage registering |
| US20150227708A1 (en) * | 2012-08-31 | 2015-08-13 | Samsung Electronics Co., Ltd. | Method and apparatus for personal medical treatment using mobile terminal |
| CN106548431A (en) * | 2016-10-14 | 2017-03-29 | 杭州伯仲信息科技有限公司 | A kind of patient propaganda and education course pushes platform and method for pushing |
| CN106991284A (en) * | 2017-03-31 | 2017-07-28 | 南华大学 | Intelligent child-rearing knowledge services method and system |
| CN107133487A (en) * | 2017-06-21 | 2017-09-05 | 深圳市海威达信息技术有限公司 | A kind of disease prevention and cure method, device and disease prevention and cure system |
| CN109166605A (en) * | 2018-07-27 | 2019-01-08 | 重庆柚瓣家科技有限公司 | Old man's system for distribution of out-patient department and method based on AI |
| US20190027254A1 (en) * | 2017-07-19 | 2019-01-24 | Fujifilm Corporation | Medical information providing apparatus, operation method of medical information providing apparatus, and medical information providing program |
| CN109599168A (en) * | 2018-10-15 | 2019-04-09 | 平安科技（深圳）有限公司 | Medical service method, device, computer equipment and storage medium |
| US20190259070A1 (en) * | 2016-10-20 | 2019-08-22 | Suzhou Deepleaper Information And Technology Company Limited | Advertising information pushing method, device and system, server, and computer readable medium |
| CN110534206A (en) * | 2019-08-26 | 2019-12-03 | 北京好医生云医院管理技术有限公司 | A kind of working method of medical diagnosis auxiliary system |
-
2019
- 2019-12-20 CN CN201911323623.1A patent/CN111079021B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129526A (en) * | 2011-04-02 | 2011-07-20 | 中国医学科学院医学信息研究所 | Public-oriented method and system for medical treatment guide-type self-help triage registering |
| US20150227708A1 (en) * | 2012-08-31 | 2015-08-13 | Samsung Electronics Co., Ltd. | Method and apparatus for personal medical treatment using mobile terminal |
| CN106548431A (en) * | 2016-10-14 | 2017-03-29 | 杭州伯仲信息科技有限公司 | A kind of patient propaganda and education course pushes platform and method for pushing |
| US20190259070A1 (en) * | 2016-10-20 | 2019-08-22 | Suzhou Deepleaper Information And Technology Company Limited | Advertising information pushing method, device and system, server, and computer readable medium |
| CN106991284A (en) * | 2017-03-31 | 2017-07-28 | 南华大学 | Intelligent child-rearing knowledge services method and system |
| CN107133487A (en) * | 2017-06-21 | 2017-09-05 | 深圳市海威达信息技术有限公司 | A kind of disease prevention and cure method, device and disease prevention and cure system |
| US20190027254A1 (en) * | 2017-07-19 | 2019-01-24 | Fujifilm Corporation | Medical information providing apparatus, operation method of medical information providing apparatus, and medical information providing program |
| CN109166605A (en) * | 2018-07-27 | 2019-01-08 | 重庆柚瓣家科技有限公司 | Old man's system for distribution of out-patient department and method based on AI |
| CN109599168A (en) * | 2018-10-15 | 2019-04-09 | 平安科技（深圳）有限公司 | Medical service method, device, computer equipment and storage medium |
| CN110534206A (en) * | 2019-08-26 | 2019-12-03 | 北京好医生云医院管理技术有限公司 | A kind of working method of medical diagnosis auxiliary system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102952A (en) * | 2020-08-24 | 2020-12-18 | 广州金域医学检验中心有限公司 | Method for identifying pathological category based on distance calculation method and related device |
| CN112102952B (en) * | 2020-08-24 | 2024-05-14 | 广州金域医学检验中心有限公司 | Method for identifying pathology category based on distance calculation method and related equipment |
| CN114242224A (en) * | 2021-12-28 | 2022-03-25 | 新瑞鹏宠物医疗集团有限公司 | Doctor recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111079021B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021073277A1 (en) | Personalized precise medication recommendation method and apparatus | |
| WO2019153504A1 (en) | Group creation method and terminal thereof | |
| US20120281910A1 (en) | Detecting facial similarity based on human perception of facial similarity | |
| CN112035741B (en) | Reservation method, device, equipment and storage medium based on user physical examination data | |
| CN110838359B (en) | Diagnosis method and device based on dialogue robot, storage medium and robot | |
| CN111079021B (en) | Method, device, server and storage medium for recommending medical information content | |
| EP4071765A1 (en) | Method and system for drawing brain functional atlas | |
| CN112420141B (en) | Traditional Chinese medicine health evaluation system and application thereof | |
| CN111091906A (en) | Auxiliary medical diagnosis method and system based on real world data | |
| CN114065856B (en) | Doctor recommendation method, device and equipment based on doctor portrait and storage medium | |
| CN112164451A (en) | Intelligent diagnosis guiding and registering method, device, equipment and storage medium | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN111476029A (en) | Resource recommendation method and device | |
| US20220207242A1 (en) | Method for testing medical data | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN111428070A (en) | Ophthalmologic case retrieval method, ophthalmologic case retrieval device, ophthalmologic case retrieval server and storage medium | |
| US7200612B2 (en) | processing data for interpretation | |
| CN110752027A (en) | Electronic medical record data pushing method and device, computer equipment and storage medium | |
| Li et al. | PLDGAN: portrait line drawing generation with prior knowledge and conditioning target | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| CN113032621A (en) | Data sampling method and device, computer equipment and storage medium | |
| CN111104481B (en) | Method, device and equipment for identifying matching field | |
| CN114822800A (en) | Internet medical triage method and system | |
| CN115130493A (en) | Face deformation recommendation method, device, equipment and medium based on image recognition | |
| KR20100103098A (en) | Online client diagnosis system and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40021981 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |