Screening methods and related equipment for clinical trial institutions based on artificial intelligence

Abstract

The present application provides a method and related equipment for screening clinical trial institutions based on artificial intelligence, and relates to the field of computer technology. In the method, basic information, historical project experience, equipment facilities and researcher qualifications of clinical trial institutions are obtained; information extraction of basic information, historical project experience, equipment facilities and researcher qualifications is performed using a pre-trained neural network model to obtain institution information, project information, equipment information and personnel qualification information; an association relationship between institution information, project information, equipment information and personnel qualification information is established, and a recommendation model is constructed based on the association relationship; screening conditions are obtained, and information extraction of the screening conditions is performed to obtain screening keywords; based on the screening keywords, a recommendation model is used to select a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened, and the selected clinical trial institution is recommended, so as to realize intelligent screening.

Description

Technical Field

[0001] The present application relates to the field of intelligent screening of clinical trial institutions, and specifically to an artificial intelligence-based screening method and related equipment for clinical trial institutions. Background Art

[0002] At present, with the rapid development of pharmaceutical research and development, the professionalism and experience of clinical trial institutions directly affect the quality and efficiency of the trial. Selecting institutions with rich experience and professional knowledge can ensure the scientificity, rationality and operability of the trial design, thereby improving the accuracy and reliability of the trial results. Therefore, the selection of clinical trial institutions has become particularly important. In related technologies, the selection of clinical trial institutions is carried out through manual analysis and judgment, which is inefficient and prone to errors, and the human factor has a greater impact. Summary of the invention

[0003] The present application provides an artificial intelligence-based screening method and related equipment for clinical trial institutions, which can realize intelligent screening, not only with high accuracy, but also with a comprehensive reference range and little influence from human factors.

[0004] The technical solution of the embodiment of the present application is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for screening clinical trial institutions based on artificial intelligence, the method comprising:

[0006] Obtain basic information of clinical trial institutions, historical project experience, equipment and facilities, and researcher qualifications;

[0007] Using a pre-trained first neural network model to extract information from the basic information to obtain institutional information, using a pre-trained second neural network model to extract information from the historical project experience to obtain project information, using a pre-trained third neural network model to extract information from the equipment and facilities to obtain equipment information, and using a pre-trained fourth neural network model to extract information from the researcher qualifications to obtain personnel qualification information;

[0008] Establishing associations among the organization information, the project information, the equipment information, and the personnel qualification information, and constructing a recommendation model based on the associations;

[0009] Obtaining screening conditions, and extracting information from the screening conditions to obtain screening keywords;

[0010] According to the screening keywords, a clinical trial institution that meets the preset evaluation conditions is selected from a plurality of clinical trial institutions to be screened using the recommendation model, and the selected clinical trial institution is recommended.

[0011] In the above technical scheme, basic information, historical project experience, equipment and facilities, and qualifications of researchers of clinical trial institutions are obtained. By obtaining more comprehensive reference information, the accuracy of screening can be improved. The basic information is extracted using the pre-trained first neural network model to obtain the institution information. The historical project experience is extracted using the pre-trained second neural network model to obtain the project information. The equipment and facilities are extracted using the pre-trained third neural network model to obtain the equipment information. The qualifications of researchers are extracted using the pre-trained fourth neural network model to obtain the personnel qualification information. The use of neural network models for information extraction is conducive to subsequent analysis, avoids manual analysis operations, reduces errors, and realizes intelligent screening. The association between the institution information, project information, equipment information, and personnel qualification information is established, and a recommendation model is constructed based on the association, which is conducive to the subsequent use of the recommendation model for recommendation and improves accuracy. The screening conditions are obtained, and the screening conditions are extracted to obtain screening keywords. According to the screening keywords, the recommendation model is used to select clinical trial institutions that meet the preset evaluation conditions from multiple clinical trial institutions to be screened, and the selected clinical trial institutions are recommended to realize intelligent screening and reduce the influence of human factors.

[0012] In some embodiments of the present application, constructing a recommendation model according to the association relationship includes:

[0013] According to the association relationship, extracting a plurality of matching keywords and associated keywords related to each of the matching keywords;

[0014] Combining each of the matching keywords and the associated keywords to obtain a combined keyword;

[0015] Scoring the combined keywords according to a plurality of preset evaluation indicators to obtain a scoring result;

[0016] A recommendation model is obtained by performing recommendations based on the scoring results.

[0017] In some embodiments of the present application, the evaluation indicators include institution level, project success rate, and equipment standards;

[0018] The combination keyword is scored according to a plurality of preset evaluation indicators to obtain a scoring result, including:

[0019] Scoring each of the combined keywords using the institution level, the project success rate, and the equipment standard to obtain a first score corresponding to the institution level, a second score corresponding to the project success rate, and a third score corresponding to the equipment standard;

[0020] The first score, the second score and the third score are weightedly summed to obtain the score result.

[0021] In some embodiments of the present application, the establishing of the association relationship among the organization information, the project information, the equipment information and the personnel qualification information includes:

[0022] Establishing an organization-project relationship between the organization information and the project information, establishing a project-equipment relationship between the project information and the equipment information, and establishing a project-personnel relationship between the project information and the personnel qualification information;

[0023] The association relationship is obtained according to the organization-project relationship, the project-personnel relationship and the project-equipment relationship.

[0024] In some embodiments of the present application, the selecting a clinical trial institution that meets the preset evaluation conditions from a plurality of clinical trial institutions to be screened using the recommendation model according to the screening keywords includes:

[0025] According to the screening keyword, the screening keyword is matched with the keyword to be screened by using the recommendation model to obtain a matching result, and the score between the screening keyword and the related words to be screened corresponding to the keyword to be screened is calculated to obtain a matching score, wherein the keyword to be screened and the related words to be screened are obtained by processing a plurality of clinical trial institutions to be screened;

[0026] Combining the matching result and the matching score to obtain a recommendation score;

[0027] When the recommended score meets the preset evaluation conditions, a clinical trial institution corresponding to the recommended score is selected.

[0028] In some embodiments of the present application, after obtaining basic information, historical project experience, equipment and facilities, and researcher qualifications of the clinical trial institution, the method further includes:

[0029] Performing data cleaning on the basic information, the historical project experience, the equipment and facilities, and the researcher qualifications to obtain cleaned basic information corresponding to the basic information, cleaned historical project experience corresponding to the historical project experience, cleaned equipment and facilities corresponding to the equipment and facilities, and cleaned researcher qualifications corresponding to the researcher qualifications;

[0030] The cleaned basic information, the cleaned historical project experience, the cleaned equipment and facilities, and the cleaned researcher qualifications are standardized and integrated to obtain standardized structure data for information extraction.

[0031] In some embodiments of the present application, after selecting a clinical trial institution that meets the preset evaluation conditions from a plurality of clinical trial institutions to be screened using the recommendation model according to the screening keywords, and recommending the selected clinical trial institution, the method further includes:

[0032] In response to the display operation on the selected clinical trial institution, the selected clinical trial institution is visualized and counted and displayed.

[0033] In a second aspect, an embodiment of the present application provides a screening device for a clinical trial institution based on artificial intelligence, the device comprising:

[0034] Data acquisition module, used to obtain basic information of clinical trial institutions, historical project experience, equipment and facilities, and researcher qualifications;

[0035] An information processing module is used to extract information from the basic information using a pre-trained first neural network model to obtain institutional information, to extract information from the historical project experience using a pre-trained second neural network model to obtain project information, to extract information from the equipment and facilities using a pre-trained third neural network model to obtain equipment information, and to extract information from the researcher qualifications using a pre-trained fourth neural network model to obtain personnel qualification information;

[0036] A model building module, used to establish an association relationship between the organization information, the project information, the equipment information and the personnel qualification information, and to build a recommendation model based on the association relationship;

[0037] The condition acquisition and processing module is used to acquire the screening conditions and extract information from the screening conditions to obtain screening keywords;

[0038] The screening recommendation module is used to select a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened based on the screening keywords and using the recommendation model, and recommend the selected clinical trial institution.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a user interface, a communication bus and a network interface, wherein the processor, the memory, the user interface and the network interface are respectively connected to the communication bus, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods provided in the first aspect.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any one of the methods provided in the first aspect is executed.

[0041] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0042] 1. By obtaining the basic information, historical project experience, equipment and facilities, and qualifications of researchers of clinical trial institutions, more comprehensive reference information can be obtained, which can improve the accuracy of screening; using the pre-trained first neural network model to extract basic information, obtain institutional information, using the pre-trained second neural network model to extract historical project experience, obtain project information, using the pre-trained third neural network model to extract equipment and facilities, obtain equipment information, using the pre-trained fourth neural network model to extract researcher qualifications, obtain personnel qualification information, and using the neural network model to extract information is conducive to subsequent analysis, and also avoids manual analysis operations, reduces errors, and realizes intelligent screening; establishes the association between institutional information, project information, equipment information, and personnel qualification information, and constructs a recommendation model based on the association, which is conducive to the subsequent recommendation of the recommendation model and improves accuracy; obtains screening conditions, and extracts information from the screening conditions to obtain screening keywords; according to the screening keywords, uses the recommendation model to select clinical trial institutions that meet the preset evaluation conditions from multiple clinical trial institutions to be screened, and recommends the selected clinical trial institutions, realizes intelligent screening, and reduces the influence of human factors. Therefore, the problem of low manual efficiency and easy errors in related technologies and the large influence of human factors is effectively solved.

[0043] 2. Through multi-dimensional and multi-indicator evaluation, a more comprehensive evaluation can further improve the accuracy of screening.

[0044] 3. Through visualization, users can quickly understand and select appropriate clinical trial institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is one of the flow diagrams of a method for screening clinical trial institutions based on artificial intelligence provided in one embodiment of the present application;

[0046] Figure 2 yes Figure 1 A schematic flow chart of a sub-step of step S300;

[0047] Figure 3 yes Figure 1 Another sub-step flow chart of step S300;

[0048] Figure 4 yes Figure 3 A schematic flow chart of a sub-step of step S350;

[0049] Figure 5 yes Figure 1 A schematic flow chart of a sub-step of step S500;

[0050] Figure 6 It is a schematic diagram of the structure of a screening device for a clinical trial institution based on artificial intelligence provided by one embodiment of the present application;

[0051] Figure 7 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0053] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0054] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0055] The embodiments of the present application provide a method, device, electronic device and readable storage medium for screening clinical trial institutions based on artificial intelligence. The method for screening clinical trial institutions based on artificial intelligence first obtains basic information, historical project experience, equipment and facilities, and qualifications of researchers of the clinical trial institutions to obtain more comprehensive reference information, which can improve the accuracy of screening; uses a pre-trained first neural network model to extract information from the basic information to obtain institutional information, uses a pre-trained second neural network model to extract information from historical project experience to obtain project information, uses a pre-trained third neural network model to extract information from equipment and facilities to obtain equipment information, and uses a pre-trained fourth neural network model to extract information from researchers. The information of personnel qualifications is extracted to obtain the personnel qualification information. The information extraction by using the neural network model is beneficial to the subsequent analysis, avoids manual analysis operation, reduces errors, and realizes intelligent screening. The association relationship between the institution information, project information, equipment information and personnel qualification information is established, and a recommendation model is constructed according to the association relationship, which is beneficial to the subsequent use of the recommendation model for recommendation and improves accuracy. The screening conditions are obtained, and the information of the screening conditions is extracted to obtain the screening keywords. According to the screening keywords, the recommendation model is used to select the clinical trial institutions that meet the preset evaluation conditions from multiple clinical trial institutions to be screened, and the selected clinical trial institutions are recommended to realize intelligent screening and reduce the influence of human factors.

[0056] It should be noted that this artificial intelligence-based clinical trial institution screening method is applied to the selection of clinical trial institutions in the process of pharmaceutical research and development. Through multi-dimensional evaluation and the application of artificial intelligence technology in the selection of clinical trial institutions, it achieves rapid and accurate screening of clinical trial institutions and improves screening efficiency and accuracy; at the same time, it reduces the interference of human factors and better meets the rapidly changing needs of clinical trials.

[0057] The technical solution provided in the embodiments of the present application is further described below in conjunction with the accompanying drawings.

[0058] Reference Figure 1 , Figure 1 It is a flowchart of a method for screening clinical trial institutions based on artificial intelligence provided by an embodiment of the present application. The method for screening clinical trial institutions based on artificial intelligence is applied to a screening device for clinical trial institutions based on artificial intelligence, and the method for screening clinical trial institutions based on artificial intelligence is executed by a processor in an electronic device or a readable storage medium, and the method for screening clinical trial institutions based on artificial intelligence includes steps S100, S200, S300, S400, and S500.

[0059] Step S100, obtaining basic information, historical project experience, equipment and facilities, and researcher qualifications of the clinical trial institution.

[0060] In one embodiment, the basic information includes: the name of the institution, the geographical location of the institution, the type of institution, the time of establishment, and the qualification certificates such as the institution's qualification certificate and the institution's filing certificate; historical project experience includes completed projects, ongoing projects, and project success rates; equipment settings include key equipment used for clinical trials, the status of the equipment, and facility conditions; researcher qualifications include researchers, the qualifications certificates and research experience that researchers have. The basic information, historical project experience, equipment facilities, and researcher qualifications of clinical trial institutions can be collected by visiting the official websites of various clinical trial institutions; data can also be obtained through government platform announcements; data can also be obtained through third-party databases, and can also be in other forms, which will not be elaborated here. By obtaining more comprehensive reference information, the accuracy of screening can be improved and support can be provided for subsequent screening.

[0061] In one embodiment, after obtaining the basic information, historical project experience, equipment and facilities, and qualifications of researchers of the clinical trial institution, the screening method of the clinical trial institution based on artificial intelligence also includes but is not limited to: performing data cleaning on the basic information, historical project experience, equipment and facilities, and qualifications of researchers to obtain the cleaned basic information corresponding to the basic information, the cleaned historical project experience corresponding to the historical project experience, the cleaned equipment and facilities corresponding to the equipment and facilities, and the cleaned researcher qualifications corresponding to the researcher qualifications.

[0062] In some possible embodiments of the present application, data cleaning includes outlier processing and data format conversion. Since there may be missing data in basic information, historical project experience, equipment and facilities, and researcher qualifications, the missing values ​​of the basic information, historical project experience, equipment and facilities, and researcher qualifications are first supplemented to improve the accuracy of recommendations.

[0063] In other possible embodiments of the present application, since the data is relatively comprehensive and divided into data of different dimensions, the data format may not be unified. Then, the cleaned basic information, cleaned historical project experience, cleaned equipment and facilities, and cleaned researcher qualifications are standardized and integrated respectively. Standardizing the data can represent the multi-dimensional data in a unified format, and then the standardized data is integrated according to structured data to obtain standardized structured data, so that the neural network model can be used to extract information from the data later.

[0064] Step S200, using the pre-trained first neural network model to extract basic information to obtain institutional information, using the pre-trained second neural network model to extract historical project experience to obtain project information, using the pre-trained third neural network model to extract equipment and facilities information to obtain equipment information, using the pre-trained third neural network model to extract researcher qualifications information to obtain personnel qualification information.

[0065] In one embodiment, the pre-trained first neural network model, the pre-trained second neural network model, the pre-trained third neural network model, and the pre-trained third neural network model can be the same network model structure or different network model structures. Exemplarily, taking the same network model structure as an example, the pre-trained first neural network model can be a recurrent neural network model or a variant of a recurrent neural network model or a graph convolutional neural network, etc., and the training method is not repeated here. The basic information is extracted using a graph convolutional neural network to obtain institutional information, which includes the name of the institution and the type of institution, etc.; the historical project experience is extracted using a graph convolutional neural network to obtain project information, which includes the category of completed projects and the success rate of the project, etc.; the equipment and facilities are extracted using a graph convolutional neural network to obtain equipment information, which includes key equipment and facility conditions, etc.; the researcher qualifications are extracted using a graph convolutional neural network to obtain personnel qualification information, which includes researcher qualifications and research experience. By using a neural network model for information extraction, subsequent analysis is facilitated, manual analysis operations are avoided, errors are reduced, and intelligent screening is achieved.

[0066] Step S300, establishing associations among organization information, project information, equipment information and personnel qualification information, and constructing a recommendation model based on the associations.

[0067] In one embodiment, based on the organization information, project information, equipment information and personnel qualification information obtained in step S200, an association relationship is established among the organization information, project information, equipment information and personnel qualification information, and a recommendation model is constructed based on the association relationship, which is conducive to the subsequent use of the recommendation model to improve accuracy.

[0068] like Figure 2 As shown, establishing the association relationship between the organization information, project information, equipment information and personnel qualification information includes but is not limited to the following steps:

[0069] Step S310, constructing an organization-project relationship between the organization information and the project information, constructing a project-equipment relationship between the project information and the equipment information, and constructing a project-personnel relationship between the project information and the personnel qualification information.

[0070] In one embodiment, according to step S200, the institution information includes the institution name and the institution type, the institution information includes the institution name and the institution type; the project information includes the category of completed projects and the project success rate; the equipment information includes key equipment and facility conditions; the personnel qualification information includes the qualifications and research experience of researchers. The institution type can be represented by the level of the hospital, such as a tertiary hospital, a secondary hospital, etc. The institution type is affected by projects, equipment and researchers, and the institution-project connection between the institution information and the project information is established through the institution type, project category and project success rate. The project category and project success rate in the project information will also be affected by key equipment and facility conditions, and the project-equipment connection between the project information and the equipment information will be established; the project category and project success rate will also be affected by the qualifications and experience of the R&D personnel, and the project-personnel connection between the project information and the personnel qualification information will be established. By establishing a connection, each piece of information can be related to each other and have an impact, thereby realizing reference multi-dimensional indicator screening and improving screening accuracy.

[0071] Step S320, obtaining association relationships based on the organization-project relationship, the project-personnel relationship, and the project-equipment relationship.

[0072] In one embodiment, the organization information is not only affected by the project information, but also by the equipment information and the personnel qualification information. The project-personnel connection and project-equipment connection projects are established to associate all the connections. The organization-project connection, project-personnel connection and project-equipment connection are summarized, and the organization information is connected with the project information to form a connection edge. The project information is respectively associated with the personnel qualification information and the equipment information to form a connection edge, and finally a total association relationship is formed. According to the association relationship, it is beneficial to use the recommendation model for subsequent recommendations and improve the accuracy.

[0073] like Figure 3 As shown, building a recommendation model based on the association relationship includes but is not limited to the following steps:

[0074] Step S330: extract multiple matching keywords and related keywords related to each matching keyword according to the association relationship.

[0075] In one embodiment, a plurality of matching keywords are extracted according to the association relationship using a keyword extraction algorithm, and the keyword extraction algorithm may be Word2Vec or HITS algorithm, etc. And the associated keywords related to each matching keyword are obtained according to the matching keywords and the connection relationship, and the matching keywords and the associated keywords are obtained so as to obtain the combined keywords in the subsequent step, thereby scoring.

[0076] Step S340: Combine each matching keyword and associated keyword to obtain a combined keyword.

[0077] In one embodiment, each matching keyword can be combined with an associated keyword corresponding to the matching keyword, and the combination method can be specifically to concatenate the matching keyword and the associated keyword to obtain multiple groups of combined keywords. The combination method can also be to summarize the matching keyword and the associated keyword to obtain multiple combined keywords, and by obtaining the combined keywords, the accuracy of intelligent screening can be improved.

[0078] Step S350, scoring the combined keywords according to a plurality of preset evaluation indicators to obtain a scoring result.

[0079] In one embodiment, the evaluation indicators include institution level, project success rate and equipment standards; Figure 4 As shown, the combined keywords are scored according to a plurality of preset evaluation indicators to obtain a scoring result, including but not limited to the following steps:

[0080] Step S351, using the institution level, project success rate and equipment standard to score each combination keyword respectively, to obtain a first score corresponding to the institution level, a second score corresponding to the project success rate and a third score corresponding to the equipment standard;

[0081] In some possible embodiments of the present application, the organization level is represented by different scores, the project success rate is also represented by scores, and the equipment standard is also represented by scores. Exemplarily, the structure level is divided into three levels, 1-3 is divided into the first level, 4-6 is divided into the second level, 7-9 is divided into the third level, etc. The project success rate is expressed as 1 for complete success, 8-9 is good, 6-7 is passed, and the project below 6 points is unsuccessful. The equipment standard adopts 8-10 points for new equipment and good facilities, 5-8 points for general, and 5 points or less for poor conditions. According to the above standards, the combination keywords are scored according to the organization level to obtain the first score, the project success rate standard is scored to obtain the second score, and the equipment standard index is scored to obtain the third score. By obtaining the first score, the second score and the third score for subsequent calculation of the total score of multiple dimensions, the screening accuracy is further improved.

[0082] Step S352: Perform weighted summation on the first score, the second score, and the third score to obtain a score result.

[0083] In some possible embodiments of the present application, the first score, the second score, and the third score obtained in step S351 are weighted and summed, specifically: the first score, the second score, and the third score can be directly added to obtain a scoring result; corresponding weights can also be set for the first score, the second score, and the third score, respectively, and the total weight ratio is 1. A score with a higher weight ratio is set according to experience and actual needs, and the first score, the second score, and the third score are respectively multiplied by the corresponding weights, and then the three product results are added to obtain a scoring result. Obtaining a scoring result is conducive to the subsequent recommendation model to perform screening and recommendation.

[0084] Step S360: perform recommendation based on the scoring results to obtain a recommendation model.

[0085] In one embodiment, the rule of the recommendation model is to select the institution with the highest score from the scoring results, or select the top N institutions from the scoring results, where N can be 5, 6, or 7. Then manually screen the top N institutions. It should be noted that to select the top N institutions, the scoring results must be sorted in descending order before selection.

[0086] Step S400, obtaining screening conditions, and extracting information from the screening conditions to obtain screening keywords.

[0087] In one embodiment, the screening condition includes one or more of project experience, personnel qualifications and equipment settings. The screening requirement is manually input in the displayed input box, and the screening condition is obtained by reading the content of the input box. Since the key points of the conditions input by the user may not be very obvious, a guiding word can be set, and Word2Vec can be used to extract information from the screening condition to obtain the screening keyword for subsequent matching and screening.

[0088] Step S500, based on the screening keywords, a clinical trial institution that meets the preset evaluation conditions is selected from a plurality of clinical trial institutions to be screened using a recommendation model, and the selected clinical trial institution is recommended.

[0089] like Figure 5 As shown, according to the screening keywords, a recommendation model is used to select a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened, including but not limited to the following steps:

[0090] Step S510, according to the screening keywords, use the recommendation model to match the screening keywords with the keywords to be screened to obtain a matching result, and calculate the score between the screening keywords and the related words to be screened corresponding to the keywords to be screened to obtain a matching score, wherein the keywords to be screened and the related words to be screened are obtained by processing multiple clinical trial institutions to be screened.

[0091] In one embodiment, the keywords to be screened and the related words to be screened are obtained by processing a plurality of clinical trial institutions to be screened, and the processing is similar to step S200 and will not be described in detail here. According to the screening keywords, using the recommendation rules of the recommendation model, the screening keywords are first matched with the keywords to be screened using a string matching algorithm to obtain a matching result, which is expressed in the form of a score, and the screening keywords and the related words to be screened corresponding to the keywords to be screened are scored using a string matching algorithm to obtain a matching score, which is expressed in the form of a score. By calculating the scores of the screening keywords, the keywords to be screened and the related words to be screened, respectively, and evaluating from multiple indicators, the accuracy of the screening is further improved.

[0092] Step S520: Combine the matching result and the matching score to obtain a recommendation score.

[0093] In one embodiment, the matching result and the matching score obtained in step S510 are both expressed in the form of scores. The matching result and the matching score can be added to obtain a recommendation score. Alternatively, corresponding weights can be set for the matching result and the matching score, respectively, and the total weight ratio is 1. A score with a higher weight ratio is set based on experience and actual needs, and the matching result is multiplied by its corresponding weight, and the matching score is multiplied by its corresponding weight, and then the obtained product results are added to obtain a recommendation score. Obtaining a recommendation score is conducive to subsequent screening and recommendation.

[0094] Step S530: When the recommended score meets the preset evaluation conditions, a clinical trial institution corresponding to the recommended score is selected.

[0095] In one embodiment, the preset evaluation condition is a score set based on experience. When the recommendation score is greater than the set score, the clinical trial institution corresponding to the highest recommendation score is screened out and recommended. Intelligent recommendation can be achieved, human intervention can be reduced, and the impact of human factors can be reduced. When the recommendation score is less than the set score, no recommendation is made.

[0096] In one embodiment, after selecting a clinical trial institution that meets preset evaluation conditions from multiple clinical trial institutions to be screened using a recommendation model based on screening keywords and recommending the selected clinical trial institution, the screening method for clinical trial institutions based on artificial intelligence also includes but is not limited to: in response to a display operation on the selected clinical trial institution, visually counting the selected clinical trial institution and displaying it.

[0097] In some possible embodiments of the present application, the screening method of clinical trial institutions based on artificial intelligence is applied to the back-end server and interacts with the front-end. In response to the display operation of the selected clinical trial institution, the back-end server receives the display information, calls the visualization processing program, performs visual automatic statistics on the selected clinical trial institution, and transmits the statistical results to the front-end page for display. Among them, the visualization processing program can be an Excel spreadsheet or a visualization program written in Python. By performing visualization, it is convenient for users to quickly understand and select suitable clinical trial institutions.

[0098] like Figure 6 As shown, the embodiment of the present application provides a screening device 100 for clinical trial institutions based on artificial intelligence. The screening device 100 for clinical trial institutions based on artificial intelligence obtains basic information, historical project experience, equipment and facilities, and qualifications of researchers of clinical trial institutions through a data acquisition module 110. By obtaining more comprehensive reference information, the accuracy of screening can be improved; the basic information is extracted by a pre-trained first neural network model through an information processing module 120 to obtain institutional information, the historical project experience is extracted by a pre-trained second neural network model to obtain project information, the equipment and facilities are extracted by a pre-trained third neural network model to obtain equipment information, and the qualifications of researchers are extracted by a pre-trained fourth neural network model to obtain Personnel qualification information is extracted by using a neural network model, which is beneficial to subsequent analysis, avoids manual analysis operations, reduces errors, and realizes intelligent screening; then the model building module 130 is used to establish the association between the institution information, project information, equipment information and personnel qualification information, and a recommendation model is built based on the association, which is beneficial to the subsequent use of the recommendation model to improve accuracy; the condition acquisition and processing module 140 is used to obtain the screening conditions, and the information of the screening conditions is extracted to obtain the screening keywords; then the screening recommendation module 150 is used to select the clinical trial institutions that meet the preset evaluation conditions from multiple clinical trial institutions to be screened based on the screening keywords and the recommendation model, and the selected clinical trial institutions are recommended to realize intelligent screening and reduce the influence of human factors.

[0099] It should be noted that the data acquisition module 110 is connected to the information processing module 120, the information processing module 120 is connected to the model building module 130, the model building module 130 is connected to the condition acquisition and processing module 140, and the condition acquisition and processing module 140 is connected to the screening recommendation module 150. The above-mentioned artificial intelligence-based clinical trial institution screening method is applied to the artificial intelligence-based clinical trial institution screening device 100. The artificial intelligence-based clinical trial institution screening device 100 realizes rapid and accurate screening of clinical trial institutions through multiple-dimensional evaluation and application of artificial intelligence technology in the selection of clinical trial institutions, thereby improving screening efficiency and accuracy; at the same time, it reduces the interference of human factors and better meets the rapidly changing clinical trial needs.

[0100] It should also be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0101] The present application also discloses an electronic device. Figure 7 , Figure 7 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0102] The communication bus 502 is used to realize the connection and communication between these components.

[0103] The user interface 503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0104] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0105] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0106] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. Refer to Figure 7 , the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a screening method for a clinical trial institution based on artificial intelligence.

[0107] exist Figure 7In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 501 can be used to call the application program stored in the memory 505 for a screening method of a clinical trial institution based on artificial intelligence. When executed by one or more processors 501, the electronic device 500 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0108] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0112] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, 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, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0113] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0114] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for screening clinical trial institutions based on artificial intelligence, characterized in that: The method comprises: Obtain basic information of clinical trial institutions, historical project experience, equipment and facilities, and researcher qualifications; Using a pre-trained first neural network model to extract information from the basic information to obtain institutional information, using a pre-trained second neural network model to extract information from the historical project experience to obtain project information, using a pre-trained third neural network model to extract information from the equipment and facilities to obtain equipment information, and using a pre-trained fourth neural network model to extract information from the researcher qualifications to obtain personnel qualification information; Establishing associations among the institution information, the project information, the equipment information and the personnel qualification information, and constructing a recommendation model based on the associations; constructing the recommendation model based on the associations, including: extracting multiple matching keywords and associated keywords related to each matching keyword according to the associations; combining each matching keyword and the associated keywords to obtain a combined keyword; scoring the combined keyword according to multiple preset evaluation indicators to obtain a scoring result; recommending a recommendation model based on the scoring result; the evaluation indicators include institution level, project success rate and equipment standard; scoring the combined keyword according to multiple preset evaluation indicators to obtain a scoring result, including: using the institution level, project success rate and equipment standard to power and the equipment standard respectively score each of the combined keywords to obtain a first score corresponding to the institution level, a second score corresponding to the project success rate, and a third score corresponding to the equipment standard; weighted sum the first score, the second score, and the third score to obtain the scoring result; the establishment of the association relationship between the institution information, the project information, the equipment information, and the personnel qualification information includes: constructing an institution-project connection between the institution information and the project information, constructing a project-equipment connection between the project information and the equipment information, and constructing a project-personnel connection between the project information and the personnel qualification information; obtaining the association relationship according to the institution-project connection, the project-personnel connection, and the project-equipment connection; Obtaining screening conditions, and extracting information from the screening conditions to obtain screening keywords; According to the screening keywords, the recommendation model is used to select a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened, and the selected clinical trial institution is recommended; the method of selecting a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened according to the screening keywords and the recommendation model includes: according to the screening keywords, the recommendation model is used to match the screening keywords with the keywords to be screened to obtain a matching result, and the score between the screening keywords and the related words to be screened corresponding to the keywords to be screened is calculated to obtain a matching score, wherein the keywords to be screened and the related words to be screened are obtained by processing multiple clinical trial institutions to be screened; the matching result and the matching score are combined to obtain a recommendation score; when the recommendation score meets the preset evaluation conditions, the clinical trial institution corresponding to the recommendation score is selected.

2. The method according to claim 1, characterized in that After obtaining the basic information, historical project experience, equipment and facilities, and researcher qualifications of the clinical trial institution, the method further includes: Perform data cleaning on the basic information, the historical project experience, the equipment and facilities, and the researcher qualifications to obtain the cleaned basic information corresponding to the basic information, the cleaned historical project experience corresponding to the historical project experience, the cleaned equipment and facilities corresponding to the equipment and facilities, and the cleaned researcher qualifications corresponding to the researcher qualifications; standardize and integrate the cleaned basic information, the cleaned historical project experience, the cleaned equipment and facilities, and the cleaned researcher qualifications to obtain standardized structure data for information extraction.

3. The method according to claim 1, characterized in that After selecting a clinical trial institution that meets the preset evaluation conditions from a plurality of clinical trial institutions to be screened using the recommendation model according to the screening keywords and recommending the selected clinical trial institution, the method further includes: In response to the display operation on the selected clinical trial institution, the selected clinical trial institution is visualized and counted and displayed.

4. A screening device for clinical trial institutions based on artificial intelligence, characterized in that: The device comprises: A data acquisition module (110) is used to obtain basic information, historical project experience, equipment and facilities, and researcher qualifications of clinical trial institutions; An information processing module (120) is used to extract information from the basic information using a pre-trained first neural network model to obtain institutional information, to extract information from the historical project experience using a pre-trained second neural network model to obtain project information, to extract information from the equipment and facilities using a pre-trained third neural network model to obtain equipment information, and to extract information from the researcher qualifications using a pre-trained fourth neural network model to obtain personnel qualification information; A model building module (130) is used to establish associations among the organization information, the project information, the equipment information and the personnel qualification information, and to build a recommendation model based on the associations; the building of the recommendation model based on the associations includes: extracting multiple matching keywords and associated keywords related to each matching keyword according to the associations; combining each matching keyword and the associated keywords to obtain a combined keyword; scoring the combined keyword according to multiple preset evaluation indicators to obtain a scoring result; and recommending a recommendation model based on the scoring result; the evaluation indicators include organization level, project success rate and equipment standard; scoring the combined keyword according to multiple preset evaluation indicators to obtain a scoring result includes: using the organization level The method further comprises: scoring each of the combined keywords according to the level of the organization, the project success rate and the equipment standard, and obtaining a first score corresponding to the organization level, a second score corresponding to the project success rate and a third score corresponding to the equipment standard; performing weighted summation on the first score, the second score and the third score to obtain the scoring result; establishing an association relationship among the organization information, the project information, the equipment information and the personnel qualification information, including: constructing an organization-project connection between the organization information and the project information, constructing a project-equipment connection between the project information and the equipment information, and constructing a project-personnel connection between the project information and the personnel qualification information; obtaining the association relationship according to the organization-project connection, the project-personnel connection and the project-equipment connection; A condition acquisition and processing module (140) is used to acquire screening conditions and extract information from the screening conditions to obtain screening keywords; A screening recommendation module (150) is used to select a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened using the recommendation model according to the screening keyword, and recommend the selected clinical trial institution; the method of selecting a clinical trial institution that meets the preset evaluation conditions from multiple clinical trial institutions to be screened using the recommendation model according to the screening keyword includes: matching the screening keyword with the keyword to be screened using the recommendation model according to the screening keyword to obtain a matching result, and calculating a score between the screening keyword and the related words to be screened corresponding to the keyword to be screened to obtain a matching score, wherein the keyword to be screened and the related words to be screened are obtained by processing multiple clinical trial institutions to be screened; combining the matching result and the matching score to obtain a recommendation score; and selecting the clinical trial institution corresponding to the recommendation score when the recommendation score meets the preset evaluation conditions.

5. An electronic device, characterized in that: The electronic device (500) comprises a processor (501), a memory (505), a user interface (503), a communication bus (502) and a network interface (504), wherein the processor (501), the memory (505), the user interface (503) and the network interface (504) are respectively connected to the communication bus (502), the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to communicate with other devices, and the processor (501) is used to execute the instructions stored in the memory (505) so that the electronic device (500) executes the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 3 is performed.

Images