A doctor matching method and device based on a new social relationship and an electronic device
By acquiring doctors' social relationship information, establishing a graphical database, and performing multi-dimensional scoring, the problem of multiple people having the same name in doctor identity verification was solved, achieving efficient and accurate doctor identity matching.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- MEDOMINO INSIGHTS CO LTD
- Filing Date
- 2023-04-26
- Publication Date
- 2026-07-24
AI Technical Summary
In the medical field, existing technologies struggle to effectively integrate doctors' academic information and behavioral patterns, making it impossible to determine a doctor's true identity when multiple people share the same name.
By acquiring the social relationship information of the doctors to be matched, including collaborators' names, hospital names, departments, provinces, cities, and hospital levels, a graphical database is established. A multi-dimensional scoring system is used to determine the matching score of the candidate doctors, and finally, the identity of the doctors to be matched is determined.
It enables accurate location of doctors with the same name in the database, improving the accuracy and efficiency of doctor identity verification.
Smart Images
Figure CN116467501B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a doctor matching method, device, and electronic device based on a new type of social relationship. Background Technology
[0002] In the medical field, online information contains a wide variety of data about doctors, broadly categorized into two types: academic information and behavioral data. Academic information includes doctors' articles, clinical trials, conference proceedings, etc., while behavioral data includes online consultations, live streams, and patient education. However, in real life, multiple people often share the same name, making it impossible to determine a person's true identity solely based on their name. Therefore, integrating each doctor's academic information and behavioral data online to identify each individual is crucial. Summary of the Invention
[0003] This application provides a method, device, and electronic device for matching doctors based on novel social relationships, which can determine the doctor's identity based on social relationships such as collaborators.
[0004] In a first aspect, embodiments of this application provide a doctor matching method based on a novel social relationship, the method comprising: Obtain the information of the resources to be matched, and get the name of the doctor to be matched; Information is extracted from the resource information to be matched in a standardized manner to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level; By filtering the doctor information database for doctors with the same name as the doctor to be matched, at least one candidate doctor is obtained; All candidate doctors were scored sequentially based on multiple dimensions; Calculate the matching score for each candidate doctor and sort them. The candidate doctor with the highest matching score is selected as the doctor to be matched, and the match is successful.
[0005] One possible design also includes: Import the matched doctor data into the database; Each doctor is set as a node, and each doctor node has a unique identifier and multiple attributes; Create an edge between two nodes with the same attribute; Set the initial weight for each attribute; Access to a database of doctor information.
[0006] In one possible design, the collaborator and the doctor to be matched have at least one common attribute, including: having co-authored articles, having co-presented at conferences as speakers, being from the same city, being in the same field, being in the same department, or being from the same hospital.
[0007] In one possible design, the multiple dimensions include: a social dimension; The social dimension of the candidate doctor is scored to obtain a relationship score, which is the relationship score between the candidate doctor and the collaborator, representing the candidate doctor's social relationship.
[0008] In one possible design, the relationship score is equal to the sum of all path scores between the candidate doctor node and the collaborator node; The path score is equal to the reciprocal of the path length multiplied by the weight multiplied by the number of collaborations, with the reciprocal of the path length being the exponent. The path length is the number of edges that the candidate doctor node needs to traverse to reach the collaborator node, and the number of collaborations is the number of collaborations between the candidate doctor and the collaborator.
[0009] In one possible design, calculating the matching score for each candidate doctor includes: Pre-set weights for multiple dimensions; The scores of each dimension are multiplied by their respective weights and summed to obtain the matching score for each candidate doctor.
[0010] In one possible design, if the matching score of the candidate doctor with the highest matching score is less than a first threshold, the matching fails.
[0011] Secondly, embodiments of this application provide a doctor matching device based on a novel social relationship, characterized in that the device comprises: The receiving module obtains the resource information to be matched and gets the name of the doctor to be matched; The information extraction module extracts information from the resource information to be matched in a standardized manner to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level; The processing module filters doctors with the same name as the doctor to be matched from the doctor information database to obtain at least one candidate doctor; scores all candidate doctors according to multiple dimensions in turn; calculates the matching score of each candidate doctor and sorts them; and selects the candidate doctor with the highest matching score as the doctor to be matched, thus achieving a successful match.
[0012] Thirdly, embodiments of this application provide an electronic device, the electronic device including a memory and one or more processors; wherein, the memory is used to store computer program code, the computer program code including computer instructions; when the computer instructions are executed by the processor, the electronic device performs some or all of the steps of the method in the first aspect or various possible implementations of the first aspect.
[0013] Fourthly, embodiments of this application provide a computer storage medium storing instructions that, when executed on a computer, cause the computer to perform some or all of the steps of the method in the first aspect or various possible implementations of the first aspect.
[0014] This application provides a doctor matching method based on novel social relationships. The method includes: acquiring resource information to be matched to obtain the name of the doctor to be matched; extracting information from the resource information to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level; filtering doctors with the same name as the doctor to be matched from a doctor information database to obtain at least one candidate doctor; scoring all candidate doctors according to multiple dimensions; calculating and sorting the matching score of each candidate doctor; and selecting the candidate doctor with the highest matching score as the doctor to be matched, thus achieving a successful match. By acquiring the social relationships of the doctor to be matched and scoring candidate doctors with the same name in the database from multiple dimensions, the doctor's identity can be determined based on the doctor information. Attached Figure Description
[0015] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 A flowchart illustrating a doctor matching method based on a novel social relationship, provided for embodiments of this application; Figure 2 A schematic diagram illustrating an exemplary composition of a doctor matching device 200 based on a novel social relationship, provided in an embodiment of this application; Figure 3 This is an exemplary structural diagram of the electronic device 300 provided in an embodiment of this application. Implementation
[0017] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings.
[0018] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that although the terms first, second, etc., may be used in the following embodiments to describe a class of objects, the objects are not limited to these terms. These terms are only used to distinguish specific objects of that class of objects. For example, the terms first, second, etc., may be used in the following embodiments to describe thresholds, but thresholds are not limited to these terms. These terms are only used to distinguish different thresholds. Other classes of objects that may be described using the terms first, second, etc. in the following embodiments are similarly not described here.
[0019] This application provides a doctor matching method based on novel social relationships, which can perform identity matching by combining information such as the target's social relationships.
[0020] The following describes a doctor matching method based on novel social relationships, which is described in the embodiments of this application through several implementation methods.
[0021] like Figure 1 As shown, Figure 1 This illustrates a doctor matching method 100 based on a novel social relationship (hereinafter referred to as method 100), which includes the following steps: Step S101: Obtain the resource information to be matched and get the name of the doctor to be matched.
[0022] Step S102: Standardize and extract information from the resource information to be matched to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level.
[0023] In this embodiment, various information about the doctor to be identified is first obtained. However, based solely on this information, it is not possible to accurately confirm the identity of the doctor to be identified, as there may be other doctors with the same name. Therefore, it is necessary to judge the doctors with the same name based on multiple dimensions.
[0024] Step S103: Filter doctors with the same name as the doctor to be matched from the doctor information database to obtain at least one candidate doctor.
[0025] Step S104: Score all candidate doctors according to multiple dimensions.
[0026] In this embodiment, each candidate doctor is scored based on multiple dimensions, including hospital, city, province, department, field relevance, and social dimension.
[0027] Step S105: Calculate the matching score for each candidate doctor and sort them.
[0028] In this embodiment, the scores of multiple dimensions are integrated and added together according to a preset threshold, and then sorted according to the score height.
[0029] Step S106: Select the candidate doctor with the highest matching score as the doctor to be matched, and the match is successful.
[0030] This application obtains the social relationships of the doctor to be matched, scores candidate doctors with the same name in the database from multiple dimensions, and then determines the identity of the doctor to be matched based on the doctor information.
[0031] In one optional implementation, it further includes: Import the matched doctor data into the database; Each doctor is set as a node, and each doctor node has a unique identifier and multiple attributes; Create an edge between two nodes with the same attribute; Set the initial weight for each attribute; Access to a database of doctor information.
[0032] In this embodiment, resources with pre-matched doctor information and identities are pre-acquired. A relationship network is established based on a graph database using these existing resources. First, the basic database environment is built. Then, the matched resources are imported into the database. Each doctor is treated as a node, with DID serving as the node's value and unique identifier. Other information, such as city, province, location, and domain, serves as attributes of the corresponding node. Doctor information includes, but is not limited to, the information described above. Subsequently, edges are established between nodes based on shared attributes. For example, if two nodes share the same city attribute (meaning two doctors reside in the same city), they can be connected via a city edge.
[0033] In one alternative implementation, the collaborator and the doctor to be matched have at least one common attribute, including: having co-authored articles, having co-presented at conferences as speakers, being from the same city, being in the same field, being in the same department, or being from the same hospital.
[0034] In this embodiment, as collaborators of the doctor to be matched, there must be an edge connecting the two.
[0035] In one optional implementation, the plurality of dimensions includes: a social dimension; The social dimension of the candidate doctor is scored to obtain a relationship score, which is the relationship score between the candidate doctor and the collaborator, representing the candidate doctor's social relationship.
[0036] In this embodiment, in order to determine whether the candidate doctor and the doctor to be matched have the same name but different identities, it is necessary to score the candidate doctor. First, the relationship score between the collaborator of the doctor to be matched and each candidate doctor is calculated.
[0037] In one optional implementation, the relationship score is equal to the sum of all path scores between the candidate doctor node and the collaborator node; The path score is equal to the reciprocal of the path length multiplied by the weight multiplied by the number of collaborations, with the reciprocal of the path length being the exponent. The path length is the number of edges that the candidate doctor node needs to traverse to reach the collaborator node, and the number of collaborations is the number of collaborations between the candidate doctor and the collaborator.
[0038] In this embodiment, an initial weight is first assigned to each attribute, and then the scores of candidate doctor nodes and collaborator nodes are calculated according to the relationship score calculation formula. The path length refers to the number of edges on the path from node A to node B. When there is no direct connection between node A and node B, node C is connected to both node A and node B. Therefore, node C can be used to travel from node A to node B. In this case, the path is ACB, and the path length is 2. Due to the large number of nodes in the database, the maximum path length is set to 4. In practical applications, the maximum path length can be adjusted as needed. In the formula, the path length is used as the denominator. The purpose is that the longer the path length, the smaller the relationship score. This is because in reality, the more intermediate nodes are needed for two doctors to establish a connection, the weaker the relationship strength between them. Therefore, when node A and node B can establish a direct connection, i.e., when the path length is 1, their relationship score is higher.
[0039] In this embodiment, the number of collaborations typically refers to the number of collaborations or similarity between two nodes on a path, which can be used to measure the strength or similarity of the relationship between nodes. The special feature is that an exponent is used for collaboration strength, the purpose of which is to ensure that the collaboration strength decreases as the path length increases. The number of collaborations is e, the path length is m, the exponent x = 1 / m, and the collaboration strength y = e^x. As m increases, x and y decrease. In reality, if nodes A and B can be connected through node C, then when calculating the path score for ACB, compared to calculating the path score for AB, the longer the path length, the lower the actual contribution.
[0040] In addition, when calculating the relationship score between node A and node B, there is a relationship score threshold. When the relationship score is greater than the threshold, the relationship score is recorded as the relationship score threshold.
[0041] In one optional implementation, calculating the matching score for each candidate doctor includes: Pre-set weights for multiple dimensions; The scores of each dimension are multiplied by their respective weights and summed to obtain the matching score for each candidate doctor.
[0042] In this embodiment, weights can be used to measure the importance or influence of each dimension. The greater the weight, the greater the influence of the dimension. Therefore, it is necessary to pre-set a threshold based on the actual situation. In actual calculation, the score obtained by each dimension needs to be multiplied by the corresponding weight first, and then all of them are added together. Finally, score normalization is performed, that is, the maximum score of each dimension is first multiplied by the weight and then summed to obtain the ideal maximum value. The range from 0 to the maximum value is mapped to the range from 0 to 1 to obtain the final score.
[0043] In one alternative implementation, if the matching score of the candidate doctor with the highest matching score is less than a first threshold, the matching fails.
[0044] In this embodiment, if a candidate's score exceeds 0.8, the match is successful; if none of the candidates' scores exceed the threshold, the match fails, indicating that the doctor's information does not exist in the database.
[0045] In summary, the doctor matching method based on novel social relationships in this application utilizes a doctor information database, obtains the social relationships of the doctor to be matched, scores candidate doctors with the same name in the database from multiple dimensions, and then determines the identity of the doctor to be matched based on the doctor information.
[0046] correspond Figure 1 In addition to the method described above, this application also provides an apparatus for performing the above method.
[0047] like Figure 2 As shown, Figure 2 This diagram illustrates a doctor matching device 200 based on a novel social relationship, the device comprising: The receiving module 201 obtains the resource information to be matched and gets the name of the doctor to be matched. Information extraction module 202 extracts information from the resource information to be matched in a standardized manner to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level; The processing module 203 filters doctors with the same name as the doctor to be matched from the doctor information database to obtain at least one candidate doctor; scores all candidate doctors according to multiple dimensions in turn; calculates the matching score of each candidate doctor and sorts them; and selects the candidate doctor with the highest matching score as the doctor to be matched, thus achieving a successful match.
[0048] It is understandable that the above division of modules / units is merely a logical functional division. In actual implementation, the functions of these modules can be integrated into hardware entities. For example, the processing module can be integrated into a processor, and the receiving module can be integrated into a transceiver. The programs and instructions that implement the functions of these modules can be maintained in memory. For example, Figure 3 An electronic device 300 is provided, which includes a processor 301, a transceiver 302, and a memory 303. The transceiver 302 is used to transmit and receive data and signals in method 100. The memory 303 can be used to store programs / code required by the processor 301 to execute method 100.
[0049] In a specific implementation, corresponding to the aforementioned electronic device 300, this application embodiment also provides a computer storage medium. The computer storage medium disposed in the electronic device 300 may store a program. When the program is executed, it may implement some or all of the steps in the embodiments of methods 100 to 300. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0050] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0051] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.
[0052] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0053] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0054] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a cloud gaming control device, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0055] Although alternative embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make further changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0056] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of this application should be included within the scope of protection of this invention.
Claims
1. A doctor matching method based on novel social relationships, characterized in that, The method includes: Obtain the information of the resources to be matched, and get the name of the doctor to be matched; Information is extracted from the resource information to be matched in a standardized manner to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, hospital level. The collaborator and the doctor to be matched must have at least one common attribute, including: having co-authored articles, having co-presented at conferences as speakers, being from the same city, being from the same field, being from the same department, or being from the same hospital. By filtering the doctor information database for doctors with the same name as the doctor to be matched, at least one candidate doctor is obtained; All candidate doctors are scored sequentially based on multiple dimensions, including a social dimension. A relationship score is obtained by scoring the social dimension of the candidate doctors. The relationship score represents the relationship between the candidate doctor and the collaborator, and is equal to the sum of all path scores between the candidate doctor node and the collaborator node. The path score is equal to the reciprocal of the path length multiplied by the weight multiplied by the number of collaborations, where the reciprocal of the path length is a power of the exponent, the path length is the number of edges that the candidate doctor node needs to traverse to reach the collaborator node, and the number of collaborations is the number of times the candidate doctor and the collaborator have collaborated. Calculate the matching score for each candidate doctor and sort them. The candidate doctor with the highest matching score is selected as the doctor to be matched, and the match is successful; Also includes: Each doctor is set as a node, and each doctor node has a unique identifier and multiple attributes; Create an edge between two nodes with the same attribute; Set the initial weight for each attribute; Access to a database of doctor information.
2. The method as described in claim 1, characterized in that, The calculation of the matching score for each candidate doctor includes: Pre-set weights for multiple dimensions; The scores of each dimension are multiplied by their respective weights and summed to obtain the matching score for each candidate doctor.
3. The method as described in claim 1, characterized in that, If the matching score of the candidate doctor with the highest matching score is less than the first threshold, the matching fails.
4. A doctor matching device based on a novel social relationship, characterized in that, The device includes: The receiving module obtains the resource information to be matched and gets the name of the doctor to be matched; The information extraction module extracts information from the resource information to be matched in a standardized manner to obtain the information of the doctor to be matched, including at least one of the following: collaborator's name, hospital name, department, province, city, and hospital level. The collaborator and the doctor to be matched must have at least one common attribute, including: having co-authored an article, having co-presented a conference as speakers, being from the same city, being from the same field, being from the same department, or being from the same hospital. The processing module filters doctors with the same name as the doctor to be matched from the doctor information database, obtaining at least one candidate doctor; it scores all candidate doctors sequentially according to multiple dimensions, including a social dimension, scoring the candidate doctor's social dimension to obtain a relationship score. The relationship score represents the relationship between the candidate doctor and the collaborator, and is equal to the sum of all path scores between the candidate doctor node and the collaborator node. The path score is equal to the reciprocal of the path length multiplied by the weight multiplied by the number of collaborations, where the reciprocal of the path length is a power of the exponent, the path length is the number of edges required for the candidate doctor node to reach the collaborator node, and the number of collaborations is the number of collaborations between the candidate doctor and the collaborator; it calculates the matching score for each candidate doctor and sorts them; it selects the candidate doctor with the highest matching score as the doctor to be matched, and the match is successful; it sets each doctor as a node, and each doctor node has a unique identifier and multiple attributes, establishes an edge between two nodes with the same attribute, sets the initial weight corresponding to each attribute, and obtains the doctor information database.
5. An electronic device, characterized in that, The electronic device includes a memory and one or more processors; wherein the memory is used to store computer program code, the computer program code including computer instructions; when the computer instructions are executed by the processor, the electronic device performs the method as described in any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that, Includes a computer program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 3.