Medical conference data supervision system and method based on big data
By integrating historical meeting records, identifying compliance approval process characteristics, and constructing reference meeting groups, the big data-based pharmaceutical conference data supervision system solves the compliance and guest management challenges in pharmaceutical industry conference management, and improves management efficiency and security.
Patent Information
- Application Number
- CN202410940516.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Meeting management in the pharmaceutical industry faces challenges such as difficulty in ensuring compliance, managing guests, inconvenience in information dissemination, and high security requirements.
By using a big data-based medical conference data monitoring system, historical conference records are integrated, compliance approval process characteristics are identified, reference conference groups are constructed, characteristic nodes affecting the approval rate are identified, and upcoming conference requirements are marked and prompted.
It improved the management efficiency and accuracy of compliance approval processes for medical conferences, ensured conference security and guest identification, and simplified information dissemination and guest management.
Smart Images

Figure CN118917787A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of conference process approval management, and in particular to a medical conference data supervision system and method based on big data. Background Art
[0002] The development of the pharmaceutical industry cannot be separated from the support of conference activities. Holding and conducting various academic conferences is an important and very meaningful way for industry exchanges and development. However, in the actual planning and implementation process, pharmaceutical industry conferences often have the following characteristics: 1. Strict industry supervision, compliance is difficult to control, and the progress of the conference is difficult to grasp; 2. Large scale, large number of participants, online guest registration and guest admission are difficult to manage; 3. The conference is rich in information and contains a lot of professional content. A platform that can be displayed to the outside world is needed for publishing conference information, introductions and data downloads; 4. Pharmaceutical and medical industry conferences often discuss a series of emerging medical devices, technologies, and drugs, and have high requirements for conference security. Venue security and guest identity recognition are also points of great concern to the organizers.
[0003] Therefore, the success of every medical conference event is inseparable from the support of digital technology. The medical conference event system based on the Anma BPM process digital platform breaks the platform boundaries, intelligently allocates event tasks, and realizes a task-driven working method. The WeChat public account realizes dual-platform interaction, integrates CRM, BPM and financial systems, brings efficient and convenient collaboration to users, and makes management easier. Summary of the invention
[0004] The purpose of the present invention is to provide a medical conference data supervision system and method based on big data to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for supervising medical conference data based on big data, the method comprising:
[0006] Step S1: extract all historical meeting creation records of the medical conference activity platform, and obtain the meeting requirement information released by the corresponding pharmaceutical company through the medical conference activity platform when creating a drug recommendation meeting on the medical conference activity platform from each historical meeting creation record of the medical conference activity platform through authorization;
[0007] Step S2: In each historical meeting creation record, the compliance approval process of the relevant participants created by the medical conference activity platform for the initiated drug recommendation meeting in accordance with the full business process of the standard medical conference activity and the corresponding meeting requirements information is sorted out, and the characteristic information of each approval node is sorted out;
[0008] Step S3: Evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set an approval rate threshold, sort out the numerical distribution of the approval rates of all historical drug recommendation meetings based on the approval rate threshold, and construct several reference meeting groups;
[0009] Step S4: judging and identifying the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meetings through the deviation of characteristic information presented by different historical drug recommendation meetings in each reference meeting group at the same approval node and the information deviation between the approval conditions;
[0010] Step S5: Identify and extract the characteristic information that affects the approval rate from each characteristic approval node respectively, and based on the results obtained from sorting out the frequency distribution of each characteristic information, generate a judgment basis for highlighting part of the content of the meeting request information uploaded by the pharmaceutical company and about to be released to the public when the pharmaceutical conference activity platform receives the meeting creation request initiated by the pharmaceutical company in real time, and provide key points to the applicant when initiating the meeting application.
[0011] Preferably, step S2 comprises:
[0012] Step S2-1: in each historical meeting creation record, the medical conference activity platform identifies the compliance approval process of the relevant participants for the drug recommendation meeting created in accordance with the standard full business process of the medical conference activity, and extracts the content of the approval conditions determined by the medical conference activity platform for each approval node constituting the corresponding compliance approval process according to the corresponding meeting requirement information;
[0013] The standard full business process of medical conference activities is related to the level of the corresponding medical conference activities. In this application, the compliance approval process created by the standard full business process of the same medical conference activities is assumed to be the same, that is, the approval business corresponding to each approval node is the same, but the approval conditions corresponding to each approval node are different, that is, under the same business model, the range of conditions based on the deviation between meetings is different;
[0014] Step S2-2: When the medical conference activity platform determines the corresponding approval conditions for each approval node, the information content part referenced in the meeting request information is circled, and the information content part is used as the first characteristic information of each approval node;
[0015] Step S2-3: Through authorization, from the medical conference activity platform, for each historical applicant that has passed the compliance approval process in each historical conference creation record, collect the application materials uploaded when applying for compliance qualification approval; for each approval node in the compliance approval process, automatically capture the information part captured from the application materials of each historical applicant under the preset approval mechanism;
[0016] Step S2-4: respectively collect the information parts captured in each approval node, and perform feature extraction at the same time, and use the obtained feature information as the second feature information of each approval node.
[0017] Preferably, step S3 includes:
[0018] Step S3-1: For each historical drug recommendation meeting, obtain the total number of meeting application records H initiated to the corresponding compliance approval process from the medical meeting activity platform, accumulate the total number of meeting application records N that passed the compliance approval process, and calculate the approval rate of each historical drug recommendation meeting η = N / H;
[0019] Step S3-2: classify historical drug recommendation meetings with approval rates greater than or equal to the approval rate threshold as first category meetings, and classify historical drug recommendation meetings with approval rates less than the approval rate threshold as second category meetings;
[0020] Step S3-3: Traverse the meeting requirement information released by the corresponding pharmaceutical companies through the pharmaceutical conference activity platform in each historical drug recommendation meeting; if among all the first-category meetings, the meeting requirement information corresponding to a first-category meeting meets the highest information similarity with the meeting requirement information corresponding to a second-category meeting, a first-category meeting A is combined with a first-category meeting B to construct a reference meeting group; combine all reference meeting groups; among them, if the total number of first-category meeting groups is n, the total number of reference meeting groups finally constructed is also n.
[0021] Preferably, step S4 comprises:
[0022] Step S4-1: In the reference meeting group D = {A, B} consisting of the historical drug recommendation meeting A and the historical drug recommendation meeting B, the historical drug recommendation meeting A belongs to the first category of meetings, and the historical drug recommendation meeting B belongs to the second category of meetings; respectively extract the first characteristic information, the second characteristic information, and the corresponding approval conditions corresponding to each approval node from the compliance approval process of each historical drug recommendation meeting in the reference meeting group D = {A, B};
[0023] Step S4-2: respectively obtaining, in each approval node, the content similarity α between the content of the approval conditions corresponding to the historical drug recommendation conference A and the content of the approval conditions corresponding to the historical drug recommendation conference B, and the information similarity β between the second feature information corresponding to the historical drug recommendation conference A and the second feature information corresponding to the historical drug recommendation conference B; wherein 1≥β≥0, 1≥α≥0;
[0024] Step S4-3: when (1-β) / (1-α)≥δ is satisfied in a certain approval node, the certain approval node is judged to be a characteristic approval node that affects the approval rate of the historical drug recommendation meeting B, where δ represents a threshold; all characteristic approval nodes are extracted from the reference meeting group D={A,B};
[0025] Among them, (1-β) represents the degree of information deviation between the second characteristic information corresponding to the historical drug recommendation meeting A and the second characteristic information corresponding to the historical drug recommendation meeting B at a certain approval node. If the (1-β) value is larger, it means that the similarity between the parts of the application materials that can be approved by the two historical drug recommendation meetings at this approval node is smaller; (1-α) represents the degree of content deviation between the content of the approval conditions corresponding to the historical drug recommendation meeting A and the content of the approval conditions corresponding to the historical drug recommendation meeting B at a certain approval node. If the (1-α) value is larger, it means that the similarity between the approval conditions corresponding to the two historical drug recommendation meetings at this approval node is smaller; if the (1-β) / (1-α) value is larger, it means that the historical drug recommendation meeting B made a larger change at this approval node compared with the historical drug recommendation meeting A at this approval node, resulting in a higher possibility that the approval rate of the historical drug recommendation meeting B is lower than the threshold, and the direct cause of the change in the approval node can often be traced back to the meeting request information initially issued by the pharmaceutical company.
[0026] Preferably, step S5 comprises:
[0027] Step S5-1: In each characteristic approval node extracted from any reference meeting group, the first characteristic information corresponding to the historical drug recommendation meeting belonging to the first category of meetings is used as the reference information Q 1 , the first feature information corresponding to the historical drug recommendation meeting belonging to the second category of meetings is used as the comparison information Q 2 ; respectively for the benchmark information Q 1 and comparison information Q 2 Extract feature information and obtain corresponding benchmark information Q 1 The feature information set W(Q 1 ), corresponding to the benchmark information Q 2 The feature information set W(Q 2); extract the target information set P = W (Q 2 )-W(Q 2 )∩W(Q 1 );
[0028] Step S5-2: Gather all target information sets extracted from all feature approval nodes, and in all target information sets, accumulate the frequency K of each feature information in turn; and feed back the feature information with a frequency greater than a threshold to the medical conference activity platform;
[0029] Step S5-3: Whenever the medical conference activity platform receives a conference creation request initiated by a medical company, it traverses the conference requirement information uploaded by the medical company and to be released to the public, highlights the information content parts of each feature information whose frequency is greater than the threshold, and organizes the highlighted information content parts into key information. When the applicant uploads the application materials to the medical conference activity platform, the applicant is prompted with key points.
[0030] In order to better implement the above method, a medical conference data supervision system is also proposed, which includes: a conference record sorting module, a conference data management module, a reference conference group extraction management module, a feature approval node identification and judgment module, and a conference approval auxiliary management module;
[0031] The meeting record sorting module is used to extract all historical meeting creation records of the medical conference activity platform, and obtain the meeting requirement information released by the corresponding pharmaceutical company through the medical conference activity platform when creating a drug recommendation meeting on the medical conference activity platform through authorization from each historical meeting creation record of the medical conference activity platform;
[0032] The meeting data management module is used to sort out the characteristic information of each approval node in each historical meeting creation record, based on the full business process of the standard medical meeting activities and the corresponding meeting requirements information, and the compliance approval process of the relevant participants created by the medical meeting activity platform for the initiated drug recommendation meeting;
[0033] The reference meeting group extraction management module is used to evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set the approval rate threshold, sort out the numerical distribution of the approval rate of all historical drug recommendation meetings based on the approval rate threshold, and construct several reference meeting groups;
[0034] The feature approval node identification and judgment module is used to identify the feature approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting through the feature information deviations presented by different historical drug recommendation meetings in each reference meeting group at the same approval node and the information deviations between the approval conditions;
[0035] The conference approval auxiliary management module is used to identify and extract characteristic information that affects the approval rate from each characteristic approval node. Based on the results obtained from sorting out the frequency distribution of each characteristic information, it generates a judgment basis for highlighting part of the content of the conference request information uploaded by the pharmaceutical company and about to be released to the public when the pharmaceutical conference activity platform receives the conference creation request initiated by the pharmaceutical company in real time, and provides key points to the applicant when initiating the meeting application.
[0036] Preferably, the reference conference group extraction management module includes an approval pass rate evaluation calculation unit and a reference conference group construction management unit;
[0037] The approval pass rate evaluation and calculation unit is used to evaluate and calculate the approval pass rate of the corresponding compliance approval process in each historical drug recommendation meeting;
[0038] A management unit is constructed by referring to the conference group, which is used to set the approval rate threshold, sort out the approval rates of all historical drug recommendation meetings, and construct several reference conference groups based on the numerical distribution of the approval rate threshold.
[0039] Preferably, the feature approval node identification and judgment module includes an information deviation sorting unit and a judgment and identification management unit;
[0040] The information deviation combing unit is used to comb the characteristic information deviations presented by different historical drug recommendation meetings in each reference meeting group at the same approval node, as well as the information deviations between approval conditions;
[0041] The judgment and identification management unit is used to judge and identify the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting.
[0042] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention integrates and analyzes information on all historical meeting creation records initiated by pharmaceutical companies through the pharmaceutical conference activity platform, identifies the characteristic approval information involved in each approval node in the compliance approval process of the relevant participants; then, by evaluating and calculating the approval pass rate of each historical drug recommendation meeting, all historical drug recommendation meetings are classified and managed, and a reference meeting group composed of historical drug recommendation meetings of different categories is constructed to realize the judgment and identification of characteristic approval nodes and characteristic information that affect the approval pass rate of the corresponding historical drug recommendation meetings, thereby generating a judgment basis for whether to highlight some content in the meeting requirement information uploaded by the pharmaceutical company and to be released to the outside world, and providing key points to applicants when initiating meeting applications, thereby improving the management efficiency of the pharmaceutical conference activity platform and improving the compliance approval process for the qualification approval process of the participants. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0044] Figure 1 It is a flow chart of a method for supervising medical conference data based on big data of the present invention;
[0045] Figure 2 It is a structural schematic diagram of a medical conference data supervision system based on big data of the present invention. DETAILED DESCRIPTION
[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0047] See also Figure 1-Figure 2 The present invention provides a technical solution: a method for supervising medical conference data based on big data, characterized in that the method includes:
[0048] Step S1: extract all historical meeting creation records of the medical conference activity platform, and obtain the meeting requirement information released by the corresponding pharmaceutical company through the medical conference activity platform when creating a drug recommendation meeting on the medical conference activity platform from each historical meeting creation record of the medical conference activity platform through authorization;
[0049] Step S2: In each historical meeting creation record, the compliance approval process of the relevant participants created by the medical conference activity platform for the initiated drug recommendation meeting in accordance with the full business process of the standard medical conference activity and the corresponding meeting requirements information is sorted out, and the characteristic information of each approval node is sorted out;
[0050] Wherein, step S2 comprises:
[0051] Step S2-1: in each historical meeting creation record, the medical conference activity platform identifies the compliance approval process of the relevant participants for the drug recommendation meeting created in accordance with the standard full business process of the medical conference activity, and extracts the content of the approval conditions determined by the medical conference activity platform for each approval node constituting the corresponding compliance approval process according to the corresponding meeting requirement information;
[0052] Step S2-2: When the medical conference activity platform determines the corresponding approval conditions for each approval node, the information content part referenced in the meeting request information is circled, and the information content part is used as the first characteristic information of each approval node;
[0053] Step S2-3: Through authorization, from the medical conference activity platform, for each historical applicant that has passed the compliance approval process in each historical conference creation record, collect the application materials uploaded when applying for compliance qualification approval; for each approval node in the compliance approval process, automatically capture the information part captured from the application materials of each historical applicant under the preset approval mechanism;
[0054] Step S2-4: respectively collect the information parts captured in each approval node, and perform feature extraction at the same time, and use the obtained feature information as the second feature information of each approval node;
[0055] Step S3: Evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set an approval rate threshold, sort out the numerical distribution of the approval rates of all historical drug recommendation meetings based on the approval rate threshold, and construct several reference meeting groups;
[0056] Wherein, step S3 comprises:
[0057] Step S3-1: For each historical drug recommendation meeting, obtain the total number of meeting application records H initiated to the corresponding compliance approval process from the medical meeting activity platform, accumulate the total number of meeting application records N that passed the compliance approval process, and calculate the approval rate of each historical drug recommendation meeting η = N / H;
[0058] Step S3-2: classify historical drug recommendation meetings with approval rates greater than or equal to the approval rate threshold as first category meetings, and classify historical drug recommendation meetings with approval rates less than the approval rate threshold as second category meetings;
[0059] Step S3-3: traverse the meeting requirement information released by the corresponding pharmaceutical companies through the pharmaceutical conference activity platform in each historical drug recommendation meeting; if the meeting requirement information corresponding to a first-category meeting and the meeting requirement information corresponding to a second-category meeting meet the highest information similarity among all first-category meetings, a first-category meeting A and a first-category meeting B are aggregated to construct a reference meeting group; aggregate all reference meeting groups; wherein, if the total number of first-category meeting groups is n, the total number of reference meeting groups finally constructed is also n;
[0060] Step S4: judging and identifying the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meetings through the deviation of characteristic information presented by different historical drug recommendation meetings in each reference meeting group at the same approval node and the information deviation between the approval conditions;
[0061] Wherein, step S4 comprises:
[0062] Step S4-1: In the reference meeting group D = {A, B} consisting of the historical drug recommendation meeting A and the historical drug recommendation meeting B, the historical drug recommendation meeting A belongs to the first category of meetings, and the historical drug recommendation meeting B belongs to the second category of meetings; respectively extract the first characteristic information, the second characteristic information, and the corresponding approval conditions corresponding to each approval node from the compliance approval process of each historical drug recommendation meeting in the reference meeting group D = {A, B};
[0063] Step S4-2: respectively obtaining, in each approval node, the content similarity α between the content of the approval conditions corresponding to the historical drug recommendation conference A and the content of the approval conditions corresponding to the historical drug recommendation conference B, and the information similarity β between the second feature information corresponding to the historical drug recommendation conference A and the second feature information corresponding to the historical drug recommendation conference B; wherein 1≥β≥0, 1≥α≥0;
[0064] Step S4-3: when (1-β) / (1-α)≥δ is satisfied in a certain approval node, the certain approval node is judged to be a characteristic approval node that affects the approval rate of the historical drug recommendation meeting B, where δ represents a threshold; all characteristic approval nodes are extracted from the reference meeting group D={A,B};
[0065] Step S5: Identify and extract the characteristic information that affects the approval rate from each characteristic approval node, and generate a judgment basis for highlighting part of the content of the conference request information uploaded by the pharmaceutical company and to be released to the public when the pharmaceutical conference activity platform receives the conference creation request initiated by the pharmaceutical company in real time, based on the results obtained from sorting out the frequency distribution of each characteristic information, so as to provide key points to the applicant when initiating the conference application;
[0066] Wherein, step S5 comprises:
[0067] Step S5-1: In each characteristic approval node extracted from any reference meeting group, the first characteristic information corresponding to the historical drug recommendation meeting belonging to the first category of meetings is used as the reference information Q 1 , the first feature information corresponding to the historical drug recommendation meeting belonging to the second category of meetings is used as the comparison information Q 2 ; respectively for the benchmark information Q 1 and comparison information Q2 Extract feature information and obtain corresponding benchmark information Q 1 The feature information set W(Q 1 ), corresponding to the benchmark information Q 2 The feature information set W(Q 2 ); extract the target information set P = W (Q 2 )-W(Q 2 )∩W(Q 1 );
[0068] Step S5-2: Gather all target information sets extracted from all feature approval nodes, and in all target information sets, accumulate the frequency K of each feature information in turn; and feed back the feature information with a frequency greater than a threshold to the medical conference activity platform;
[0069] Step S5-3: Whenever the medical conference activity platform receives a conference creation request initiated by a medical company, it traverses the conference requirement information uploaded by the medical company and to be released to the public, highlights the information content parts of each feature information whose frequency is greater than the threshold, and organizes the highlighted information content parts into key information. When the applicant uploads the application materials to the medical conference activity platform, the applicant is prompted with key points.
[0070] For example, the characteristic information received by the medical conference activity platform with a frequency greater than the threshold includes information a, information b, information c, and information d;
[0071] Among them, after content recognition is performed on the meeting request information uploaded by the current pharmaceutical company and to be released to the public, it is found that the feature information obtained after feature extraction of the information content part F1 in the meeting request information includes information a and information f; wherein F1 is specifically the information content part between the 3rd and 4th lines in the uploaded application document. Because it contains information a, the information content part between the 3rd and 4th lines in the application document uploaded by the pharmaceutical company can be highlighted;
[0072] Among them, after content recognition is performed on the meeting request information uploaded by the current pharmaceutical company and to be released to the public, it is found that the feature information obtained after feature extraction of the information content part F2 in the meeting request information includes information a, information d, and information g; among them, F2 is specifically the information content part between the 5th and 7th lines in the uploaded application document. Because it contains information a and information d, the information content part between the 5th and 7th lines in the application document uploaded by the pharmaceutical company can be highlighted;
[0073] Among them, after content recognition of the meeting request information uploaded by the current pharmaceutical company and about to be released to the public, it is found that the feature information obtained after feature extraction of the information content part F3 in the meeting request information includes information e, information f, and information r; among them, F2 is specifically the information content part between the 8th and 13th lines in the uploaded application document, and because it does not contain information a, information b, information c or information d, the information content part between the 8th and 13th lines in the application document uploaded by the pharmaceutical company may not be highlighted;
[0074] In order to better implement the above method, a medical conference data supervision system is also proposed, which includes: a conference record sorting module, a conference data management module, a reference conference group extraction management module, a feature approval node identification and judgment module, and a conference approval auxiliary management module;
[0075] The meeting record sorting module is used to extract all historical meeting creation records of the medical conference activity platform, and obtain the meeting requirement information released by the corresponding pharmaceutical company through the medical conference activity platform when creating a drug recommendation meeting on the medical conference activity platform through authorization from each historical meeting creation record of the medical conference activity platform;
[0076] The meeting data management module is used to sort out the characteristic information of each approval node in each historical meeting creation record, based on the full business process of the standard medical meeting activities and the corresponding meeting requirements information, and the compliance approval process of the relevant participants created by the medical meeting activity platform for the initiated drug recommendation meeting;
[0077] The reference meeting group extraction management module is used to evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set the approval rate threshold, sort out the numerical distribution of the approval rate of all historical drug recommendation meetings based on the approval rate threshold, and construct several reference meeting groups;
[0078] Among them, the reference conference group extraction management module includes an approval pass rate evaluation calculation unit and a reference conference group construction management unit;
[0079] An approval pass rate evaluation and calculation unit is used to evaluate and calculate the approval pass rate of the corresponding compliance approval process in each historical drug recommendation meeting;
[0080] A management unit is constructed by referring to the meeting group, which is used to set the approval rate threshold, sort out the approval rates of all historical drug recommendation meetings based on the numerical distribution of the approval rate threshold, and construct several reference meeting groups;
[0081] The feature approval node identification and judgment module is used to identify the feature approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting through the feature information deviations presented by different historical drug recommendation meetings in each reference meeting group at the same approval node and the information deviations between the approval conditions;
[0082] Among them, the feature approval node identification and judgment module includes an information deviation sorting unit and a judgment and identification management unit;
[0083] The information deviation combing unit is used to comb the characteristic information deviations presented by different historical drug recommendation meetings in each reference meeting group at the same approval node, as well as the information deviations between approval conditions;
[0084] A judgment and identification management unit is used to judge and identify characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting;
[0085] The conference approval auxiliary management module is used to identify and extract characteristic information that affects the approval rate from each characteristic approval node. Based on the results obtained from sorting out the frequency distribution of each characteristic information, it generates a judgment basis for highlighting part of the content of the conference request information uploaded by the pharmaceutical company and about to be released to the public when the pharmaceutical conference activity platform receives the conference creation request initiated by the pharmaceutical company in real time, and provides key points to the applicant when initiating the meeting application.
[0086] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0087] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for supervising medical conference data based on big data, characterized in that: The method comprises: Step S1: extract all historical meeting creation records of the medical conference activity platform, and obtain, by authorization, from each historical meeting creation record of the medical conference activity platform, the meeting requirement information released externally through the medical conference activity platform when the corresponding pharmaceutical company creates a drug recommendation meeting on the medical conference activity platform; Step S2: In each historical meeting creation record, the compliance approval process of the relevant participants created by the medical conference activity platform for the initiated drug recommendation meeting in accordance with the full business process of the standard medical conference activity and the corresponding meeting requirements information is sorted out, and the characteristic information of each approval node is sorted out; Step S3: Evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set an approval rate threshold, sort out the numerical distribution of the approval rates of all historical drug recommendation meetings based on the approval rate threshold, and construct several reference meeting groups; Step S4: judging and identifying the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meetings through the deviation of characteristic information presented by different historical drug recommendation meetings in each reference meeting group at the same approval node and the information deviation between the approval conditions; Step S5: Identify and extract the characteristic information that affects the approval rate from each characteristic approval node respectively, and based on the results obtained from sorting out the frequency distribution of each characteristic information, generate a judgment basis for highlighting part of the content of the meeting request information uploaded by the pharmaceutical company and about to be released to the public when the pharmaceutical conference activity platform receives the meeting creation request initiated by the pharmaceutical company in real time, and provide key points to the applicant when initiating the meeting application.
2. According to the method for supervising medical conference data based on big data in claim 1, it is characterized in that: The step S2 comprises: Step S2-1: in each historical meeting creation record, the medical conference activity platform identifies the compliance approval process of the relevant participants created for the drug recommendation meeting according to the standard full business process of the medical conference activity, and extracts the content of the approval conditions determined by the medical conference activity platform for each approval node constituting the corresponding compliance approval process according to the corresponding meeting requirement information; Step S2-2: When the medical conference activity platform determines the corresponding approval conditions for each approval node, the information content part referenced in the meeting request information is circled, and the information content part is used as the first characteristic information of each approval node; Step S2-3: Through authorization, from the medical conference activity platform, for each historical applicant that has passed the compliance approval process in each historical conference creation record, the application materials uploaded when applying for compliance qualification approval are collected; for each approval node in the compliance approval process, the information part captured from the application materials of each historical applicant is automatically captured under the preset approval mechanism; Step S2-4: respectively collect the information parts captured in each approval node, and extract features at the same time, and use the obtained feature information as the second feature information of each approval node.
3. A method for supervising medical conference data based on big data according to claim 2, characterized in that: The step S3 comprises: Step S3-1: For each historical drug recommendation meeting, obtain the total number of meeting application records H initiated to the corresponding compliance approval process from the medical meeting activity platform, accumulate the total number of meeting application records N that passed the compliance approval process, and calculate the approval rate η=N / H of each historical drug recommendation meeting; Step S3-2: classify historical drug recommendation meetings with approval rates greater than or equal to the approval rate threshold as first category meetings, and classify historical drug recommendation meetings with approval rates less than the approval rate threshold as second category meetings; Step S3-3: Traverse the meeting requirement information released by the corresponding pharmaceutical companies through the pharmaceutical conference activity platform in each historical drug recommendation meeting; if among all first-category meetings, the meeting requirement information corresponding to a first-category meeting and the meeting requirement information corresponding to a second-category meeting meet the highest information similarity, a first-category meeting A and a first-category meeting B are combined to construct a reference meeting group; all reference meeting groups are combined.
4. A method for supervising medical conference data based on big data according to claim 3, characterized in that: The step S4 comprises: Step S4-1: In the reference meeting group D = {A, B} consisting of the historical drug recommendation meeting A and the historical drug recommendation meeting B, the historical drug recommendation meeting A belongs to the first category of meetings, and the historical drug recommendation meeting B belongs to the second category of meetings; respectively extract the first characteristic information, the second characteristic information, and the corresponding approval conditions corresponding to each approval node from the compliance approval process of each historical drug recommendation meeting in the reference meeting group D = {A, B}; Step S4-2: respectively obtaining, in each approval node, the content similarity α between the content of the approval conditions corresponding to the historical drug recommendation conference A and the content of the approval conditions corresponding to the historical drug recommendation conference B, and the information similarity β between the second feature information corresponding to the historical drug recommendation conference A and the second feature information corresponding to the historical drug recommendation conference B; wherein 1≥β≥0, 1≥α≥0; Step S4-3: When (1-β) / (1-α)≥δ is satisfied in a certain approval node, the certain approval node is judged to be a characteristic approval node that affects the approval rate of the historical drug recommendation meeting B, where δ represents the threshold; all characteristic approval nodes are extracted from the reference meeting group D={A,B}.
5. A method for supervising medical conference data based on big data according to claim 4, characterized in that: The step S5 comprises: Step S5-1: In each characteristic approval node extracted from any reference meeting group, the first characteristic information corresponding to the historical drug recommendation meeting belonging to the first category of meetings is used as the reference information Q 1 , the first feature information corresponding to the historical drug recommendation meeting belonging to the second category of meetings is used as the comparison information Q 2 ; respectively for the benchmark information Q 1 and comparison information Q 2 Extract feature information and obtain corresponding benchmark information Q 1 The feature information set W(Q 1 ), corresponding to the benchmark information Q 2 The feature information set W(Q 2 ); extract the target information set P = W (Q 2 )-W(Q 2 )∩W(Q 1 ); Step S5-2: Gather all target information sets extracted from all feature approval nodes, and in all target information sets, accumulate the frequency K of each feature information in turn; and feed back the feature information with a frequency greater than a threshold to the medical conference activity platform; Step S5-3: Whenever the medical conference activity platform receives a conference creation request initiated by a medical company, it traverses the conference requirement information uploaded by the medical company and to be released to the public, highlights the information content parts of each feature information whose frequency is greater than the threshold, and organizes the highlighted information content parts into key information. When the applicant uploads the application materials to the medical conference activity platform, the applicant is prompted with key points.
6. A medical conference data supervision system, used to execute a medical conference data supervision method based on big data as described in any one of claims 1 to 5, characterized in that: The system includes: a meeting record arrangement module, a meeting data management module, a reference meeting group extraction management module, a feature approval node identification and judgment module, and a meeting approval auxiliary management module; The meeting record arrangement module is used to extract all historical meeting creation records of the medical conference activity platform, and obtain the meeting requirement information released externally through the medical conference activity platform when the corresponding pharmaceutical company creates a drug recommendation meeting on the medical conference activity platform through authorization from each historical meeting creation record of the medical conference activity platform; The conference data management module is used to sort out the characteristic information of each approval node in each historical conference creation record for the compliance approval process of the relevant participants created by the medical conference activity platform for the initiated drug recommendation conference according to the full business process of the standard medical conference activity and the corresponding meeting requirements information; The reference meeting group extraction management module is used to evaluate and calculate the approval rate of the corresponding compliance approval process in each historical drug recommendation meeting, set the approval rate threshold, sort out the numerical distribution of the approval rate of all historical drug recommendation meetings based on the approval rate threshold, and construct a number of reference meeting groups; The characteristic approval node identification and judgment module is used to judge and identify the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting through the characteristic information deviation presented in the same approval node by different historical drug recommendation meetings in each reference meeting group, and the information deviation between the approval conditions; The conference approval auxiliary management module is used to identify and extract characteristic information that affects the approval rate from each characteristic approval node, and based on the results obtained from sorting out the frequency distribution of each characteristic information, generate a judgment basis for highlighting part of the content of the conference request information uploaded by the pharmaceutical company and about to be released to the public when the pharmaceutical conference activity platform receives a conference creation request initiated by the pharmaceutical company in real time, and provide key points to the applicant when initiating the meeting application.
7. A medical conference data supervision system according to claim 6, characterized in that: The reference conference group extraction management module includes an approval pass rate evaluation calculation unit and a reference conference group construction management unit; The approval pass rate evaluation and calculation unit is used to evaluate and calculate the approval pass rate of the corresponding compliance approval process in each historical drug recommendation meeting; The reference meeting group construction management unit is used to set an approval rate threshold, sort out the approval rates of all historical drug recommendation meetings based on the numerical distribution presented by the approval rate threshold, and construct a number of reference meeting groups.
8. A medical conference data supervision system according to claim 6, characterized in that: The feature approval node identification and judgment module includes an information deviation sorting unit and a judgment and identification management unit; The information deviation combing unit is used to comb the characteristic information deviations presented by different historical drug recommendation meetings in each reference meeting group at the same approval node, as well as the information deviations between approval conditions; The judgment and identification management unit is used to judge and identify the characteristic approval nodes that have an impact on the approval rate of the corresponding historical drug recommendation meeting.
