CN108122611B - Information recommendation method and device, storage medium and program product - Google Patents
Information recommendation method and device, storage medium and program product Download PDFInfo
- Publication number
- CN108122611B CN108122611B CN201711407945.5A CN201711407945A CN108122611B CN 108122611 B CN108122611 B CN 108122611B CN 201711407945 A CN201711407945 A CN 201711407945A CN 108122611 B CN108122611 B CN 108122611B
- Authority
- CN
- China
- Prior art keywords
- information
- symptom
- symptom information
- disease
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the application discloses an information recommendation method, which is used for recommending corresponding medical resource information for a user, and comprises the following steps: establishing an ontology knowledge base, wherein the ontology knowledge base comprises a corresponding relation between symptom information and disease information; acquiring symptom information input by a user, and taking the symptom information input by the user as specified symptom information; calculating the correlation degree of the disease information and the designated symptom information according to the ontology knowledge base; and determining disease information with the correlation degree meeting preset conditions from the disease information as target information, wherein the target information is used for recommending corresponding medical resource information to the user.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to an information recommendation method, apparatus, storage medium, and program product.
Background
The services such as reservation registration, payment and the like based on the Internet or the mobile Internet provide in-hospital treatment services for the patients facing the designated hospital, reduce the queuing waiting time of the patients and realize the disclosure and fairness of medical resources. However, when a patient needs to visit which department, the patient needs to make a decision by himself or seek manual diagnosis guide service of the hospital.
Therefore, the existing reservation registration service based on the internet or the mobile internet is not really realized to recommend proper medical resources to the patient, which possibly causes the patient to delay the best treatment time and even to be treated by mistake.
Disclosure of Invention
In view of this, embodiments of the present application provide an information recommendation method and apparatus, a storage medium, and a program product, so as to solve the technical problem in the prior art that medical resources cannot be effectively recommended to a user.
In order to solve the above problem, the technical solution provided by the embodiment of the present application is as follows:
an information recommendation method establishes an ontology knowledge base, wherein the ontology knowledge base comprises a corresponding relation between symptom information and disease information, and the method comprises the following steps:
acquiring symptom information input by a user, wherein the symptom information input by the user is used as appointed symptom information;
calculating the correlation degree of the disease information and the appointed symptom information according to the ontology knowledge base;
and determining the disease information with the correlation degree meeting a preset condition from the disease information as target information, wherein the target information is used for recommending corresponding medical resource information to the user.
Optionally, the method further includes:
and calculating related symptom information according to the symptom information input by the user, and recommending the related symptom information to the user.
Optionally, the calculating related symptom information according to the symptom information input by the user includes:
searching a set of all disease information which has a corresponding relation with the symptom information input by the user from the ontology knowledge base to be used as a first disease information set;
searching a set of symptom information having a corresponding relation with the disease information in the first disease information set from the ontology knowledge base as a first symptom information set;
and sorting the symptom information in the first symptom information set in a descending order according to the weight of each symptom information in the first symptom information set to obtain a sorting result, and determining related symptom information according to the sorting result, wherein the weight of each symptom information is inversely proportional to the quantity of disease information corresponding to the symptom information.
Optionally, the method further includes:
acquiring symptom information selected by a user from the related symptom information, and taking the symptom information input by the user and the symptom information selected by the user from the related symptom information as specified symptom information;
calculating the correlation degree of the disease information and the appointed symptom information according to the ontology knowledge base;
and determining target information with the correlation degree meeting preset conditions from the disease information, wherein the target information is used for recommending corresponding medical resource information to the user.
Optionally, the calculating, according to the ontology knowledge base, a correlation between the disease information and the designated symptom information includes:
and calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base and the weight of each symptom information in the ontology knowledge base, wherein the weight of each symptom information is inversely proportional to the quantity of the disease information corresponding to the symptom information.
Optionally, the calculating, according to the ontology knowledge base and the weight of each symptom information in the ontology knowledge base, a correlation between the disease information and the designated symptom information includes:
searching a set of all disease information having a corresponding relation with the specified symptom information from the ontology knowledge base as a second disease information set;
searching a set of symptom information having a corresponding relation with any disease information in the second disease information set from the ontology knowledge base as a second symptom information set;
taking intersection of the second symptom information set and the specified symptom information to obtain a third symptom information set;
calculating the sum of the weights of all the symptom information in the third symptom information set, and as a first result, calculating the sum of the weights of all the symptom information in the second symptom information set, and as a second result, the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information;
calculating a ratio of the first result and the second result as a degree of correlation of the disease information with the specified symptom information.
Optionally, the correspondence between the symptom information and the disease information is stored in the ontology knowledge base in the form of a graph model.
An information recommendation apparatus, the apparatus comprising:
the system comprises an establishing unit, a judging unit and a judging unit, wherein the establishing unit is used for establishing an ontology knowledge base, and the ontology knowledge base comprises a corresponding relation between symptom information and disease information;
a first acquisition unit configured to acquire symptom information input by a user, the symptom information input by the user being designated symptom information;
the first calculating unit is used for calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base;
the first determining unit is used for determining the disease information with the correlation degree meeting a preset condition from the disease information as target information, and the target information is used for recommending corresponding medical resource information to the user.
Optionally, the apparatus further comprises:
the second calculating unit is used for calculating related symptom information according to the symptom information input by the user;
and the recommending unit is used for recommending the related symptom information to the user.
Optionally, the second computing unit includes:
the first searching subunit is used for searching a set of all disease information which has a corresponding relation with the symptom information input by the user from the ontology knowledge base to serve as a first disease information set;
the second searching subunit is used for searching a set of symptom information which has a corresponding relation with the disease information in the first disease information set from the ontology knowledge base to serve as the first symptom information set;
and the sorting subunit is configured to sort, in a descending order, the symptom information in the first symptom information set according to the weight of each symptom information in the first symptom information set to obtain a sorting result, and determine related symptom information according to the sorting result, where the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information.
Optionally, the apparatus further comprises:
a second acquisition unit configured to acquire symptom information selected by a user from the related symptom information, and to take the symptom information input by the user and the symptom information selected by the user from the related symptom information as specified symptom information;
the third calculating unit is used for calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base;
and the second determining unit is used for determining target information with the correlation degree meeting a preset condition from the disease information, and the target information is used for recommending corresponding medical resource information to the user.
Optionally, the first calculating unit is specifically configured to calculate a degree of correlation between the disease information and the specified symptom information according to the ontology knowledge base and a weight of each piece of symptom information in the ontology knowledge base, where the weight of each piece of symptom information is inversely proportional to a quantity of the disease information corresponding to the symptom information.
Optionally, the first computing unit includes:
a third searching subunit, configured to search, from the ontology knowledge base, a set of all disease information having a corresponding relationship with the specified symptom information as a second disease information set;
a fourth searching subunit, configured to search, from the ontology knowledge base, a set of symptom information having a correspondence relationship with any disease information in the second disease information set as a second symptom information set;
the acquisition subunit is configured to acquire an intersection of the second symptom information set and the specified symptom information to acquire a third symptom information set;
a first calculating subunit, configured to calculate a sum of weights of each piece of symptom information in the third symptom information set, as a first result, calculate a sum of weights of each piece of symptom information in the second symptom information set, as a second result, where the weight of each piece of symptom information is inversely proportional to the number of pieces of disease information corresponding to the piece of symptom information;
and a second calculating subunit, configured to calculate a ratio of the first result and the second result as a degree of correlation between the disease information and the designated symptom information.
Optionally, the correspondence between the symptom information and the disease information is stored in the ontology knowledge base in the form of a graph model.
A computer-readable storage medium having stored therein instructions which, when run on a terminal device, cause the terminal device to execute the above-mentioned information recommendation method.
A computer program product, which, when running on a terminal device, causes the terminal device to execute the above-mentioned information recommendation method.
Therefore, the embodiment of the application has the following beneficial effects:
according to the embodiment of the application, the ontology knowledge base comprising the corresponding relation between the symptom information and the disease information is established in advance, after the symptom information input by the user is obtained, the correlation degree between each piece of disease information and the symptom information input by the user can be calculated according to the ontology knowledge base, the target information can be determined from each piece of disease information according to the correlation degree, the target information can prompt the disease information possibly corresponding to the symptom information input by the user, and the medical resource information can be further recommended to the user according to the target information, for example, which hospital department the user should go to for a doctor is recommended to the user, so that the medical resource is recommended to the user.
Drawings
Fig. 1 is an exemplary diagram of an application scenario of an information recommendation method according to an embodiment of the present application;
fig. 2 is a flowchart of an information recommendation method according to an embodiment of the present application;
FIG. 3 is an exemplary diagram of an ontology repository provided by an embodiment of the present application;
fig. 4 is an exemplary diagram of a display interface for determining target information on a terminal device according to an embodiment of the present application;
FIG. 5 is a flowchart of a method for calculating relevancy according to an embodiment of the present disclosure;
fig. 6a is a diagram illustrating a relationship between a weight of each symptom information and a quantity of disease information corresponding to the symptom information provided in an embodiment of the present application;
FIG. 6b is a diagram of an example of weights for various symptom information provided by an embodiment of the present application;
FIG. 7 is a flowchart of a method for calculating relevant symptom information according to an embodiment of the present disclosure;
fig. 8 is an exemplary diagram of a display interface for determining target information on a terminal device according to an embodiment of the present application;
fig. 9 is a block diagram of an information recommendation device according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanying the drawings are described in detail below.
In the existing reservation registration service based on the internet or the mobile internet, medical resource information such as hospitals and departments is generally directly provided for users to select, and the user generally needs to make a decision by himself or herself on which kind of medical resource information is selected, so that proper medical resources cannot be recommended to the user. Therefore, the existing reservation registration service based on the internet or the mobile internet is not really realized to recommend proper medical resources to the user, so that the user may delay the best treatment opportunity and even may be mistakenly diagnosed and treated.
Therefore, embodiments of the present application provide an information recommendation method, an information recommendation apparatus, a storage medium, and a program product, so as to solve the technical problem in the prior art that medical resources cannot be effectively recommended to a user, and implement determining disease information corresponding to specified symptom information and recommending medical resource information corresponding to the disease information to the user, so that the user can find a suitable medical resource for a medical treatment.
The method provided by the embodiment of the Application can be applied to terminal equipment with data processing capability, for example, the method can be realized through an APP (Application program) on the terminal equipment, and can also be realized through a computer; the method of the embodiment can also be completed by a server, and the terminal equipment displays each result obtained by the server to a user; the method of the embodiment of the present application may also be implemented by using a server to interact with a terminal device, which is not limited in the embodiment of the present application.
Referring to fig. 1, fig. 1 shows an application scenario of the embodiment of the present application. In this application scenario, an ontology knowledge base is pre-established in the server 103, and the ontology knowledge base includes a corresponding relationship between symptom information and disease information. The user 101 may input symptom information in APP on the terminal device 102, the server 103 may obtain the symptom information input by the user, use the symptom information input by the user as specified symptom information, calculate a degree of correlation between the disease information and the specified symptom information according to the ontology knowledge base, and determine target information from each disease information according to the degree of correlation. The terminal device 102 may obtain the target information for display, and the target information may prompt the user to input possible corresponding disease information, so that the terminal device 102 may further recommend medical resource information to the user according to the target information. A presentation interface in which the terminal device 102 presents the target information to the user may be shown as 104 in fig. 1.
It should be noted that the above application scenarios are only presented to facilitate understanding of the present invention, and the embodiments of the present invention are not limited in any way in this respect. Rather, embodiments of the present invention may be applied to any scenario where applicable.
Various non-limiting embodiments of the present invention are described in detail below with reference to the accompanying drawings.
An information recommendation method provided in an embodiment of the present application is shown in fig. 2, which is a flowchart illustrating the information recommendation method provided in the embodiment of the present application, and may include the following steps:
step 201: acquiring symptom information input by a user, and taking the symptom information input by the user as specified symptom information.
The user may input at least one piece of symptom information according to the condition of the user, and the symptom information input by the user may be used as the designated symptom information, that is, in this embodiment, the at least one piece of designated symptom information may be included.
Since the method provided by this embodiment can be implemented based on the ontology knowledge base, before the method provided by this embodiment is executed, the ontology knowledge base may be pre-established, where the ontology knowledge base includes a corresponding relationship between the symptom information and the disease information, so as to determine the disease information corresponding to the specified symptom information according to the ontology knowledge base.
It should be noted that, in the embodiment of the present invention, the disease information, the symptom information, and the relationship data between the disease information and the symptom information may be obtained through various ways, so that an ontology base of the disease information and the symptom information may be established according to the disease information, the symptom information, and the relationship data, and the expression form of the ontology base may be as shown in fig. 3.
The ontology knowledge base may describe the corresponding relationship between the disease information and the symptom information, for example, the symptom information "wasting", "polydipsia", "diuresis" and "polyphagia" shown in fig. 3 respectively have a corresponding relationship with the disease information "type 1 diabetes", and are described by using a Resource Description Framework (RDF), and each corresponding relationship may be represented by a connecting line with an arrow in fig. 3.
The ontology knowledge base can also describe classification relations of disease information and symptom information, for example, the disease information "type 1 diabetes", "insulin dependent diabetes", and the like shown in fig. 3 belong to diabetes in classification, and are described by using RDF; the disease information "diabetes" pertains to diseases of the endocrine and metabolic systems in categories, described in the language of RDF vocabulary definition (RDF Schema, RDFs for short), and each category relationship can be represented by a line with an arrow in fig. 3.
The Ontology knowledge base may also describe the synonymous relationship between disease information or the synonymous relationship between symptom information, for example, the disease information "type 1 diabetes" and the disease information "insulin dependent diabetes" shown in fig. 3 are synonymous relationships, and the symptom information "headache", "headache" and "headache" are synonymous relationships, and are described using Web Ontology Language (OWL), and each synonymous relationship may be represented by a connecting line with an arrow in fig. 3.
It can be understood that, in order to facilitate searching for the corresponding relationship between the symptom information and the disease information in the ontology knowledge base, so that the corresponding disease information can be quickly determined according to the symptom information input by the user, and the searching efficiency is improved.
Step 202: and calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base.
Since the ontology knowledge base includes the corresponding relationship between the symptom information and the disease information, the disease information corresponding to the specified symptom information can be determined according to the corresponding relationship between the symptom information and the disease information in the ontology knowledge base. Generally, the determined disease information corresponding to the specified symptom information may include a plurality of pieces of information, and the relevance between different pieces of disease information and the specified symptom information may be different, so that the suitability of the medical resource information recommended to the user according to different pieces of disease information is different, for example, the greater the relevance between the disease information and the specified symptom information is, the more suitable the medical resource information recommended to the user according to the disease information and corresponding to the disease information is. For this, the degree of correlation of the disease information with the specified symptom information may be calculated so as to determine the disease information used for recommending the medical resource information to the user based on the degree of correlation.
The implementation of calculating the correlation between the disease information and the specific symptom information will be described in detail in the following embodiments. ,
step 203: and determining the disease information with the correlation degree meeting a preset condition from the disease information as target information, wherein the target information is used for recommending corresponding medical resource information to the user.
After the correlation degree is calculated, the disease information with the correlation degree meeting the preset condition can be determined from all the disease information with the corresponding relation with the specified symptom information as target information according to the correlation degree, and the terminal equipment can display the target information to the user so as to recommend corresponding medical resource information to the user according to the target information.
One implementation manner of determining, as target information, disease information whose degree of correlation satisfies a preset condition from the disease information may be: after the correlation degree is obtained through calculation, whether the correlation degree reaches a first threshold value is judged, and if the correlation degree reaches the first threshold value, disease information corresponding to the correlation degree is used as target information. Wherein the first threshold may be set empirically.
For example, in step 202, it is calculated that the degree of correlation between the disease information a and the designated symptom information is 33%, the degree of correlation between the disease information B and the designated symptom information is 26%, the degree of correlation between the disease information C and the designated symptom information is 20%, and the first threshold value is 25%. By the judgment of the respective degrees of correlation, 33% is greater than the first threshold value by 25%, 26% is greater than the first threshold value by 25%, and 20% is less than the first threshold value by 25%, and therefore, it can be determined that the disease information a and the disease information B can be targeted information.
Another implementation manner of determining, as target information, disease information whose degree of correlation satisfies a preset condition from the disease information may be: after the correlation degree is obtained through calculation, the disease information is sequenced according to the correlation degree from large to small, the serial number of the disease information in the sequence is obtained, and the disease information with the serial number smaller than a second threshold value is determined from the disease information and serves as target information. Wherein the second threshold may be set empirically.
Continuing with the example where the correlation between the disease information a and the designated symptom information obtained in the above is 33%, the correlation between the disease information B and the designated symptom information is 26%, and the correlation between the disease information C and the designated symptom information is 20%, since 33% is greater than 26% and 26% is greater than 20%, the disease information may be arranged in the sequence: the disease information a, the disease information B, and the disease information C are numbered 1, 2, and 3 in the sequence, and if the second threshold is 3, the disease information a and the disease information B having a number smaller than 3 can be specified as the target information.
The presentation interface for determining the target information on the terminal device provided in this embodiment may be as shown in fig. 4, where 401 indicates that the symptom information input by the user is "dyspepsia", 403 indicates possible target information, and in addition, the correlation corresponding to each target information may be displayed by a dashed box in 403.
In addition, it should be noted that the target information obtained in the embodiment of the present application does not represent the health condition of the user, and the target information is used for recommending the corresponding medical resource information to the user so as to guide the user to visit a corresponding medical institution.
According to the embodiment of the application, the ontology knowledge base comprising the corresponding relation between the symptom information and the disease information is established in advance, after the symptom information input by the user is obtained, the correlation degree between each piece of disease information and the symptom information input by the user can be calculated according to the ontology knowledge base, the target information can be determined from each piece of disease information according to the correlation degree, the target information can prompt the disease information possibly corresponding to the symptom information input by the user, and the medical resource information can be further recommended to the user according to the target information, for example, which hospital department the user should go to for a doctor is recommended to the user, so that the medical resource is recommended to the user.
In the related art, the correlation between the disease information and the designated symptom information is measured mainly according to the number of the designated symptom information which can be matched with each disease information, so that the disease information corresponding to the designated symptom information is determined. For example, the user provides 5 pieces of specified symptom information, assuming certain disease information D14 pieces of the prescribed symptom information are matched, and the other disease information D2Matching 3 pieces of designated symptom information, visible disease information D1Matched fingerThe amount of symptom information is more than that of disease information D2The number of matching specified symptom information, then the disease information D is considered1The degree of correlation with the designated symptom information is higher than that of the disease information D2The degree of correlation with the designated symptom information, and therefore, it may be determined that the disease information corresponding to the 5 pieces of designated symptom information is D1Probability ratio of (D)2If large, the user may be recommended with the disease information D1Corresponding medical resource information.
However, in the method of measuring the degree of correlation between disease information and designated symptom information provided in the related art, the importance of each designated symptom information to determining disease information is the same, but this is not the case. In some cases, many different disease information may correspond to the same symptom information, but the importance of the symptom information to the different disease information may be different. If the disease information has a corresponding relationship with symptom information having a higher importance among the specified symptom information, the disease information is more likely to be the disease information corresponding to the specified symptom information, and medical resource information recommended to the user according to the disease information may be more appropriate.
For example, in the above example, the disease information D1The matched 4 pieces of designated symptom information may all be pieces of symptom information having very little importance for determining the disease information, and the disease information D2The matching 3 pieces of specified symptom information may all be pieces of symptom information having great importance for determining the disease information, and thus, may result in D2The degree of correlation with the designated symptom information is higher than that of the disease information D1Degree of correlation with prescribed symptom information, disease information D2More likely to be disease information corresponding to the designated symptom information, and the disease information D should be recommended to the user2Corresponding medical resource information.
Therefore, the method for calculating the correlation degree of the disease information and the specified symptom information according to the number of the specified symptom information which can be matched with each piece of disease information in the related technology may cause that the determined disease information is inaccurate, and further cause that the medical resource information recommended to the user is not appropriate.
To this end, one possible implementation of calculating the correlation in step 202 may be: and calculating the correlation between the disease information and the designated symptom information according to the ontology base and the weight of each symptom information in the ontology base, wherein the weight of each symptom information is inversely proportional to the number of the disease information corresponding to the symptom information, the weight of each symptom information can represent the importance of the symptom information to the determination of the disease information, and the larger the weight of each symptom information is, the higher the importance of the symptom information to the determination of the disease information is.
Based on the information recommendation method provided in the foregoing, referring to fig. 5, a flowchart illustrating a method for calculating a correlation between the disease information and the specified symptom information according to the ontology knowledge base and weights of each symptom information in the ontology knowledge base provided in the embodiment of the present application is shown, and may include the following steps:
step 501: and searching a set of all disease information having a corresponding relation with the specified symptom information from the ontology knowledge base to serve as a second disease information set.
Step 502: and searching a set of symptom information having a corresponding relation with any disease information in the second disease information set from the ontology knowledge base to serve as a second symptom information set.
Step 503: and taking intersection of the second symptom information set and the symptom information input by the user to obtain a third symptom information set.
Step 504: and calculating the sum of the weights of the symptom information in the third symptom information set, and as a first result, calculating the sum of the weights of the symptom information in the second symptom information set, wherein as a second result, the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information.
Generally, one symptom information can correspond to a plurality of disease information, if the symptom information includes "headache", which is a symptom information that many disease information may correspond to, it is difficult to determine the disease information that the symptom information may correspond to based on "headache", so that it is less important to determine the disease information corresponding to the symptom information, and the weight of the symptom information can be smaller; if the symptom information includes "bloody nasal discharge", since "bloody nasal discharge" appears in only a few disease information, the symptom information can be taken as typical symptom information of the several disease information, and the importance for determining the disease information corresponding to the symptom information is large, the weight of the symptom information can be large.
Thus, the weight of each symptom information is related to the number of disease information corresponding to the symptom information, for example, the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information, as shown in fig. 6a, where the abscissa N is the abscissasThe number of disease information items corresponding to the symptom information, and the ordinate WsIndicating a weight associated with the symptom information.
In order to ensure that the weight of each symptom information is inversely proportional to the number of the disease information corresponding to the symptom information, the weight of each symptom information can be directly set for each symptom information according to experience and stored in the ontology knowledge base; the weight of each symptom information may be calculated by using the number of disease information corresponding to the symptom information based on the ontology knowledge base.
As an example, a formula for calculating the weight of the symptom information using the number of disease information corresponding to the symptom information may be as follows:
wherein s represents a symptom information, WsRepresents the weight of the symptom information, N represents the total number of disease information included in the ontology knowledge base, NsIndicates the number of disease information including the symptom information s.
The calculated weights of the symptom information may be stored in a list form on the server or the terminal device, as shown in fig. 6b, wherein the numerical values in the dashed box may represent the weights of the symptom information, and may be modified. Of course, the weight of each symptom information may also be calculated in real time in the information recommendation process.
Step 505: calculating a ratio of the first result and the second result as a degree of correlation of the disease information with the specified symptom information.
For example, the set of all symptoms entered by the user is S1={s1,s2,…sv,…,smD, a set D of all disease information in the ontology knowledge base, which has a corresponding relationship with the designated symptom information1={d1,d2,…dk,…,dlAnd taking the set as a second disease information set. For set D1={d1,d2,…dk,…,dlCertain disease information d in }kSearching and disease information d from ontology knowledge basekIs SdkAs a second symptom information set, the second symptom information set S is setdkWherein the set of symptom information belonging to the designated symptom information is the third symptom information set S'dk. Calculating S'dkAs a first result, and calculates SdkThe sum of the weights of the respective symptom information as a second result. Finally, the disease information d is obtained by calculating the ratio of the first result and the second resultkCorrelation with the specified symptom information.
Calculating disease information dkDegree of correlation r with prescribed symptom informationdkThe formula of (a) can be as follows:
wherein r isdkRepresents disease information dkDegree of correlation with given symptom information, S ∈ SdkIndicating belonging to a second set S of symptom informationdkS ∈ S'dkRepresents belonging to a third symptom information set S'dkInformation on symptoms in (1), wsA weight representing the information of each symptom is given,wsmeans for calculating a sum of weights of respective symptom information in the third symptom information set,the sum of the weights of the symptom information in the second symptom information set is calculated.
In the embodiment, when the correlation between the disease information and the symptom information is calculated, the importance of each symptom information to the disease information is considered, and the importance of each symptom information to the disease information is expressed by using the weight of each symptom information, so that the correlation between the disease information and the symptom information can be more accurately determined, the target information can be accurately determined, and more appropriate medical resource information can be recommended to the user.
After the target information is determined by taking the symptom information input by the user as the specified symptom information, in some cases, the symptom information input by the user may be only partial symptom information or the symptom information input by the user is not typical symptom information, so that when the disease information corresponding to the specified information is determined, the specified symptom information is more comprehensive and can reflect the typical symptom information of the disease information, the disease information corresponding to the specified symptom information can be determined more accurately, and more appropriate medical resource information is recommended for the user.
In the embodiment of the application, after the symptom information input by the user is obtained, the related symptom information can be calculated according to the symptom information input by the user, so that when the target information is displayed to the user, the related symptom information is recommended to the user, the user can select from the related symptom information, the appointed symptom information is adjusted according to the selected related symptom information, the target information is re-determined, and more appropriate medical resource information is recommended to the user.
Referring to fig. 7, a flowchart illustrating a method for calculating related symptom information provided in an embodiment of the present application is shown, which may include the following steps:
step 701: and searching a set of all disease information having a corresponding relation with the symptom information input by the user from the ontology knowledge base to be used as a first disease information set.
Step 702: and searching a set of symptom information having a corresponding relation with the disease information in the first disease information set from the ontology knowledge base to serve as a first symptom information set.
Step 703: and sorting the symptom information in the first symptom information set in a descending order according to the weight of each symptom information in the first symptom information set to obtain a sorting result, and determining related symptom information according to the sorting result, wherein the weight of each symptom information is inversely proportional to the quantity of disease information corresponding to the symptom information.
In this embodiment, for example, when the symptom information input by the user is the symptom information s, and the relevant symptom information is calculated from the symptom information s, first, the set of all disease information having a correspondence relationship with the symptom information s is searched from the ontology repository as D2={d1,d2,…dj,…,dpAs a first set of disease information. Then, for the first disease information set D2Searching the symptom information corresponding to the disease information in the first disease information set from the ontology knowledge base, and if the symptom information is directed at d1The searched symptom information is s1、s2In respect of d2The searched symptom information is s1、…s2、siIn respect of djThe searched symptom information is s1、…,sqSimilarly, the symptom information corresponding to each disease information is searched, and a first symptom information set is formed by using all the searched symptom information, where the first symptom information set may be S2={s1,s2,…si,…,sq}. Then, according to the first symptom information set S2={s1,s2,…si,…,sqWeight of each symptom information in }And sorting each symptom information in the first symptom information set in a descending order to obtain a sorting result, and determining related symptom information according to the sorting result.
It can be understood that, in this embodiment, the symptom information may be ranked from large to small according to the weight of each symptom information, and the obtained ranking result is s1,s2,…si,…,sqIf the symptom information s appears when the symptom information s is selected, the symptom information s is skipped, and continuous selection is continued backwards until the first N pieces of symptom information are selected.
For example, if N can take 6, s will be1,s2,…si,…,sqSymptom information s ranked in top 61、s2、s3、s4、s5And s6As related symptom information, recommending to the user so that the user can obtain the symptom information s1、s2、s3、s4、s5And s6Selects symptom information matching the user.
It should be noted that, in the present embodiment, the manner of obtaining the weight of each symptom information is described in detail in the foregoing step 504, and is not described herein again.
After obtaining the relevant symptom information, the user may be presented with the relevant symptom information, and a presentation interface of the relevant symptom information may be shown as 402 in fig. 4.
The user can select the symptom information matched with the user from the related symptom information according to the condition of the user, as shown in 802 in fig. 8, and the user needs to select the symptom information of postpartum digestive system symptom and skin yellowing from the related symptom information shown in 402. Then, according to the symptom information selected by the user from the related symptom information, the method described in step 202 to step 203 is executed again, with the symptom information input by the user and the symptom information selected by the user from the related symptom information as the designated symptom information. The resulting target information is shown as 803 in fig. 8, and the correlation of each target information with the specified symptom information is given. Comparing the target information shown in 803 with that shown in 403, it can be seen that in the present embodiment, the target information and the correlation degree between each target information and the designated symptom information are adjusted by using the symptom information selected by the user from the related symptom information, so that more accurate target information is presented to the user.
For specific implementation manners of step 202 and step 203, reference may be made to the foregoing embodiments, which are not described herein again.
Based on the foregoing provided information recommendation method, an embodiment of the present application further provides an information recommendation apparatus, as shown in fig. 9, fig. 9 shows a structural block diagram of an apparatus for implementing information recommendation, where the apparatus includes a creating unit 901, a first obtaining unit 902, a first calculating unit 903, and a first determining unit 904:
the establishing unit 901 is configured to establish an ontology knowledge base, where the ontology knowledge base includes a corresponding relationship between symptom information and disease information;
the first obtaining unit 902 is configured to obtain symptom information input by a user, and use the symptom information input by the user as specified symptom information;
the first calculating unit 903 is configured to calculate a correlation between the disease information and the designated symptom information according to the ontology knowledge base;
the first determining unit 904 is configured to determine, from the disease information, disease information with the correlation degree satisfying a preset condition as target information, where the target information is used to recommend corresponding medical resource information to the user.
Optionally, the apparatus further comprises:
the second calculating unit is used for calculating related symptom information according to the symptom information input by the user;
and the recommending unit is used for recommending the related symptom information to the user.
Optionally, the second computing unit includes:
the first searching subunit is used for searching a set of all disease information which has a corresponding relation with the symptom information input by the user from the ontology knowledge base to serve as a first disease information set;
the second searching subunit is used for searching a set of symptom information which has a corresponding relation with the disease information in the first disease information set from the ontology knowledge base to serve as the first symptom information set;
and the sorting subunit is configured to sort, in a descending order, the symptom information in the first symptom information set according to the weight of each symptom information in the first symptom information set to obtain a sorting result, and determine related symptom information according to the sorting result, where the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information.
Optionally, the apparatus further comprises:
a second acquisition unit configured to acquire symptom information selected by a user from the related symptom information, and to take the symptom information input by the user and the symptom information selected by the user from the related symptom information as specified symptom information;
the third calculating unit is used for calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base;
and the second determining unit is used for determining target information with the correlation degree meeting a preset condition from the disease information, and the target information is used for recommending corresponding medical resource information to the user.
Optionally, the first calculating unit is specifically configured to calculate a degree of correlation between the disease information and the specified symptom information according to the ontology knowledge base and a weight of each symptom information in the ontology knowledge base, where the weight of each symptom information is inversely proportional to a quantity of the disease information corresponding to the symptom information.
Optionally, the first computing unit includes:
a third searching subunit, configured to search, from the ontology knowledge base, a set of all disease information having a corresponding relationship with the specified symptom information as a second disease information set;
a fourth searching subunit, configured to search, from the ontology knowledge base, a set of symptom information having a correspondence relationship with any disease information in the second disease information set as a second symptom information set;
the acquisition subunit is configured to acquire an intersection of the second symptom information set and the specified symptom information to acquire a third symptom information set;
a first calculating subunit, configured to calculate a sum of weights of each piece of symptom information in the third symptom information set, as a first result, calculate a sum of weights of each piece of symptom information in the second symptom information set, as a second result, where the weight of each piece of symptom information is inversely proportional to the number of pieces of disease information corresponding to the piece of symptom information;
and a second calculating subunit, configured to calculate a ratio of the first result and the second result as a degree of correlation between the disease information and the designated symptom information.
Optionally, the correspondence between the symptom information and the disease information is stored in the ontology knowledge base in the form of a graph model.
According to the embodiment of the application, the ontology knowledge base comprising the corresponding relation between the symptom information and the disease information is established in advance, after the symptom information input by the user is obtained, the correlation degree between each piece of disease information and the symptom information input by the user can be calculated according to the ontology knowledge base, the target information can be determined from each piece of disease information according to the correlation degree, the target information can prompt the disease information possibly corresponding to the symptom information input by the user, and the medical resource information can be further recommended to the user according to the target information, for example, which hospital department the user should go to for a doctor is recommended to the user, so that the medical resource is recommended to the user.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the system or the device disclosed by the embodiment, the description is simple because the system or the device corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An information recommendation method is characterized in that an ontology knowledge base is established, the ontology knowledge base comprises a corresponding relation between symptom information and disease information, and the method comprises the following steps:
acquiring symptom information input by a user, wherein the symptom information input by the user is used as appointed symptom information;
calculating the correlation degree of the disease information and the appointed symptom information according to the ontology knowledge base;
the calculating the correlation degree of the disease information and the designated symptom information according to the ontology knowledge base comprises the following steps: calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base and the weight of each symptom information in the ontology knowledge base, wherein the weight of each symptom information is inversely proportional to the number of the disease information corresponding to the symptom information;
the calculating the correlation between the disease information and the designated symptom information according to the ontology knowledge base and the weight of each symptom information in the ontology knowledge base comprises:
searching a set of all disease information having a corresponding relation with the specified symptom information from the ontology knowledge base as a second disease information set;
searching a set of symptom information having a corresponding relation with any disease information in the second disease information set from the ontology knowledge base as a second symptom information set;
taking intersection of the second symptom information set and the specified symptom information to obtain a third symptom information set;
calculating the sum of the weights of all the symptom information in the third symptom information set, and as a first result, calculating the sum of the weights of all the symptom information in the second symptom information set, and as a second result, the weight of each symptom information is inversely proportional to the number of disease information corresponding to the symptom information;
calculating the ratio of the first result and the second result as the correlation degree of the disease information and the specified symptom information;
and determining the disease information with the correlation degree meeting a preset condition from the disease information as target information, wherein the target information is used for recommending corresponding medical resource information to the user.
2. The method of claim 1, further comprising:
and calculating related symptom information according to the symptom information input by the user, and recommending the related symptom information to the user.
3. The method of claim 2, wherein said calculating relevant symptom information from said user-entered symptom information comprises:
searching a set of all disease information which has a corresponding relation with the symptom information input by the user from the ontology knowledge base to be used as a first disease information set;
searching a set of symptom information having a corresponding relation with the disease information in the first disease information set from the ontology knowledge base as a first symptom information set;
and sorting the symptom information in the first symptom information set in a descending order according to the weight of each symptom information in the first symptom information set to obtain a sorting result, and determining related symptom information according to the sorting result, wherein the weight of each symptom information is inversely proportional to the quantity of disease information corresponding to the symptom information.
4. The method of claim 2, further comprising:
acquiring symptom information selected by a user from the related symptom information, and taking the symptom information input by the user and the symptom information selected by the user from the related symptom information as specified symptom information;
calculating the correlation degree of the disease information and the appointed symptom information according to the ontology knowledge base;
and determining target information with the correlation degree meeting preset conditions from the disease information, wherein the target information is used for recommending corresponding medical resource information to the user.
5. The method of claim 1, wherein the correspondence between the symptom information and the disease information is stored in an ontology knowledge base in the form of a graph model.
6. An information recommendation apparatus, characterized in that the apparatus comprises:
the system comprises an establishing unit, a judging unit and a judging unit, wherein the establishing unit is used for establishing an ontology knowledge base, and the ontology knowledge base comprises a corresponding relation between symptom information and disease information;
a first acquisition unit configured to acquire symptom information input by a user, the symptom information input by the user being designated symptom information;
the first calculating unit is used for calculating the correlation degree of the disease information and the specified symptom information according to the ontology knowledge base;
the first calculating unit is specifically configured to calculate a degree of correlation between the disease information and the specified symptom information according to the ontology knowledge base and a weight of each piece of symptom information in the ontology knowledge base, where the weight of each piece of symptom information is inversely proportional to the number of pieces of disease information corresponding to the symptom information;
the first calculation unit includes:
a third searching subunit, configured to search, from the ontology knowledge base, a set of all disease information having a corresponding relationship with the specified symptom information as a second disease information set;
a fourth searching subunit, configured to search, from the ontology knowledge base, a set of symptom information having a correspondence relationship with any disease information in the second disease information set as a second symptom information set;
the acquisition subunit is configured to acquire an intersection of the second symptom information set and the specified symptom information to acquire a third symptom information set;
a first calculating subunit, configured to calculate a sum of weights of each piece of symptom information in the third symptom information set, as a first result, calculate a sum of weights of each piece of symptom information in the second symptom information set, as a second result, where the weight of each piece of symptom information is inversely proportional to the number of pieces of disease information corresponding to the piece of symptom information;
a second calculating subunit, configured to calculate a ratio of the first result and the second result as a degree of correlation between the disease information and the designated symptom information;
the first determining unit is used for determining the disease information with the correlation degree meeting a preset condition from the disease information as target information, and the target information is used for recommending corresponding medical resource information to the user.
7. A computer-readable storage medium having stored therein instructions that, when run on a terminal device, cause the terminal device to perform the information recommendation method of any one of claims 1-5.
8. A computer program product, characterized in that the computer program product, when run on a terminal device, causes the terminal device to perform the information recommendation method of any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711407945.5A CN108122611B (en) | 2017-12-22 | 2017-12-22 | Information recommendation method and device, storage medium and program product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711407945.5A CN108122611B (en) | 2017-12-22 | 2017-12-22 | Information recommendation method and device, storage medium and program product |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108122611A CN108122611A (en) | 2018-06-05 |
CN108122611B true CN108122611B (en) | 2021-05-07 |
Family
ID=62231252
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711407945.5A Active CN108122611B (en) | 2017-12-22 | 2017-12-22 | Information recommendation method and device, storage medium and program product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108122611B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110648754A (en) * | 2018-06-27 | 2020-01-03 | 北京百度网讯科技有限公司 | Department recommendation method, device and equipment |
CN109300535A (en) * | 2018-07-06 | 2019-02-01 | 北京康夫子科技有限公司 | Hospital guide's method, hospital guide's device and machine readable storage medium |
CN112655054B (en) * | 2018-12-07 | 2024-08-20 | 北京嘀嘀无限科技发展有限公司 | Artificial intelligence medical symptom recognition system based on end-to-end learning |
CN110175295B (en) * | 2019-06-21 | 2021-05-04 | 卓尔智联(武汉)研究院有限公司 | Advertisement space recommendation method, electronic device and computer readable storage medium |
CN110504028A (en) * | 2019-08-22 | 2019-11-26 | 上海软中信息***咨询有限公司 | A kind of disease way of inquisition, device, system, computer equipment and storage medium |
CN110911005A (en) * | 2019-11-22 | 2020-03-24 | 傲网信息科技(厦门)有限公司 | Data analysis system and server |
CN111951955A (en) * | 2020-08-13 | 2020-11-17 | 神州数码医疗科技股份有限公司 | Method and device for constructing clinical decision support system based on rule reasoning |
CN111986793B (en) * | 2020-09-03 | 2023-09-19 | 深圳平安智慧医健科技有限公司 | Diagnosis guiding processing method and device based on artificial intelligence, computer equipment and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184314A (en) * | 2011-04-02 | 2011-09-14 | 中国医学科学院医学信息研究所 | Deviation symptom description-oriented automatic computer-aided diagnosis method |
KR20140058244A (en) * | 2012-11-06 | 2014-05-14 | 한국 한의학 연구원 | Apparatus and method for searching nature of a disease on based symptom weight |
CN103885971A (en) * | 2012-12-20 | 2014-06-25 | 阿里巴巴集团控股有限公司 | Data pushing method and data pushing device |
CN104102816A (en) * | 2014-06-20 | 2014-10-15 | 周晋 | Symptom match and machine learning-based automatic diagnosis system and method |
CN104463754A (en) * | 2014-12-30 | 2015-03-25 | 天津迈沃医药技术有限公司 | Method for building medical ontology database based on disease characteristics |
CN104200069B (en) * | 2014-08-13 | 2017-08-04 | 周晋 | A kind of medication commending system and method based on symptom analysis and machine learning |
CN107330287A (en) * | 2017-07-10 | 2017-11-07 | 叮当(深圳)健康机器人科技有限公司 | A kind of disease information analysis method and device |
-
2017
- 2017-12-22 CN CN201711407945.5A patent/CN108122611B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184314A (en) * | 2011-04-02 | 2011-09-14 | 中国医学科学院医学信息研究所 | Deviation symptom description-oriented automatic computer-aided diagnosis method |
KR20140058244A (en) * | 2012-11-06 | 2014-05-14 | 한국 한의학 연구원 | Apparatus and method for searching nature of a disease on based symptom weight |
CN103885971A (en) * | 2012-12-20 | 2014-06-25 | 阿里巴巴集团控股有限公司 | Data pushing method and data pushing device |
CN104102816A (en) * | 2014-06-20 | 2014-10-15 | 周晋 | Symptom match and machine learning-based automatic diagnosis system and method |
CN104200069B (en) * | 2014-08-13 | 2017-08-04 | 周晋 | A kind of medication commending system and method based on symptom analysis and machine learning |
CN104463754A (en) * | 2014-12-30 | 2015-03-25 | 天津迈沃医药技术有限公司 | Method for building medical ontology database based on disease characteristics |
CN107330287A (en) * | 2017-07-10 | 2017-11-07 | 叮当(深圳)健康机器人科技有限公司 | A kind of disease information analysis method and device |
Non-Patent Citations (1)
Title |
---|
"智能导医***中TF-IDF权重改进算法研究";徐奕枫等;《计算机工程与应用》;20170228(第04期);第238-243页 * |
Also Published As
Publication number | Publication date |
---|---|
CN108122611A (en) | 2018-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108122611B (en) | Information recommendation method and device, storage medium and program product | |
US8548996B2 (en) | Ranking content items related to an event | |
CN107705842B (en) | Intelligent diagnosis system and its working method | |
CN104636430B (en) | Case base represents and case similarity acquisition methods and system | |
US10685052B2 (en) | Method of and system for information retrieval | |
US9542451B2 (en) | Mobile application search ranking | |
Yang et al. | Doctor recommendation based on an intuitionistic normal cloud model considering patient preferences | |
US20050210025A1 (en) | System and method for predicting the ranking of items | |
KR101220557B1 (en) | Method and system for searching mobile application using human activity knowledge database | |
JP2015515079A (en) | Keyword recommendation | |
Rafeh et al. | An adaptive approach to dealing with unstable behaviour of users in collaborative filtering systems | |
US20190065550A1 (en) | Query optimizer for combined structured and unstructured data records | |
EP2778985A1 (en) | Search result ranking by department | |
CN108039200A (en) | A kind of information recommendation method, device and storage medium, program product | |
JP6526849B1 (en) | Estimation device, estimation method and estimation program | |
WO2017039755A1 (en) | Fast and accurate search generating a ranked list of healthcare providers | |
US20150248720A1 (en) | Recommendation engine | |
CN113782195A (en) | Physical examination package customization method and device | |
US20140012853A1 (en) | Search device, search method, search program, and computer-readable memory medium for recording search program | |
CN104462556B (en) | Question and answer page relevant issues recommend method and apparatus | |
US9779460B2 (en) | Systems, methods and non-transitory computer readable storage media for tracking and evaluating predictions regarding relationships | |
KR101958555B1 (en) | Apparatus and method for providing search result | |
CN111090805A (en) | Recommendation index attribution method and device and electronic equipment | |
Sousa et al. | A hybrid approach toward biomedical relation extraction training corpora: combining distant supervision with crowdsourcing | |
JP6970527B2 (en) | Content selection method and content selection program |
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 |