CN113656601A - Doctor-patient matching method, device, equipment and storage medium - Google Patents
Doctor-patient matching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113656601A CN113656601A CN202111004058.XA CN202111004058A CN113656601A CN 113656601 A CN113656601 A CN 113656601A CN 202111004058 A CN202111004058 A CN 202111004058A CN 113656601 A CN113656601 A CN 113656601A
- Authority
- CN
- China
- Prior art keywords
- target
- doctor
- patient
- knowledge graph
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 208000024891 symptom Diseases 0.000 claims abstract description 103
- 238000006243 chemical reaction Methods 0.000 claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 238000012163 sequencing technique Methods 0.000 claims abstract description 16
- 201000010099 disease Diseases 0.000 claims description 38
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000013598 vector Substances 0.000 description 4
- 208000037919 acquired disease Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 208000034619 Gingival inflammation Diseases 0.000 description 1
- 206010018291 Gingival swelling Diseases 0.000 description 1
- 206010019233 Headaches Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 201000001245 periodontitis Diseases 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 206010039083 rhinitis Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000004371 toothache Diseases 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The invention relates to the field of artificial intelligence, and discloses a doctor-patient matching method, a doctor-patient matching device, doctor-patient matching equipment and a storage medium, which are used for improving the accuracy of doctor-patient matching. The doctor-patient matching method comprises the following steps: structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data; calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence. In addition, the invention also relates to a blockchain technology, and the target doctor can be stored in the blockchain node.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a doctor-patient matching method, a doctor-patient matching device, doctor-patient matching equipment and a storage medium.
Background
With the rapid development of computer technology, the efficiency of communicating with users and processing user demands through the internet is very high and a large time cost can be saved. With the acceleration of the process of medical informatization, the establishment of electronic cases and health records is realizing the arrangement and analysis of fragmented medical information by an artificial intelligence technology, thereby improving the quality of medical service.
At present, doctors and patients are matched with doctors suitable for the patients when the patients use internet hospitals, the existing scheme is that the professions and specialties of the doctors are presented to the patients through list classified tour, and the doctors and the patients are matched according to the preference of the patients, but the accuracy rate of the doctors and the patients is low at present.
Disclosure of Invention
The invention provides a doctor-patient matching method, a doctor-patient matching device, doctor-patient matching equipment and a storage medium, which are used for improving the accuracy of doctor-patient matching.
The invention provides a doctor-patient matching method in a first aspect, which comprises the following steps: acquiring symptom data of a patient, wherein the symptom data comprises disease vocabularies and symptom vocabularies; structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data; calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph; and sequencing a preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining of symptom data of the patient, where the symptom data includes a disease vocabulary and a symptom vocabulary, includes: acquiring electronic medical record data of a patient, and performing text extraction on the electronic medical record data to obtain text data; recognizing disease keywords and symptom keywords of the text data to obtain disease vocabularies and symptom vocabularies; and taking the disease vocabulary and the symptom vocabulary as symptom data.
Optionally, in a second implementation manner of the first aspect of the present invention, the structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data includes: carrying out data structuring processing on the symptom data to obtain structured data; matching the structured data with a preset triple to obtain a target triple corresponding to the structured data; and writing the target triple into the knowledge graph corresponding to the patient to obtain the target knowledge graph.
Optionally, in a third implementation manner of the first aspect of the present invention, the invoking a preset credibility model to perform spatial transformation on the target knowledge graph to obtain a target spatial relationship, and performing credibility calculation on the target spatial relationship according to a preset scoring function to obtain a target credibility corresponding to the target knowledge graph includes: carrying out space conversion on the target knowledge graph through a preset credibility model to obtain a target space relation; and calculating the reliability of the target knowledge graph based on a preset scoring function and the target spatial relationship to obtain the target reliability.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the performing spatial transformation on the target knowledge graph through a preset credibility model to obtain a target spatial relationship includes: modeling entities and relations of the target knowledge graph through a preset credibility model to obtain initial entities and initial relations; respectively carrying out relationship conversion on the initial entity and the initial relationship to obtain a conversion entity and a conversion relationship; and carrying out spatial relationship synthesis on the conversion entity and the conversion relationship to obtain a target spatial relationship.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing, by the target knowledge graph, reliability calculation based on a preset scoring function and the target spatial relationship to obtain a target reliability includes: acquiring an entity space in the target space relationship, and determining a target entity based on the entity space; projecting the target entity into the relationship space through a matrix; and carrying out reliability calculation on the target knowledge graph in the relation space through a preset scoring function to obtain the target reliability corresponding to the target triple.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the sorting a preset doctor list according to the target reliability to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence includes: sequencing a preset doctor list based on the target credibility to obtain a target sequence; and acquiring a preference index of the patient, and matching a target doctor corresponding to the patient from the target sequence according to the preference index.
A second aspect of the present invention provides a doctor-patient matching apparatus, including: the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring symptom data of a patient, and the symptom data comprises disease vocabularies and symptom vocabularies; the processing module is used for carrying out structural processing on the symptom data to obtain structural data and constructing a target knowledge graph corresponding to the patient based on the structural data; the calculation module is used for calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph; and the generating module is used for sequencing a preset doctor list according to the target credibility to obtain a target sequence and generating a target doctor corresponding to the patient according to the target sequence.
Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: acquiring electronic medical record data of a patient, and performing text extraction on the electronic medical record data to obtain text data; recognizing disease keywords and symptom keywords of the text data to obtain disease vocabularies and symptom vocabularies; and taking the disease vocabulary and the symptom vocabulary as symptom data.
Optionally, in a second implementation manner of the second aspect of the present invention, the processing module is specifically configured to: carrying out data structuring processing on the symptom data to obtain structured data; matching the structured data with a preset triple to obtain a target triple corresponding to the structured data; and writing the target triple into the knowledge graph corresponding to the patient to obtain the target knowledge graph.
Optionally, in a third implementation manner of the second aspect of the present invention, the calculation module includes: the conversion unit is used for carrying out space conversion on the target knowledge graph through a preset credibility model to obtain a target space relation; and the credibility calculation unit is used for carrying out credibility calculation on the target knowledge graph based on a preset scoring function and the target spatial relationship to obtain the target credibility.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the conversion unit is specifically configured to: modeling entities and relations of the target knowledge graph through a preset credibility model to obtain initial entities and initial relations; respectively carrying out relationship conversion on the initial entity and the initial relationship to obtain a conversion entity and a conversion relationship; and carrying out spatial relationship synthesis on the conversion entity and the conversion relationship to obtain a target spatial relationship.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the reliability calculating unit is specifically configured to: acquiring an entity space in the target space relationship, and determining a target entity based on the entity space; projecting the target entity into the relationship space through a matrix; and carrying out reliability calculation on the target knowledge graph in the relation space through a preset scoring function to obtain the target reliability corresponding to the target triple.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the generating module is specifically configured to: sequencing a preset doctor list based on the target credibility to obtain a target sequence; and acquiring a preference index of the patient, and matching a target doctor corresponding to the patient from the target sequence according to the preference index.
A third aspect of the present invention provides a doctor-patient matching apparatus, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the doctor-patient matching device to perform the doctor-patient matching method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the doctor-patient matching method described above.
In the technical scheme provided by the invention, a target knowledge map corresponding to a patient is constructed based on symptom data; calling a preset credibility model to carry out credibility calculation on a target knowledge graph to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the target user according to the target sequence. According to the invention, the knowledge graph corresponding to the symptom data of the patient is constructed, and doctor matching is carried out on the patient through the knowledge graph, so that the accuracy of doctor-patient matching is improved.
Drawings
FIG. 1 is a diagram of an embodiment of a doctor-patient matching method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a doctor-patient matching method in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a doctor-patient matching device in an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a doctor-patient matching device in an embodiment of the invention;
fig. 5 is a schematic diagram of an embodiment of a doctor-patient matching device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a doctor-patient matching method, a doctor-patient matching device, doctor-patient matching equipment and a storage medium, which are used for improving the accuracy of doctor-patient matching. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a doctor-patient matching method in an embodiment of the present invention includes:
101. acquiring symptom data of a patient, wherein the symptom data comprises disease vocabularies and symptom vocabularies;
it is understood that the executing subject of the present invention may be a doctor-patient matching device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
In order to ensure the authenticity of the symptom data, the symptom data may be acquired from a medical website, a medical institution database, or the like. The symptom data is text data comprising disease vocabularies and symptom vocabularies, and the symptom data can be acquired from medical websites or medical institution data through a preset crawler, wherein the medical websites or the medical institution data record the disease vocabularies and the symptom vocabularies of patients to generate the symptom data, and the disease vocabularies and the symptom vocabularies can also be directly input by the patients to obtain the symptom data.
102. Structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data;
specifically, the server constructs a target knowledge graph corresponding to the patient based on symptom data, wherein the target knowledge graph can fuse multi-source heterogeneous information, an entity-relation-entity triple is used for describing the relation between an entity and an entity, a reticular knowledge structure is formed through the relation, the server conducts data structuring processing on the symptom data to obtain structured data, and the data structuring processing is that the symptom data are described through the triple, namely the structured data correspond to the target triple one to one.
103. Calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph;
specifically, the server identifies an entity space with specific meaning or strong reference from the target knowledge graph, the server identifies time, place and the like from the target knowledge graph, after the server inputs the target knowledge graph into a pre-trained credibility model, the credibility model can output medical entities described by the patient in the target knowledge graph, and after the credibility model outputs the entity space and the relation space, the server performs credibility calculation on the target knowledge graph based on a preset scoring function and a target space relation to obtain target credibility.
104. And sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence.
Specifically, the server sorts the target reliability, selects the maximum value of the doctor label corresponding to the target reliability to obtain the maximum value of the doctor label, and takes the doctor label corresponding to the maximum value as the target doctor.
For example: when the target reliability is 0.6325, the server determines that the doctor label is doctor A, when the target reliability is 0.5655, the server determines that the doctor label is doctor B, the server compares the target reliabilities, and the server sets doctor A corresponding to 0.6325 with the maximum target reliability as the target doctor corresponding to the patient.
Further, the server stores the target doctor in a blockchain database, which is not limited herein.
In the embodiment of the invention, a target knowledge graph corresponding to a patient is constructed based on symptom data; calling a preset credibility model to carry out credibility calculation on the target knowledge graph to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the target user according to the target sequence. According to the invention, the knowledge graph corresponding to the symptom data of the patient is constructed, and doctor matching is carried out on the patient through the knowledge graph, so that the accuracy of doctor-patient matching is improved.
Referring to fig. 2, a second embodiment of the doctor-patient matching method according to the embodiment of the present invention includes:
201. acquiring symptom data of a patient, wherein the symptom data comprises disease vocabularies and symptom vocabularies;
specifically, the server collects electronic medical record data of a patient, and the server extracts texts from the electronic medical record data to obtain text data; the server identifies the disease keywords and the symptom keywords of the text data to obtain disease vocabularies and symptom vocabularies; the server takes the disease vocabulary and the symptom vocabulary as symptom data.
The server inquires electronic medical record data of a patient from a medical institution website, the server extracts keywords corresponding to diseases and symptoms in the electronic medical record data, the server can conveniently distinguish the symptom data in the process of acquiring the symptom data of the patient, the symptom data can carry corresponding symptom tags, the symptom data of each symptom tag can obtain disease vocabularies and symptom vocabularies along with associated data influencing associated factors of the symptom data, and the server takes the disease vocabularies and the symptom vocabularies as the symptom data to obtain the symptom data.
202. Structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data;
specifically, the server performs data structuring processing on the symptom data to obtain structured data; the server matches the structured data with preset triples to obtain target triples corresponding to the structured data; and the server writes the target triple into the knowledge graph corresponding to the patient to obtain the target knowledge graph.
The server carries out data structuring processing on the symptom data to obtain structured data, the structured data correspond to preset target triples one by one, the server generates a target knowledge map corresponding to a patient based on the target triples, and further the server inputs the structured data, and the data structuring processing specifically comprises the following steps: target triplets of patient-symptomatic, patient-acquired-disease (i.e., underlying disease), patient-acquired-disease (i.e., historical disease), patient-likely-disease (i.e., family disease), etc. are added to the knowledge-graph to obtain the target knowledge-graph.
203. Carrying out space conversion on the target knowledge graph through a preset credibility model to obtain a target space relation;
specifically, the server carries out modeling entity and relationship on the target knowledge graph through a preset credibility model to obtain an initial entity and an initial relationship; the server respectively carries out relationship conversion on the initial entity and the initial relationship to obtain a conversion entity and a conversion relationship; and the server performs spatial relationship synthesis on the conversion entity and the conversion relationship to obtain a target spatial relationship.
The server models entities and relations of the target knowledge graph through a preset credibility model to obtain initial entities and initial relations, wherein the initial entities are abstractions of objective individuals, and a person, a movie and a sentence can be regarded as the initial entities. For example: zhang three, Li four, I is not wangwu. The initial relationship is an abstraction of the initial entity and the relationship between the initial entities.
Specifically, if two initial relations exist in the initial entity expansion library, the first initial relation is toothache-gingival swelling-gingival inflammation-periodontitis, the second initial relation is cold-fever-headache-rhinitis-cough, the server performs space transformation on the initial entities and the initial relations to obtain a target space relation, and the target space relation comprises an entity space and a relation space.
204. Performing reliability calculation on the target knowledge graph based on a preset scoring function and a target spatial relationship to obtain target reliability;
specifically, the server obtains an entity space in the target space relationship and determines a target entity based on the entity space; projecting the target entity into the relation space through the matrix; and carrying out reliability calculation on the target knowledge graph in the relation space through a preset scoring function to obtain the target reliability corresponding to the target triple.
The server performs space conversion on a target knowledge graph through a preset credibility model to obtain a target space relationship, wherein the credibility model can be a transr model, the server comprises an entity space and a relationship space in two different spaces through the credibility model, the server models the entity and the relationship through the entity space (symptoms, diseases and doctors) and the relationship space (diseases and symptoms relationship, doctors and diseases relationship and the like) to obtain the target space relationship, the server converts the target knowledge graph in the relationship space, the server projects the target entity in the entity space into the relationship space through a matrix, and the server evaluates the target triple credibility through a preset scoring function, wherein the scoring function is as follows:
wherein S and S 'represent positive and negative target triple sets of the target knowledge-graph, respectively, wherein S' is generated by randomly replacing a head entity or a tail entity of S; gamma is a marginal parameter, which is the distance between a positive case and a negative case; h 'and t' are the replaced head and tail entities, respectively.
The server acquires a target entity in an entity space; the server calculates the correlation (i.e. the reliability) between different entities through the embedded vector corresponding to the target entity (which may be the embedded vector before dimensionality reduction or the embedded vector after dimensionality reduction), the correlation between different target entities can be determined according to the distance between the target entities, and the closer the distance is, the stronger the correlation is, and the target reliability is obtained. In addition, the server calculates cosine distances, absolute distances and the like between different target entities according to the embedded vectors corresponding to the target entities; the server determines the correlation between the target entities according to the distance between the target entities.
205. And sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence.
Specifically, the server sorts a preset doctor list based on target credibility to obtain a target sequence; the server obtains the preference index of the patient and matches a target doctor corresponding to the patient from the target sequence according to the preference index.
The server ranks a preset doctor list based on target credibility to obtain a target sequence, the server considers the preference of a plurality of patients and the workload of a target doctor, defines the preference degree of the patients to measure the preference index of the patients to the target doctor, obtains the preference index corresponding to the patients by a doctor-patient matching index weighted average method, and recommends the target doctor according to the highest target credibility and the preference index after the server calculates the matching degree of the doctors in all the doctor lists to the patients. Furthermore, the server matches the target doctors with higher relevance for the patients, the inquiry experience of the patients is improved, and some target doctors with specific specialties can also match the relevant patients, so that the waste of medical resources can be avoided.
Further, the server stores the target doctor in a blockchain database, which is not limited herein.
In the embodiment of the invention, a target knowledge graph corresponding to a patient is constructed based on symptom data; calling a preset credibility model to carry out credibility calculation on the target knowledge graph to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the target user according to the target sequence. According to the invention, the knowledge graph corresponding to the symptom data of the patient is constructed, and doctor matching is carried out on the patient through the knowledge graph, so that the accuracy of doctor-patient matching is improved.
In the above description of the doctor-patient matching method in the embodiment of the present invention, referring to fig. 3, a doctor-patient matching device in the embodiment of the present invention is described below, and a first embodiment of the doctor-patient matching device in the embodiment of the present invention includes:
an obtaining module 301, configured to obtain symptom data of a patient, where the symptom data includes a disease vocabulary and a symptom vocabulary;
a processing module 302, configured to perform structural processing on the symptom data to obtain structural data, and construct a target knowledge graph corresponding to the patient based on the structural data;
the calculation module 303 is configured to call a preset credibility model to perform spatial transformation on the target knowledge graph to obtain a target spatial relationship, and perform credibility calculation on the target spatial relationship according to a preset scoring function to obtain a target credibility corresponding to the target knowledge graph;
a generating module 304, configured to sort a preset doctor list according to the target reliability to obtain a target sequence, and generate a target doctor corresponding to the patient according to the target sequence.
In the embodiment of the invention, a target knowledge graph corresponding to a patient is constructed based on symptom data; calling a preset credibility model to carry out credibility calculation on a target knowledge graph to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the target user according to the target sequence. According to the invention, the knowledge graph corresponding to the symptom data of the patient is constructed, and doctor matching is carried out on the patient through the knowledge graph, so that the accuracy of doctor-patient matching is improved.
Referring to fig. 4, a second embodiment of the doctor-patient matching device in the embodiment of the present invention includes:
an obtaining module 301, configured to obtain symptom data of a patient, where the symptom data includes a disease vocabulary and a symptom vocabulary;
a processing module 302, configured to perform structural processing on the symptom data to obtain structural data, and construct a target knowledge graph corresponding to the patient based on the structural data;
the calculation module 303 is configured to call a preset credibility model to perform spatial transformation on the target knowledge graph to obtain a target spatial relationship, and perform credibility calculation on the target spatial relationship according to a preset scoring function to obtain a target credibility corresponding to the target knowledge graph;
a generating module 304, configured to sort a preset doctor list according to the target reliability to obtain a target sequence, and generate a target doctor corresponding to the patient according to the target sequence.
Optionally, the obtaining module 301 is specifically configured to:
acquiring electronic medical record data of a patient, and performing text extraction on the electronic medical record data to obtain text data; recognizing disease keywords and symptom keywords of the text data to obtain disease vocabularies and symptom vocabularies; and taking the disease vocabulary and the symptom vocabulary as symptom data.
Optionally, the processing module 302 is specifically configured to:
carrying out data structuring processing on the symptom data to obtain structured data; matching the structured data with a preset triple to obtain a target triple corresponding to the structured data; and writing the target triple into the knowledge graph corresponding to the patient to obtain the target knowledge graph.
Optionally, the calculating module 303 includes:
a conversion unit 3031, configured to perform spatial conversion on the target knowledge graph through a preset credibility model to obtain a target spatial relationship;
and a reliability calculation unit 3032, configured to perform reliability calculation on the target knowledge graph based on a preset scoring function and the target spatial relationship, so as to obtain a target reliability.
Optionally, the conversion unit 3031 is specifically configured to:
modeling entities and relations of the target knowledge graph through a preset credibility model to obtain initial entities and initial relations; respectively carrying out relationship conversion on the initial entity and the initial relationship to obtain a conversion entity and a conversion relationship; and carrying out spatial relationship synthesis on the conversion entity and the conversion relationship to obtain a target spatial relationship.
Optionally, the reliability calculation unit 3032 is specifically configured to:
acquiring an entity space in the target space relationship, and determining a target entity based on the entity space; projecting the target entity into the relationship space through a matrix; and carrying out reliability calculation on the target knowledge graph in the relation space through a preset scoring function to obtain the target reliability corresponding to the target triple.
Optionally, the generating module 304 is specifically configured to:
sequencing a preset doctor list based on the target credibility to obtain a target sequence; and acquiring a preference index of the patient, and matching a target doctor corresponding to the patient from the target sequence according to the preference index.
In the embodiment of the invention, a target knowledge graph corresponding to a patient is constructed based on symptom data; calling a preset credibility model to carry out credibility calculation on a target knowledge graph to obtain target credibility corresponding to the target knowledge graph; and sequencing the preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the target user according to the target sequence. According to the invention, the knowledge graph corresponding to the symptom data of the patient is constructed, and doctor matching is carried out on the patient through the knowledge graph, so that the accuracy of doctor-patient matching is improved.
Fig. 3 and 4 describe the doctor-patient matching device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the doctor-patient matching device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a doctor-patient matching apparatus according to an embodiment of the present invention, where the doctor-patient matching apparatus 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions for operating on the doctor-patient matching apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the doctor-patient matching device 500.
The doctor-patient matching device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the patient and patient matching device configuration shown in fig. 5 does not constitute a limitation of the patient and patient matching device, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The invention further provides a doctor-patient matching device, which comprises a memory and a processor, wherein computer readable instructions are stored in the memory, and when the computer readable instructions are executed by the processor, the processor executes the steps of the doctor-patient matching method in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the doctor-patient matching method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A doctor-patient matching method is characterized by comprising the following steps:
acquiring symptom data of a patient, wherein the symptom data comprises disease vocabularies and symptom vocabularies;
structuring the symptom data to obtain structured data, and constructing a target knowledge graph corresponding to the patient based on the structured data;
calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph;
and sequencing a preset doctor list according to the target credibility to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence.
2. The doctor-patient matching method of claim 1, wherein the obtaining of patient symptom data, the symptom data including disease vocabulary and symptom vocabulary, comprises:
acquiring electronic medical record data of a patient, and performing text extraction on the electronic medical record data to obtain text data;
recognizing disease keywords and symptom keywords of the text data to obtain disease vocabularies and symptom vocabularies;
and taking the disease vocabulary and the symptom vocabulary as symptom data.
3. The doctor-patient matching method according to claim 1, wherein the structuring the symptom data to obtain structured data and constructing a target knowledge graph corresponding to the patient based on the structured data comprises:
carrying out data structuring processing on the symptom data to obtain structured data;
matching the structured data with a preset triple to obtain a target triple corresponding to the structured data;
and writing the target triple into the knowledge graph corresponding to the patient to obtain the target knowledge graph.
4. The doctor-patient matching method according to claim 1, wherein the calling a preset credibility model to perform spatial transformation on the target knowledge graph to obtain a target spatial relationship, and performing credibility calculation on the target spatial relationship according to a preset scoring function to obtain a target credibility corresponding to the target knowledge graph includes:
carrying out space conversion on the target knowledge graph through a preset credibility model to obtain a target space relation;
and calculating the reliability of the target knowledge graph based on a preset scoring function and the target spatial relationship to obtain the target reliability.
5. The doctor-patient matching method according to claim 4, wherein the obtaining of the target spatial relationship by spatially transforming the target knowledge graph through a preset credibility model comprises:
modeling entities and relations of the target knowledge graph through a preset credibility model to obtain initial entities and initial relations;
respectively carrying out relationship conversion on the initial entity and the initial relationship to obtain a conversion entity and a conversion relationship;
and carrying out spatial relationship synthesis on the conversion entity and the conversion relationship to obtain a target spatial relationship.
6. The doctor-patient matching method according to claim 4, wherein the calculating reliability of the target knowledge graph based on the preset scoring function and the target spatial relationship to obtain target reliability comprises:
acquiring an entity space in the target space relationship, and determining a target entity based on the entity space;
projecting the target entity into the relationship space through a matrix;
and carrying out reliability calculation on the target knowledge graph in the relation space through a preset scoring function to obtain the target reliability corresponding to the target triple.
7. The doctor-patient matching method according to any one of claims 1 to 6, wherein the sorting a preset doctor list according to the target reliability to obtain a target sequence, and generating a target doctor corresponding to the patient according to the target sequence comprises:
sequencing a preset doctor list based on the target credibility to obtain a target sequence;
and acquiring a preference index of the patient, and matching a target doctor corresponding to the patient from the target sequence according to the preference index.
8. A doctor-patient matching device, characterized in that it comprises:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring symptom data of a patient, and the symptom data comprises disease vocabularies and symptom vocabularies;
the processing module is used for carrying out structural processing on the symptom data to obtain structural data and constructing a target knowledge graph corresponding to the patient based on the structural data;
the calculation module is used for calling a preset credibility model to perform space conversion on the target knowledge graph to obtain a target space relation, and performing credibility calculation on the target space relation according to a preset scoring function to obtain target credibility corresponding to the target knowledge graph;
and the generating module is used for sequencing a preset doctor list according to the target credibility to obtain a target sequence and generating a target doctor corresponding to the patient according to the target sequence.
9. A doctor-patient matching device, characterized in that it comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the doctor-patient matching device to perform the doctor-patient matching method of any one of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the doctor-patient matching method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111004058.XA CN113656601A (en) | 2021-08-30 | 2021-08-30 | Doctor-patient matching method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111004058.XA CN113656601A (en) | 2021-08-30 | 2021-08-30 | Doctor-patient matching method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113656601A true CN113656601A (en) | 2021-11-16 |
Family
ID=78493193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111004058.XA Pending CN113656601A (en) | 2021-08-30 | 2021-08-30 | Doctor-patient matching method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113656601A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662593A (en) * | 2022-11-08 | 2023-01-31 | 北京健康在线技术开发有限公司 | Doctor-patient matching method, device, equipment and medium based on symptom knowledge graph |
| CN115862896A (en) * | 2023-02-13 | 2023-03-28 | 深圳市汇健智慧医疗有限公司 | Perioperative period-based doctor-patient cooperative management method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10102291B1 (en) * | 2015-07-06 | 2018-10-16 | Google Llc | Computerized systems and methods for building knowledge bases using context clouds |
| CN111523029A (en) * | 2020-04-20 | 2020-08-11 | 浙江大学 | Personalized recommendation method based on knowledge graph representation learning |
| CN111767410A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Construction method, device, equipment and storage medium of clinical medical knowledge map |
-
2021
- 2021-08-30 CN CN202111004058.XA patent/CN113656601A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10102291B1 (en) * | 2015-07-06 | 2018-10-16 | Google Llc | Computerized systems and methods for building knowledge bases using context clouds |
| CN111523029A (en) * | 2020-04-20 | 2020-08-11 | 浙江大学 | Personalized recommendation method based on knowledge graph representation learning |
| CN111767410A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Construction method, device, equipment and storage medium of clinical medical knowledge map |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662593A (en) * | 2022-11-08 | 2023-01-31 | 北京健康在线技术开发有限公司 | Doctor-patient matching method, device, equipment and medium based on symptom knowledge graph |
| CN115862896A (en) * | 2023-02-13 | 2023-03-28 | 深圳市汇健智慧医疗有限公司 | Perioperative period-based doctor-patient cooperative management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108986908B (en) | Method and device for processing inquiry data, computer equipment and storage medium | |
| US11232365B2 (en) | Digital assistant platform | |
| CN113707297B (en) | Medical data processing method, device, equipment and storage medium | |
| Bashir et al. | BagMOOV: A novel ensemble for heart disease prediction bootstrap aggregation with multi-objective optimized voting | |
| CN112035741B (en) | Reservation method, device, equipment and storage medium based on user physical examination data | |
| CN113724848A (en) | Medical resource recommendation method, device, server and medium based on artificial intelligence | |
| US20200311610A1 (en) | Rule-based feature engineering, model creation and hosting | |
| CN111986792A (en) | Medical institution scoring method, device, equipment and storage medium | |
| CN113656601A (en) | Doctor-patient matching method, device, equipment and storage medium | |
| Kaswan et al. | AI-based natural language processing for the generation of meaningful information electronic health record (EHR) data | |
| US10936962B1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| CN110164519B (en) | Classification method for processing electronic medical record mixed data based on crowd-sourcing network | |
| CN113724830B (en) | Medication risk detection method based on artificial intelligence and related equipment | |
| Carvalho et al. | Knowledge Graph Embeddings for ICU readmission prediction | |
| WO2022227171A1 (en) | Method and apparatus for extracting key information, electronic device, and medium | |
| CN116468043A (en) | Nested entity identification method, device, equipment and storage medium | |
| CN116522944A (en) | Picture generation method, device, equipment and medium based on multi-head attention | |
| CN113241198B (en) | User data processing method, device, equipment and storage medium | |
| WO2022249407A1 (en) | Assessment assistance system, assessment assistance method, and recording medium | |
| US20150339602A1 (en) | System and method for modeling health care costs | |
| CN114743647A (en) | Medical data processing method, device, equipment and storage medium | |
| US20210133627A1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| CN113611427A (en) | User portrait generation method, device, equipment and storage medium | |
| CN114547335A (en) | Service data processing method, device, equipment and storage medium | |
| CN113688119B (en) | Medical database construction method based on artificial intelligence and related equipment |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220530 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |