Device and method for recommending contract research organization and supporting contract

Abstract

Disclosed are a device and a method for recommending a contract research organization by analyzing a request for proposal (RFP), and for supporting a contract by reviewing errors in a quotation and the contract. The device for recommending a contract research organization and supporting a contract, according to one embodiment, may comprise: a matching unit for recommending one or more contract research organizations on the basis of an RFP for contract research organizations, received from a user; a quotation unit for performing quotation information generation and quotation suitability determination for at least one of the recommended one or more contract research organizations; and a contract unit for providing a contract error analysis and contract editing function for a contract research organization.

Description

Devices and methods for recommending and supporting contracts with clinical trial contract institutions

[0001] This relates to a device and method for recommending a clinical trial contract organization by analyzing a request for proposal and supporting a contract by reviewing errors in the quotation and contract.

[0002] Traditionally, sponsors have struggled to assess the capabilities of contract research organizations due to a lack of a systematic and reliable channel for collecting key information, including the organization's performance record, countries eligible for clinical trials, the number of clinical trials underway for each disease and drug, and analytical equipment. For this reason, sponsors tend to rely on the connections of consultants who specialize in matching clients with contract research organizations. This, in turn, carries the risk of contracts with contract research organizations being concluded at a higher price than market rates.

[0003] Korean Patent Publication No. 10-2017-0027576 discloses a researcher recommendation device and method based on research history matching.

[0004] The purpose is to provide a device and method to recommend a clinical trial contract organization by analyzing a request for proposal and to support a contract by reviewing errors in the quotation and contract.

[0005] According to one aspect, a clinical trial contract agency recommendation and contract support device may include a matching unit that recommends one or more clinical trial contract agencies based on a Request for Proposal (RFP) for clinical trial contract agencies received from a user; a quotation unit that generates quotation information for at least one of the recommended one or more clinical trial contract agencies and determines quotation appropriateness; and a contract unit that provides a contract error analysis and contract editing function for the clinical trial contract agency.

[0006] The matching unit can generate binary variable vectors and continuous variable vectors for requirements according to predetermined rules based on one or more requirements included in the request for proposal.

[0007] The matching unit can generate binary variable vectors and continuous variable vectors for institution data based on one or more matched proposal requests for clinical trial contracts stored in a database.

[0008] The matching unit generates a binary variable matrix by calculating the outer product between the binary variable vector for the requirement and the binary variable vector for the agency data, and can generate a continuous variable matrix by calculating the outer product between the continuous variable vector for the requirement and the continuous variable vector for the agency data.

[0009] The matching unit can calculate an evaluation score for one or more clinical trial contract institutions based on a binary variable matrix and a continuous variable matrix.

[0010] The matching unit may sort one or more clinical trial contract organizations based on evaluation scores for one or more clinical trial contract organizations, and may recommend one or more clinical trial contract organizations based on the ranking of the sorted one or more clinical trial contract organizations and the scope of work of the one or more clinical trial contract organizations.

[0011] The matching unit displays the user's location and one or more recommended clinical trial contract institutions on a map, and can determine the display color of one or more recommended clinical trial contract institutions based on the ranking of the clinical trial contract institutions.

[0012] The matching unit receives an input for selecting at least one of one or more clinical trial contract organizations recommended by the user, and may request a quotation from at least one of the selected clinical trial contract organizations.

[0013] The quotation department generates quotation information by calculating an expected quotation cost based on previously stored quotations for one or more recommended clinical trial contract organizations, and can compare the expected quotation cost with the quotation cost received from one or more recommended clinical trial contract organizations to determine the appropriateness of the quotation.

[0014] If there is an error in the quotation adequacy judgment, the quotation department transmits error information to the clinical trial contract organization that sent the quotation with the error. If there is no error in the quotation adequacy judgment, the quotation received from the clinical trial contract organization can be transmitted to the user.

[0015] The contract department may perform contract error analysis for clinical trial contract recipients using an artificial neural network trained to review at least one of data format, content consistency, and content omissions.

[0016] According to one aspect, a method for recommending and supporting a contract for a clinical trial contract organization, performed on a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors, may include a matching step of recommending one or more clinical trial contract organizations based on a Request For Proposal (RFP) for a clinical trial contract organization received from a user; a quotation step of generating quotation information and determining quotation appropriateness for at least one of the one or more recommended clinical trial contract organizations; and a contract step of providing a contract error analysis and contract editing function for the clinical trial contract organization.

[0017] The matching step can generate binary variable vectors and continuous variable vectors for requirements according to predetermined rules based on one or more requirements included in the request for proposal.

[0018] The matching step may generate binary variable vectors and continuous variable vectors for institution data based on one or more matched requests for proposals for each clinical trial contract institution stored in the database.

[0019] The matching step generates a binary variable matrix by calculating the cross product between the binary variable vector for requirements and the binary variable vector for agency data, and can generate a continuous variable matrix by calculating the cross product between the continuous variable vector for requirements and the continuous variable vector for agency data.

[0020] The matching step can calculate evaluation scores for one or more clinical trial contract organizations based on a binary variable matrix and a continuous variable matrix.

[0021] The matching step may sort one or more clinical trial contract organizations based on evaluation scores for one or more clinical trial contract organizations, and may recommend one or more clinical trial contract organizations based on the ranking of the sorted one or more clinical trial contract organizations and the scope of work of the one or more clinical trial contract organizations.

[0022] The matching step displays the user's location and one or more recommended clinical trial contract organizations on a map, and may determine the display color of one or more recommended clinical trial contract organizations based on the ranking of the clinical trial contract organizations.

[0023] The matching step receives input from the user to select at least one of one or more recommended clinical trial contract organizations, and may request a quotation from at least one of the selected clinical trial contract organizations.

[0024] The quotation step generates quotation information by calculating an expected quotation cost based on previously stored quotations for one or more recommended clinical trial contract organizations, and can compare the expected quotation cost with the quotation cost received from one or more recommended clinical trial contract organizations to determine the appropriateness of the quotation.

[0025] In the quotation step, if there is an error in the quotation adequacy judgment, the error information is sent to the clinical trial contract organization that sent the quotation with the error. If there is no error in the quotation adequacy judgment, the quotation received from the clinical trial contract organization can be sent to the user.

[0026] The contract stage may perform contract error analysis for clinical trial contract recipients using an artificial neural network trained to review at least one of data format, content consistency, and content omissions.

[0027] By automatically analyzing Requests for Proposals (RFPs) and recommending clinical trial contract providers, users can determine which contract providers possess the capabilities they desire. Furthermore, by reviewing estimates and contracts for errors, the system can assist in securing a secure contract at an appropriate cost.

[0028] Figure 1 is a configuration diagram of a clinical trial contract institution recommendation and contract support device according to one embodiment.

[0029] Figures 2 to 4 are exemplary diagrams for explaining the operation of a clinical trial contract institution recommendation and contract support device, for example.

[0030] Figure 5 is a flowchart illustrating a method for recommending and supporting a contract with a clinical trial contract institution according to one embodiment.

[0031] Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings. In describing the present invention, detailed descriptions of known functions or configurations will be omitted if they are deemed to unnecessarily obscure the gist of the present invention. Furthermore, the terms described below are defined based on their functions in the present invention and may vary depending on the intentions or practices of the user or operator. Therefore, their definitions should be based on the overall content of this specification.

[0032] Hereinafter, embodiments of a device and method for recommending and supporting a contract for a clinical trial contract institution are described in detail with reference to drawings.

[0033] Figure 1 is a configuration diagram of a clinical trial contract institution recommendation and contract support device according to one embodiment.

[0034] According to one embodiment, the clinical trial contract institution recommendation and contract support device (100) may include a matching unit (110), a quotation unit (120), and a contract unit (130).

[0035] According to one embodiment, the matching unit (110) may recommend one or more clinical trial contract organizations based on a request for proposal (RFP) for clinical trial contract organizations received from a user.

[0036] For example, the matching unit (110) may receive a request for proposal from a user and then recommend various contract research organizations (CROs) based on the request. During this process, the matching unit (110) may utilize a predetermined matching algorithm. For example, the matching unit (110) may use data processed into binary and continuous variables through the matching algorithm to calculate a predetermined score for recommending a contract research organization. The items utilized for matching may include specific requirements for clinical trials, the organization's expertise, past performance, and other key indicators.

[0037] For example, the matching unit (110) may initially select one or more clinical trial contract organizations based on a score calculated based on the user's proposal request and the characteristics of the clinical trial contract organization. The matching unit (110) may then derive a list of recommendations through more precise filtering among the selected organizations.

[0038] According to one embodiment, the matching unit (110) may generate a binary variable vector and a continuous variable vector for the requirements according to predetermined rules based on one or more requirements included in the request for proposal. Referring to FIG. 2, the matching unit (110) may analyze the received request for proposal and generate a binary variable vector for one or more requirements whose input data is classified into two values ​​such as 'YES' or 'NO', and may generate the other requirements as continuous variable vectors. For example, the matching unit (110) may analyze the received request for proposal and generate a binary variable vector such as [q1, q2, ..., q7] having a value of 0 or 1, and a continuous variable vector such as [c1, c2, ..., c5] having a real value.

[0039] In one embodiment, the matching unit (110) may generate binary variable vectors and continuous variable vectors for institution data based on one or more previously matched proposal requests for clinical trial contract institutions stored in the database. For example, the database may store previously matched proposal requests for clinical trial contract institutions based on previously performed matching results.

[0040] For example, each clinical trial contract recipient may have one or more RFPs associated with it, such as RFP 1 for clinical trial contract recipient 1, RFP 2 for clinical trial contract recipient 2, and so on. In this case, if multiple RFPs are associated with a single clinical trial recipient, a representative RFP can be created according to certain rules. For example, the most recent RFP can be designated as the representative RFP, or multiple RFPs can be combined to determine the representative RFP.

[0041] For example, the matching unit (110) may generate binary variable vectors and continuous variable vectors for institution data based on one or more requests for proposals matched to each clinical trial contract institution. Referring to FIG. 3, the matching unit (110) may generate binary variable vectors (CRO 1) and continuous variable vectors (CRO 1) for clinical trial contract institution 1.

[0042] According to one embodiment, the matching unit (110) may generate a binary variable matrix by calculating an outer product between a binary variable vector for a requirement and a binary variable vector for an institution data, and may generate a continuous variable matrix by calculating an outer product between a continuous variable vector for a requirement and a continuous variable vector for an institution data.

[0043] According to one example, the matching unit (110) can analyze requirements given in the request for proposal to generate binary variable vectors [q1, q2, ..., q7] having values ​​of 0 or 1, and can generate binary variable vectors such as [i1, i2, ..., i7] from the agency data. In addition, the matching unit (110) can generate continuous variable vectors [c1, c2, ..., c5] expressed as variables that can have continuous values ​​for some items of the request for proposal, and can generate continuous variable vectors such as [ic1, ic2, ..., ic5] from the agency data.

[0044] For example, the matching unit (110) may generate a binary variable matrix of size 7x7 by calculating the outer product between the binary variable vectors [q1, q2, ..., q7] for requirements and the binary variable vectors [i1, i2, ..., i7] for agency data, as shown in FIG. 3. At this time, this matrix may represent matching information on how closely the characteristics of each requirement and agency match. Each element of the matrix is ​​represented by 0 or 1, and shows the matching result for each combination of requirement and agency data.

[0045] For example, the matching unit (110) can generate a 5x5 continuous variable matrix through the outer product of the continuous variable vectors [c1, c2, ..., c5] for requirements and the continuous variable vectors [ic1, ic2, ..., ic5] for agency data. This matrix indicates how similar the values ​​of the continuous variables are and can numerically express the degree of matching. The matching unit (110) can evaluate the suitability between the agency and the request for proposal during the matching process by using the binary variable matrix and the continuous variable matrix thus generated.

[0046] According to one embodiment, the matching unit (110) can calculate an evaluation score for one or more clinical trial contract institutions based on a binary variable matrix and a continuous variable matrix. For example, the matching unit (110) can obtain two variables by adding all elements of each row and column of the binary variable matrix and the continuous variable matrix. Thereafter, the matching unit (110) can weight the two variables. For example, the weights for the weighted sum can be determined based on the sizes of the binary variable matrix and the continuous variable matrix. Through this, the matching unit (110) can calculate a final evaluation score for each institution and recommend a suitable clinical trial contract institution based on the score.

[0047] According to one embodiment, the matching unit (110) may sort one or more clinical trial contract organizations based on evaluation scores for one or more clinical trial contract organizations, and may recommend one or more clinical trial contract organizations based on the ranking of the sorted one or more clinical trial contract organizations and the scope of work of the one or more clinical trial contract organizations.

[0048] For example, the matching unit (110) may sort clinical trial contract organizations based on the evaluation scores for each clinical trial contract organization. Referring to FIG. 4, the matching unit (110) may sort clinical trial contract organizations in descending order of evaluation scores, such as CRO1, CRO 2, etc. Thereafter, the matching unit (110) may determine how closely the scope of work and requirements (Scope) of a predetermined number of clinical trial contract organizations with high evaluation scores match.

[0049] For example, the matching unit (110) can evaluate the scope of work (s1, s2, s3, etc.) of each clinical trial contract organization to determine how well it matches the user's requirements. For example, as shown in FIG. 4, the clinical trial contract organizations can be sorted in the order of CRO 1, 2, 3, 4, and 5, and the scope of work (Scope) of each CRO can be re-examined from the sorted order to determine an organization that satisfies the user's requirements (s1, s3, s5, and s6). For example, the clinical trial contract organizations corresponding to CRO 1 and CRO 4 can be determined as organizations that can satisfy the user's requirements Scope 1, 3, 5, and 6. Based on the sorted order and the scope of work (Scope) of each organization, the matching unit (110) can ultimately recommend CRO 1 and CRO 4 to the user.

[0050] According to one embodiment, the matching unit (110) may display the user's location and one or more recommended clinical trial contract institutions on a map, and determine the display color of one or more recommended clinical trial contract institutions based on the ranking of the clinical trial contract institutions.

[0051] For example, the matching unit (110) can visually display a list of recommended clinical trial contract institutions using a map based on the user's location. During this process, the location of each clinical trial contract institution is visualized using color or intensity, allowing the user to easily determine the ranking and suitability of each institution. When the user selects a clinical trial contract institution, the matching unit (110) can output additional information for each subcategory, allowing the user to view the suitability of the clinical trial contract institution at a glance.

[0052] In one embodiment, the matching unit (110) receives an input from the user to select at least one of one or more recommended clinical trial contract organizations, and may request a quotation from the at least one selected clinical trial contract organization. For example, the matching unit (110) may notify the clinical trial contract organization selected by the user that it has been recommended. Additionally, the matching unit (110) may request a quotation from the terminal of the clinical trial contract organization selected by the user.

[0053] According to one embodiment, the quotation unit (120) can generate quotation information and determine quotation appropriateness for at least one of the recommended one or more clinical trial contract institutions.

[0054] For example, the quotation unit (120) can manage the process of creating, modifying, submitting, and reviewing quotations between clinical trial contract organizations and users. For example, the quotation unit (120) can provide quotation templates and client proposal requests to matched clinical trial contract organizations, allowing the clinical trial contract organizations to create quotations based on these templates. The quotation unit (120) can provide functions for identifying errors and corrections in the quotation, as well as a memo function. Through this, the clinical trial contract organization can easily identify and correct any parts that require correction.

[0055] According to one embodiment, if there is an error in the quotation adequacy determination result, the quotation unit (120) transmits error information to the clinical trial contract organization that transmitted the quotation with the error, and if there is no error in the quotation adequacy determination result, the quotation received from the clinical trial contract organization can be transmitted to the user.

[0056] After completing the quotation, the quotation department (120) can analyze the quotation submitted by the clinical trial contract agency for data format, scope, content consistency, and missing information. If errors are discovered during the analysis, a correction request can be sent to the clinical trial contract agency. Any areas requiring correction can be identified and a note attached. The clinical trial contract agency can correct any errors within the designated upload period and resubmit the quotation. During this process, notification functions and automatic access links can be provided.

[0057] If the analysis results are deemed error-free, the quotation unit (120) delivers the quotation to the user and may provide the user with the ability to view the quotation via a notification function and an automatic access link. The quotation may have a download expiration date and may include security measures, such as a password, to grant viewing privileges.

[0058] In one embodiment, the quotation unit (120) generates quotation information by calculating an expected quotation cost based on previously stored quotations for one or more recommended clinical trial contract organizations, and compares the expected quotation cost with the quotation cost received from one or more recommended clinical trial contract organizations to determine the appropriateness of the quotation. In one example, the quotation unit (120) can visualize a price comparison based on past and present data to determine the appropriateness of the price submitted by the clinical trial contract organization. Through this, the quotation price submitted by the clinical trial contract organization can be visually presented to the user in comparison with the average price of the past and present.

[0059] In one embodiment, the contract department (130) may provide contract error analysis and contract editing functions for clinical trial contract recipients. In one example, the contract department (120) may perform contract error analysis for clinical trial contract recipients using an artificial neural network trained to review at least one of data format, content consistency, and content omissions.

[0060] For example, the contract department (130) automatically creates a contract room and manages all contract-related processes within this space. The contract department (130) can automatically generate and provide a customized contract template based on the user's and the clinical trial contract organization's basic information and quotation.

[0061] For example, the contract section (130) can analyze the contract for omissions, content consistency, and formal errors, allowing users to easily correct them. Furthermore, the contract section (130) can notify all relevant users of the status of each contract drafted, revised, or submitted, and can automatically generate and provide links to facilitate user access to the contract. For example, the contract section (120) can perform contract error analysis using a trained artificial neural network to review important elements of the contract, such as data format, content consistency, and content omissions. This neural network is trained on various contract datasets and can detect errors that may occur in contracts related to clinical trial contract organizations.

[0062] The contract section (130) can visually identify and provide users with information on areas of the contract that require revision, allowing users to discuss and revise each item via notes. Furthermore, the contract section can provide a function that allows users and clinical trial contracting agencies to add or delete specific items within the contract through consultation. The contract section (130) tracks and monitors all records, including contract revisions and downloads, to ensure the integrity and security of the contract. All records are stored to prevent falsification, and any changes to the contract can be transparently managed.

[0063] Figure 5 is a flowchart illustrating a method for recommending and supporting a contract with a clinical trial contract institution according to one embodiment.

[0064] According to one embodiment, the clinical trial contract agency recommendation and contract support device may be a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors.

[0065] According to one embodiment, the clinical trial contract agency recommendation and contract support device may recommend one or more clinical trial contract agencies based on a Request for Proposal (RFP) for clinical trial contract agencies received from a user (510), and may generate quotation information and determine the quotation appropriateness for at least one of the one or more recommended clinical trial contract agencies (520). Furthermore, the clinical trial contract agency recommendation and contract support device may provide contract error analysis and contract editing functions for the clinical trial contract agency.

[0066] Among the embodiments of Fig. 5, embodiments that overlap with the contents described with reference to Figs. 1 to 4 are omitted.

[0067] One aspect of the present invention can be implemented as computer-readable code on a computer-readable recording medium. Codes and code segments implementing the above program can be easily inferred by a computer programmer in the art. The computer-readable recording medium may include any type of recording device that stores data that can be read by a computer system. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, etc. Furthermore, the computer-readable recording medium may be distributed across network-connected computer systems, so that the computer-readable code can be written and executed in a distributed manner.

[0068] The present invention has been described above, focusing on preferred embodiments thereof. Those skilled in the art will appreciate that the present invention can be implemented in modified forms without departing from its essential characteristics. Therefore, the scope of the present invention is not limited to the aforementioned embodiments, but should be interpreted to encompass various embodiments within the scope equivalent to the claims.

[0069] The present invention is applicable to the clinical trial industry.

Claims

1. A matching unit that recommends one or more clinical trial contract organizations based on a Request for Proposal (RFP) for clinical trial contract organizations received from users; A quotation department that generates quotation information and determines quotation appropriateness for at least one of the above-mentioned recommended clinical trial contract institutions; and A clinical trial contract agency recommendation and contract support device, including a contract section that provides contract error analysis and contract editing functions for clinical trial contract agencies.

2. In paragraph 1, The above matching part A clinical trial contract agency recommendation and contract support device that generates binary variable vectors and continuous variable vectors for requirements according to predetermined rules based on one or more requirements included in a request for proposal.

3. In paragraph 2, The above matching part A clinical trial contract agency recommendation and contract support device that generates binary variable vectors and continuous variable vectors for agency data based on one or more matched proposal requests for clinical trial contract agencies stored in a database.

4. In paragraph 3, The above matching part Generate a binary variable matrix by calculating the cross product between the binary variable vector for requirements and the binary variable vector for institutional data. A clinical trial contract support device that generates a continuous variable matrix by cross-producting a continuous variable vector for requirements and a continuous variable vector for institutional data.

5. In paragraph 4, The above matching part A clinical trial contract organization recommendation and contract support device that calculates evaluation scores for one or more clinical trial contract organizations based on a binary variable matrix and a continuous variable matrix.

6. In paragraph 5, The above matching part Sort one or more clinical trial contract organizations based on the evaluation scores for the one or more clinical trial contract organizations, A clinical trial contract agency recommendation and contract support device that recommends one or more clinical trial contract agencies based on the ranking of one or more clinical trial contract agencies sorted above and the scope of work of one or more clinical trial contract agencies.

7. In paragraph 6, The above matching part Displays the user's location and one or more recommended clinical trial contract institutions on a map; A clinical trial contract organization recommendation and contract support device that determines the display color of one or more recommended clinical trial contract organizations based on the ranking of clinical trial contract organizations.

8. In paragraph 7, The above matching part Receives input for selecting at least one of one or more clinical trial contract organizations recommended by the user; A clinical trial contract organization recommendation and contract support device that requests quotations from at least one selected clinical trial contract organization.

9. In paragraph 1, The above quote section Generates quotation information by calculating the expected quotation cost based on the stored quotation for one or more recommended clinical trial contract organizations; A clinical trial contract agency recommendation and contract support device that compares the cost estimates received from one or more recommended clinical trial contract agencies with the above-mentioned expected cost estimates to determine the appropriateness of the estimates.

10. In paragraph 9, The above quote section If there is an error in the quotation adequacy judgment, the error information will be sent to the clinical trial contract organization that sent the quotation with the error. A clinical trial contract agency recommendation and contract support device that transmits a quotation received from a clinical trial contract agency to the user if there is no error in the quotation appropriateness judgment result.

11. In paragraph 1, The above contract A clinical trial contract agency recommendation and contract support device that performs contract error analysis for a clinical trial contract agency using an artificial neural network trained to review at least one of data format, content consistency, and content omission.

12. One or more processors, and A method performed in a computing device having a memory storing one or more programs executed by one or more processors, A matching step for recommending one or more clinical trial contract organizations based on a Request For Proposal (RFP) for clinical trial contract organizations received from a user; A quotation step for generating quotation information and determining quotation appropriateness for at least one of the above-mentioned recommended clinical trial contract institutions; and A method for recommending and supporting a clinical trial contract organization, including a contract stage that provides contract error analysis and contract editing functions for the clinical trial contract organization.

13. In paragraph 12, The above matching step is A method for recommending and supporting a contract for a clinical trial contract provider, wherein a binary variable vector and a continuous variable vector for the requirements are generated according to predetermined rules based on one or more requirements included in a request for proposal.

14. In paragraph 13, The above matching step is A method for recommending and supporting contracts with clinical trial contract recipients, wherein binary variable vectors and continuous variable vectors for institution data are generated based on one or more matched requests for proposals for clinical trial contract recipients stored in a database.

15. In paragraph 14, The above matching step is Generate a binary variable matrix by calculating the cross product between the binary variable vector for requirements and the binary variable vector for institutional data. A method for recommending and supporting contracts for clinical trial contract agencies, which generates a continuous variable matrix by cross-producting a continuous variable vector for requirements and a continuous variable vector for agency data.

16. In paragraph 15, The above matching step is A method for recommending and supporting a contract with a clinical trial contract organization, wherein an evaluation score for one or more clinical trial contract organizations is calculated based on a binary variable matrix and a continuous variable matrix.

17. In paragraph 16, The above matching step is Sort one or more clinical trial contract organizations based on the evaluation scores for the one or more clinical trial contract organizations, A method for recommending and supporting a contract with a clinical trial contract organization, wherein one or more clinical trial contract organizations are recommended based on the ranking of one or more clinical trial contract organizations and the scope of work of one or more clinical trial contract organizations.

18. In paragraph 17, The above matching step is Displays the user's location and one or more recommended clinical trial contract institutions on a map; A method for recommending and supporting a contract with a clinical trial contract organization, wherein the display color of one or more recommended clinical trial contract organizations is determined based on the ranking of the clinical trial contract organizations.

19. In paragraph 18, The above matching step is Receives input for selecting at least one of one or more clinical trial contract organizations recommended by the user; A method of recommending and contracting a clinical trial contract organization, requesting a quotation from at least one selected clinical trial contract organization.

20. In paragraph 12, The above quotation steps are Generates quotation information by calculating the expected quotation cost based on the stored quotation for one or more recommended clinical trial contract organizations; A method for recommending and supporting a contract with a clinical trial contract organization, wherein the appropriateness of the quotation is determined by comparing the quotation cost received from one or more recommended clinical trial contract organizations with the above-mentioned expected quotation cost.

21. In paragraph 20, The above quotation steps are If there is an error in the quotation adequacy judgment, the error information will be sent to the clinical trial contract organization that sent the quotation with the error. A method for recommending and supporting a contract with a clinical trial contract agency, which transmits a quotation received from the clinical trial contract agency to the user if there is no error in the quotation appropriateness judgment result.

22. In paragraph 12, The above contract steps are A method for recommending and supporting a contract with a clinical trial contract acceptor, wherein an error analysis of a contract for a clinical trial contract acceptor is performed using an artificial neural network trained to review at least one of data format, content consistency, and content omission.

Images