Medicine investment and research database construction method and device, computer equipment and computer readable storage medium

Abstract

The invention provides a medicine investment and research database construction method and device, computer equipment and a computer readable storage medium. The method comprises the steps that catalyst related information capable of reflecting the operation trend of a target listed medicine enterprise is acquired; based on the catalyst related information, analyzing association relationships between various events and stock prices of the pharmaceutical enterprises to determine events affecting stock price transactions as target events; determining occurrence time of the target event, wherein the occurrence time comprises future occurrence time; summarizing the occurrence time of the target event, and constructing a medicine administration and research database; the medicine investment and research database can be used for constructing a medicine investment and research information retrieval platform for users to retrieve investment and research information of listed medicine enterprises. By the adoption of the method and device, the requirement for obtaining the medicine delivery and research information in timeliness and comprehensiveness of the delivery and research user can be met, the delivery and research efficiency can be improved, and the labor cost is saved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and particularly to a method, device, computer equipment and computer-readable storage medium for constructing a pharmaceutical research and investment database. Background Art

[0002] In recent years, with the continuous investment of capital, innovative drug investment in the securities market is no longer the stage of a few people. More and more securities investors have started to regularly pay attention to the R & D, production and sales of innovative drug enterprises. Therefore, enabling more securities investors to better participate in the investment of innovative drug enterprises is a common need and important topic for enhancing the overall vitality of the industry. However, there are quite a few differences between the research and investment needs of securities market investors for innovative pharmaceutical enterprises and those in the primary market. For example: ① Compared with the primary market, the secondary market attaches importance to both the drug R & D of listed pharmaceutical enterprises and the progress of product commercialization; ② The secondary market pays attention to both the changes in the enterprise's own operating data and the business dynamics of competitors; ③ The secondary market places more emphasis on the timeliness perception of the trends and changes of the enterprise and the industry.

[0003] In the face of the above market demands, although listed pharmaceutical enterprises will regularly disclose their operating information in accordance with relevant national laws and regulations, there is inevitably a certain lag. In order to solve this information lag, research and investment personnel need to predict the approximate period of the event node in advance and conduct high-frequency retrieval during the predicted period to ensure the timeliness of information. However, simply relying on manual collation has problems such as a large workload and low research efficiency.

[0004] Therefore, developing an information retrieval platform that can improve the efficiency of obtaining pharmaceutical research and investment information, shorten the research and investment path, and assist in accurate investment to meet the unique needs of market innovative drug investors for pharmaceutical research and investment data is an urgent problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device, computer equipment and computer-readable storage medium for constructing a pharmaceutical research and investment database, so as to solve the defect that existing pharmaceutical research and investment users cannot obtain comprehensive and timely pharmaceutical research and investment information, resulting in inaccurate research and investment decisions, and at the same time improve the research and investment efficiency.

[0006] In a first aspect, the present invention provides a method for constructing a pharmaceutical research and investment database, including: Obtaining catalyst-related information that can reflect the business trends of the target listed pharmaceutical enterprise; Based on the catalyst-related information, analyzing the correlation between various events and the stock price of the pharmaceutical enterprise to determine the events that affect the abnormal movement of the stock price as the target events; Determining the occurrence time of the target events, where the occurrence time includes the future occurrence time; Summarize the occurrence times of target events to construct a pharmaceutical research and investment database; the pharmaceutical research and investment database can be used to construct a pharmaceutical research and investment information retrieval platform for users to retrieve research and investment information of listed pharmaceutical companies.

[0007] In some embodiments of the present invention, based on catalyst-related information, analyze the correlation between various events and the stock prices of pharmaceutical companies to determine the events that affect stock price movements as target events, including: based on catalyst-related information, analyze the correlation between various events and the stock prices of pharmaceutical companies to screen out the key events that affect abnormal stock price changes; according to the event attributes of the key events, aggregate each key event to obtain a target event in the form of an event set; wherein, the target event includes at least one of the following: registration progress, pipeline progress, transaction and merger, pharmaceutical conference, medical insurance shortlisting, centralized procurement, clinical result disclosure, and major industry policies.

[0008] In some embodiments of the present invention, the occurrence time further includes the actual occurrence time. When the target event is the registration progress, the steps to determine the occurrence time of the registration progress include: for the first key event in the registration progress, analyze the time field of the registration database data in the catalyst-related information to obtain the actual occurrence time and / or future occurrence time of each first key event; for the second key event in the registration progress, associate the drug approval application number in the catalyst-related information with the sorted drug time axis by window opening and sort by the start time to use the sorted start time sequence as the actual occurrence time of each second key event; wherein, the first key event includes at least one of the following: clinical application, clinical approval, listing application, listing approval, and unapproved listing; the second key event includes the completion of the first round of supplementary review and inclusion in the priority review, and at least one of the following: the completion of the second round of supplementary review, the completion of the third round of supplementary review, the completion of the fourth round of supplementary review, and the completion of the fifth round of supplementary review.

[0009] In some embodiments of the present invention, the occurrence time further includes the actual occurrence time. When the target event is pipeline progress, the steps of determining the occurrence time of the pipeline progress include: for the first enrollment event in the pipeline progress, taking the minimum value of the clinical start date, the first domestic recruitment date, and the first foreign recruitment date in the catalyst-related information as the actual occurrence time of the first enrollment event; for the first enrollment event in the pipeline progress, taking the minimum value of the estimated start date in the catalyst-related information as the future occurrence time of the first enrollment event; for the last enrollment event in the pipeline progress, taking the maximum value of the clinical preliminary completion date in the catalyst-related information as the actual occurrence time of the last enrollment event; for the last enrollment event in the pipeline progress, taking the maximum value of the estimated preliminary completion date in the catalyst-related information as the future occurrence time of the last enrollment event; for the trial end event in the pipeline progress, taking the maximum value of the clinical completion date in the catalyst-related information as the actual occurrence time of the trial end event; for the trial end event in the pipeline progress, taking the maximum value of the estimated completion date in the catalyst-related information as the future occurrence time of the trial end event; for the data readout event in the pipeline progress, determining the article publication date in the catalyst-related information as the actual occurrence time of the data readout event; for the termination event in the pipeline progress, determining the minimum value of the start date of the clinical status change history in the catalyst-related information as the actual occurrence time of the termination event.

[0010] In some embodiments of the present invention, the occurrence time further includes the actual occurrence time. When the target event is a transaction merger and acquisition, the steps of determining the occurrence time of the transaction merger and acquisition include: for the merger and acquisition event in the transaction merger and acquisition, analyzing the time field of the pharmaceutical company merger and acquisition information in the catalyst-related information, and determining the latest announcement date as the actual occurrence time of the merger and acquisition event; for the transaction event in the transaction merger and acquisition, analyzing the time field of the drug transaction information in the catalyst-related information, and determining the release time as the actual occurrence time of the transaction event.

[0011] In some embodiments of the present invention, the method for constructing a pharmaceutical investment research database further includes: if the future occurrence time of the target event is empty, analyzing the historical similar data in the catalyst-related information to obtain the estimated occurrence time as the future occurrence time.

[0012] In some embodiments of the present invention, summarizing the occurrence time of the target event to construct a pharmaceutical investment research database includes: for each target event of each target listed pharmaceutical company, summarizing the occurrence time to generate a first fact table; based on the catalyst-related information, cleaning the target pipeline and associated targets of each target event to improve the first fact table and obtain a second fact table; associating the second fact table with a preset company relationship table to construct a pharmaceutical investment research database.

[0013] Second aspect, the present invention provides a device for constructing a pharmaceutical research and investment database, including: An information acquisition module, configured to acquire catalyst-related information that can reflect the business trends of target listed pharmaceutical companies; An event determination module, configured to analyze the correlation between various events and the stock prices of pharmaceutical companies based on the catalyst-related information, so as to determine the events that affect stock price fluctuations as target events; A time determination module, configured to determine the occurrence time of the target event, where the occurrence time includes future occurrence times; An information aggregation module, configured to aggregate the occurrence times of the target events to construct a pharmaceutical research and investment database; the pharmaceutical research and investment database can be used to construct a pharmaceutical research and investment information retrieval platform for users to retrieve research and investment information of listed pharmaceutical companies.

[0014] Third aspect, the present invention further provides a computer device, including: One or more processors; A memory; and one or more application programs, where one or more of the application programs are stored in the memory and configured to be executed by the processor to implement the above-mentioned method for constructing a pharmaceutical research and investment database.

[0015] Fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is loaded by the processor to execute the steps in the method for constructing a pharmaceutical research and investment database.

[0016] Fifth aspect, an embodiment of the present invention provides a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in the first aspect above.

[0017] In the above-mentioned method, device, computer device and computer-readable storage medium for constructing a pharmaceutical research and investment database, the server acquires catalyst-related information that can reflect the business trends of target listed pharmaceutical companies, and based on the catalyst-related information, analyzes the correlation between various events and the stock prices of pharmaceutical companies to determine the target events that affect stock price fluctuations, and then determines the occurrence times corresponding to the target events, including future occurrence times, and finally aggregates the occurrence times of each target event, so as to construct a pharmaceutical research and investment database that can build a pharmaceutical research and investment information retrieval platform. In this way, the pharmaceutical research and investment information retrieval platform built based on the pharmaceutical research and investment database can be used by research and investment users to retrieve research and investment data of listed pharmaceutical companies, which not only solves the research and investment users' requirements for timely and comprehensive acquisition of pharmaceutical research and investment information, but also improves the research and investment efficiency and saves labor costs. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the scenario of the method for constructing a medical investment research database in the embodiments of the present invention; Figure 2 It is a schematic flowchart of the method for constructing a medical investment research database in the embodiments of the present invention; Figure 3 It is a schematic structural diagram of the device for constructing a medical investment research database in the embodiments of the present invention; Figure 4 It is a schematic structural diagram of a computer device in the embodiments of the present invention. Specific embodiments

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0021] It should be noted that in the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically defined.

[0022] First, the method for constructing a medical investment research database provided by the embodiments of the present invention can be applied to, for example Figure 1In the pharmaceutical research and investment database construction system shown. Among them, the pharmaceutical research and investment database construction system includes a client 102 and a server 104. The client 102 can be a device that includes both receiving and transmitting hardware, that is, a device with receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such devices can include: cellular or other communication devices, which are cellular or other communication devices with a single-line display or a multi-line display. The client 102 can specifically be a desktop terminal or a mobile terminal, and the client 102 can specifically also be one of a mobile phone, a tablet computer, or a laptop computer. The server 104 can be an independent server or a server network or server cluster composed of servers, which includes but is not limited to a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing. In addition, a communication connection is established between the client 102 and the server 104 through a network, and the network can specifically be any one of a wide area network, a local area network, or a metropolitan area network.

[0023] Secondly, those skilled in the art can understand that Figure 1 the application environment shown in is only an application scenario suitable for the solution of this application, and does not constitute a limitation on the application scenario of the solution of this application. Other application environments can also include more or fewer devices than Figure 1 shown in. For example, Figure 1 only 1 server is shown in. It can be understood that the pharmaceutical research and investment database construction system can also include one or more other devices, which are not specifically limited here. In addition, the pharmaceutical research and investment database construction system can also include a memory for storing data, such as storing pharmaceutical research and investment data.

[0024] First of all, before elaborating in detail on the technical solutions provided by the embodiments of this application, it is necessary for those skilled in the art to know that in the industry, information events that can reflect the business trends of listed pharmaceutical companies are called "catalysts". Generally speaking, in order to provide information related to the catalysts of listed pharmaceutical companies, listed pharmaceutical companies will regularly disclose their business information in accordance with relevant national laws and administrative regulations, and usually conduct such regular disclosures at quarterly intervals. However, this disclosure method has a certain lag. Therefore, in order to overcome this problem of information lag, before making research and investment decisions, research and investment personnel often need to predict the approximate time period of event nodes in advance, and then conduct high-frequency retrieval within the predicted time period and adjust strategies in real time to ensure the timeliness of information. The following is an example: 1. The China Securities Regulatory Commission stipulates that listed companies need to regularly disclose the approval and listing progress of their major new products. Listed enterprises generally disclose the information nodes of events such as product approval truthfully, but generally do not disclose information on various links such as acceptance and supplementary submission from the time of submitting a drug listing application to approval and listing. At this time, if investment researchers want to know the review information of each link of the drug, they need to manually retrieve the CDE (Center for Drug Evaluation of the National Medical Products Administration) for manual collation. The work is repetitive and cumbersome, and there is also a certain lag in the collation results. 2. The China Securities Regulatory Commission stipulates that listed companies need to regularly disclose the R & D progress of their major in - research products. Listed enterprises generally disclose the information nodes of events such as application and entry into clinical trials truthfully, while the clinical data results in drug R & D are generally announced in professional journals and academic conferences. Since this professional information generally does not fall within the scope of mandatory information disclosure, if investment researchers want to know the clinical data of drugs, they can only manually retrieve relevant professional journals and academic conferences, with a large workload and lagged information.

[0025] In summary, to address the above - mentioned requirements for the comprehensiveness and timeliness of catalyst information for listed pharmaceutical companies, the current market practice is usually to arrange dedicated investment research personnel to predict event nodes according to the general life cycle of drug R & D, and then manually search the entire network day - by - day, week - by - week, and month - by - month for listed company announcements, CDE (Center for Drug Evaluation of the National Medical Products Administration), professional academic conferences (such as the European Society for Medical Oncology Annual Meeting), professional academic journals, etc. However, there are problems such as a large workload and low research efficiency. In addition, the officially disclosed data is only a collection of events that have occurred, and the expected occurrence time of each event is not clearly announced. At this time, to ensure no information is missed, investment researchers need to frequently retrieve and count for a long time, with a heavy workload. Therefore, for this application scenario, there is an urgent need for a one - stop database tool to integrate, consolidate, and sort out the above - mentioned catalyst information for investors to make efficient decisions.

[0026] Based on the above - cited content, the embodiment of this application proposes a method for constructing a pharmaceutical investment research database. This method aims to overcome the problem of lagged disclosure of existing pharmaceutical investment research data by optimizing the data integration process and data processing details, and to achieve connectivity.

[0027] Specifically, this method will be configured in a computer device, enabling the constructed pharmaceutical investment research database to be seamlessly integrated into an efficient pharmaceutical investment research data retrieval platform and automatically run by the computer device. This platform will use advanced algorithms and data processing technologies to monitor and analyze the information regularly disclosed by listed pharmaceutical companies in real - time, so as to help investment researchers learn in advance the actual occurrence time / possible occurrence time of key event nodes, ensure the timeliness and accuracy of information, and adjust pharmaceutical investment research decisions in advance.

[0028] In addition, the platform will also provide a variety of data visualization tools and analysis models to further assist investment research personnel in conducting in-depth data mining and trend analysis, providing strong support for investment decisions.

[0029] For specific reference Figure 2 , which is a schematic flowchart of a method for constructing a pharmaceutical investment research database provided by an embodiment of the present invention. In this embodiment, the method is mainly illustrated by applying it to the server 104 in the above Figure 1 . The method includes steps S201 to S204, which are specifically as follows: S201, Obtain catalyst-related information that can reflect the business trends of target listed pharmaceutical companies.

[0030] Among them, the catalyst-related information includes but is not limited to the production, research, and sales information of target listed pharmaceutical companies, enterprise association information, and stock price movement information. The production, research, and sales information includes but is not limited to drug clinical trial information, drug review and approval information, medical conference information, etc. The enterprise association information at least includes enterprise industrial and commercial information. The stock price movement information includes but is not limited to enterprise announcement information, news and information, securities trading information, etc.

[0031] In specific implementation, the server 104 can obtain drug clinical trial information through websites such as the Center for Drug Evaluation (CDE), the official website of the US Food and Drug Administration (FDA), drug declaration and registration databases, and the official websites of pharmaceutical companies; obtain drug review and approval information through the official websites of national drug regulatory agencies (such as the NMPA official website in China and the European Medicines Agency (EMA) official website in the EU), news and information platforms, etc.; obtain medical conference information through the official websites of conferences (such as the annual meeting of the well-known American Society of Clinical Oncology (ASCO)), medical industry media (such as "Medical Economics News"), professional society and association platforms (which can include medical societies and associations in various countries and regions, such as the Chinese Pharmaceutical Association), etc.; obtain enterprise industrial and commercial information through the National Enterprise Credit Information Publicity System and commercial query platforms; obtain enterprise announcement information through the official websites of enterprises; obtain securities trading information through the websites of stock exchanges and financial information terminals.

[0032] S202, Based on the catalyst-related information, analyze the correlation between various events and the stock prices of pharmaceutical companies to determine the events that affect stock price movements as target events.

[0033] Among them, the target events include at least one of the following: registration progress, pipeline progress, transaction and merger, medical conference, medical insurance inclusion, centralized procurement, clinical result disclosure, and major industry policies.

[0034] Among them, the registration progress includes at least one of the following: applying for clinical trials, clinical approval, applying for marketing, marketing approval, marketing disapproval, completion of the first round of supplementary review, completion of the second round of supplementary review, completion of the third round of supplementary review, completion of the fourth round of supplementary review, completion of the fifth round of supplementary review, inclusion in priority review.

[0035] Among them, the pipeline progress includes at least one of the following: the first patient enrollment, the last patient enrollment, the end of the trial, data readout, termination. For example, the first patient enrollment in Phase II, the last patient enrollment in Phase II, the interim data readout in Phase II, the final data readout in Phase III, etc.

[0036] Among them, the transactions and mergers & acquisitions include at least one of the following: transaction concluded, transaction terminated, enterprise acquired, acquisition terminated.

[0037] Among them, the medical conferences include at least one of the following: AACR (American Association for Cancer Research Annual Meeting), AAN (American Academy of Neurology Annual Meeting), AASLD (American Association for the Study of Liver Diseases Annual Meeting), ACR (American College of Rheumatology Annual Meeting), ADA (American Diabetes Association Scientific Sessions), ASCO (American Society of Clinical Oncology Annual Meeting), ASH (American Society of Hematology Annual Meeting), ASN (American Society of Nephrology Annual Meeting), etc.

[0038] In specific implementation, the server 104 can analyze the correlation between various events and the stock price of pharmaceutical companies through statistical analysis algorithms (such as correlation analysis, regression analysis, etc.) and / or event study methods, and then determine the major events affecting the abnormal stock price movement as the target events.

[0039] Further, if multiple algorithms are used for analysis, weight values can be preset among the multiple algorithms, and finally the target event can be determined based on the weighted result, improving the accuracy of event determination.

[0040] For example, when using the correlation method for analysis, the server 104 can calculate the correlation coefficients between each variable in the production, research, sales information and enterprise association information and the stock price movement. For example, the Pearson correlation coefficient is used to analyze whether there is a linear relationship between the events at each stage of a pharmaceutical company's product and the stock price increase, and then the events affecting the stock price movement are locked as the target events based on the linear relationship. When using regression analysis, the server 104 can construct a regression model, with the stock price movement as the dependent variable and various progress information in the catalyst-related information as the independent variables, and determine the influence degree of each event on the stock price movement through regression analysis, so as to screen out the target events.

[0041] Another example is that when using the event study method, the server 104 can first determine the event window, then calculate the abnormal return, and finally analyze the event impact to determine the target event. Specifically, the server 104 can set an event window (such as a certain number of days before and after the event occurrence, that is, [-5, 5] days) around a specific event (such as new drug approval, merger and acquisition announcement, etc.), and then calculate the difference between the actual return and the expected return of the pharmaceutical company within the event window, that is, the abnormal return. The expected return can be estimated through a market model (such as the Capital Asset Pricing Model CAPM). If the abnormal return is significantly non-zero, it indicates that the event has an impact on the stock price. At this time, by comparing the magnitudes and directions of the abnormal returns of different types of events, it can be determined which events have a significant impact on the stock price movement. For example, the abnormal return of new drug approval is positive and large, while the abnormal return of management change is negative and small, and the approval event can be used as the target event.

[0042] In one embodiment, step S202 includes: based on the catalyst-related information, analyzing the correlation between various events and the stock price of the pharmaceutical company to screen out the key events that affect the abnormal stock price movement; aggregating each key event according to the event attributes of the key events to obtain the target event in the form of an event set; where the target event includes at least one of the following: registration progress, pipeline progress, transaction and merger, medical conference, medical insurance inclusion, centralized procurement, clinical result disclosure, major industry policies.

[0043] In specific implementation, after the server 104 uses statistical analysis algorithms and / or event study methods to analyze the correlation between various events and the stock price of the pharmaceutical company and then screens out the key events, it is also necessary to aggregate each key event according to the event attributes of the key events to obtain the target event in the form of an event set. Here, the event attributes can be divided and preset according to the links such as product R & D, registration, sales, and guideline inclusion of listed pharmaceutical companies.

[0044] S203. Determine the occurrence time of the target event, where the occurrence time includes future occurrence times.

[0045] In specific implementation, to help users better query and anticipate favorable events or major risks in advance, we have sorted out some industry catalyst events that may occur in the future and their occurrence times. Future occurrence times are very conducive to investment research users making effective investment research decisions, because by presenting the future occurrence times and corresponding events for users to query, users can anticipate favorable events or major risks in advance.

[0046] For example, the future occurrence time of the end of certain pharmaceutical pipeline trials, or the future occurrence time of clinical approval.

[0047] In one embodiment, the occurrence time also includes the actual occurrence time. When the target event is the registration progress, the steps to determine the occurrence time of the registration progress include: for the first key event in the registration progress, analyze the time field of the registration database data in the catalyst-related information to obtain the actual occurrence time and / or future occurrence time of each first key event; for the second key event in the registration progress, associate the drug approval application number in the catalyst-related information with the sorted drug time axis by window opening and sort by the start time, so as to use the sorted start time sequence as the actual occurrence time of each second key event; where the first key event includes at least one of the following: applying for clinical trial, clinical approval, applying for listing, listing approval, and unapproved listing; the second key event includes the completion of the first round of supplementary review and inclusion in the priority review, and at least one of the following: the completion of the second round of supplementary review, the completion of the third round of supplementary review, the completion of the fourth round of supplementary review, and the completion of the fifth round of supplementary review.

[0048] Among them, the registration database data may refer to the data stored in the drug declaration and registration database. Here, since the drug declaration and registration database stores the data generated by a drug from project establishment to final listing with at least one application to the drug administration (such as the initial application for project establishment, subsequent application for clinical trial, consistency testing, etc.) (such as application stage code, drug registration transaction time, review opinion change time, etc.), therefore, whether it is applying for clinical trial, clinical approval, applying for listing, listing approval or unapproved listing, the occurrence times of the sub-events in each stage can be extracted from the database. In addition, for the convenience of understanding the "acceptance number" in the following text, it should also be noted that each application of the drug to the drug administration mentioned above will actually generate a piece of data stored in the drug declaration and registration database, and use the acceptance number (application_num) as the unique identifier. One acceptance number represents one application.

[0049] Among them, the drug approval application number can be a unique specific number assigned to each drug approval application by the drug regulatory department for managing and tracking the drug approval process.

[0050] Among them, the drug timeline can be a visualization tool or concept that shows, in chronological order, all the important stages in the entire process of a drug from research and development to after-market; the said important stages include the research and development stage, clinical trial stage, approval stage, and after-market stage of the drug. The drug timeline records the status detail information of each stage after the acceptance number is registered and accepted by the drug administration, including: for each piece of data, the corresponding acceptance number (application_num) in the CDE review, an event (event), the content of the event (content), the start time (start_time) of the event, the end time (end_time), etc.

[0051] In specific implementation, after the server 104 analyzes and determines the target event, it can determine the actual occurrence time and / or future occurrence time corresponding to the target event through natural language processing algorithms, such as semantic analysis, entity recognition, rule matching, etc.

[0052] Specifically, regarding the registration progress and its sub-events, when the server 104 performs field recognition on the catalyst-related information, generally only the actual occurrence time of the event can be obtained. As for the future occurrence time of the event, since the information source usually does not publicize it, it needs to be predicted through the solution provided in the subsequent embodiments of this application, but the situation of direct publication is not excluded.

[0053] Furthermore, for the value-taking and occurrence time field content of data such as applying for clinical trials, clinical approval, applying for marketing, marketing approval, and non-marketing approval, etc., they can all be directly read from the drug application and registration database. For data such as the completion of the first to fifth rounds of supplementary review and inclusion in priority review, etc., they can also be directly read from the drug application and registration database, but all of them need to be associated with the drug timeline to determine the time information. The reason is that: different from the first key events such as applying for clinical trials and marketing approval, the time nodes of the second key events such as the completion of the first round of supplementary review and the completion of the second round of supplementary review are details in the review process and exist separately in the drug timeline table. Therefore, the drug timeline still needs to be associated to extract the occurrence time of the second key event.

[0054] Furthermore, since there are multiple drug approval application numbers in the drug time axis, window sorting needs to be performed when taking time values (so-called window sorting means grouping by drug approval application number and sorting the start time in the drug time axis). Inclusion in priority review is associated with the drug time axis after drug approval application number and window sorting, and the latest one is taken according to the start time, that is, the first one in each window. The earliest time is the first round, followed by the second round, the third round, and so on as the actual occurrence time of the completion of review for each round of supplementary review.

[0055] Similarly, the completion of review for the first to fifth rounds of supplementary review is also associated with the drug time axis after drug approval application number and window sorting through the drug approval application number, and then the earliest start time is the completion of review for the first round of supplementary review, and the start time is taken in sequence as the actual occurrence time.

[0056] In one embodiment, the occurrence time also includes the actual occurrence time. When the target event is pipeline progress, the steps to determine the occurrence time of pipeline progress include: for the first enrollment event in the pipeline progress, taking the minimum value of the clinical start date, the first domestic recruitment date, and the first foreign recruitment date in the catalyst-related information as the actual occurrence time of the first enrollment event; for the first enrollment event in the pipeline progress, taking the minimum value of the estimated start date in the catalyst-related information as the future occurrence time of the first enrollment event; for the last enrollment event in the pipeline progress, taking the maximum value of the clinical preliminary completion date in the catalyst-related information as the actual occurrence time of the last enrollment event; for the last enrollment event in the pipeline progress, taking the maximum value of the estimated preliminary completion date in the catalyst-related information as the future occurrence time of the last enrollment event; for the trial end event in the pipeline progress, taking the maximum value of the clinical completion date in the catalyst-related information as the actual occurrence time of the trial end event; for the trial end event in the pipeline progress, taking the maximum value of the estimated completion date in the catalyst-related information as the future occurrence time of the trial end event; for the data readout event in the pipeline progress, determining the article publication date in the catalyst-related information as the actual occurrence time of the data readout event; for the termination event in the pipeline progress, determining the minimum value of the start date of the clinical status change history in the catalyst-related information as the actual occurrence time of the termination event.

[0057] In a specific implementation, before the server 104 obtains the occurrence times of various events during the pipeline progress, it is necessary to perform data cleaning and association on the clinical research project table, including the splitting and aggregation of the "NCT number" (the registration number of the US Clinical Trials Registry), and the cleaning of fields such as "R & D stage", "official title", "clinical start date", "clinical completion date", "first domestic enrollment date", and "first foreign enrollment date". Those skilled in the art should understand that the fields to be cleaned are not exhausted here, but at least include the fields required for determining the time below.

[0058] Further, after the server 104 obtains the above fields, for the occurrence time of the first enrollment event, the server 104 can take the minimum value of the following three fields: "clinical start date", "first domestic enrollment date", and "first foreign enrollment date" as the actual occurrence time of the first enrollment event. The actual command that can be executed is: "min(LEAST(actual_start_date, first_enrollment_date_home, first_enrollment_date_abroad)) AS event_date". For the occurrence time of the last enrollment event (also known as the last medication event), the server 104 can take the maximum value of the "clinical preliminary completion date" as the actual occurrence time of the last enrollment event. The actual command that can be executed is: "max(actual_primary_completion_date) AS event_date". For the occurrence time of the trial end event, the server 104 can take the maximum value of the "clinical completion date" as the actual occurrence time of the trial end event. The actual command that can be executed is: "max(actual_completion_date) AS event_date".

[0059] Furthermore, for the future occurrence time of the first enrollment event, server 104 can take the minimum value of the field: "anticipated start date", and the actual command executed can be: "min(anticipated_start_date) AS predicted_date". For the future occurrence time of the last enrollment event, server 104 can take the maximum value of "anticipated preliminary completion date", and the actual command executed can be: "max(anticipated_primary_completion_date) AS predicted_date". For the future occurrence time of the trial end event, server 104 can take the maximum value of "anticipated completion date", and the actual command executed can be: "max(anticipated_completion_date) AS predicted_date".

[0060] It should be noted that for the same event, the coexistence of its "occurrence time" and "future occurrence time" does not affect each other, because they belong to two different fields and can take their respective values. In actual application scenarios, if a user retrieves a piece of data with both an "occurrence time" and a "future occurrence time", and the corresponding values of the two times are different, the validity of this piece of data cannot be denied. The reason may be that when cleaning the data source in the early stage, only the "future occurrence time" with a non-null value can be extracted, and the "occurrence time" cannot be extracted. However, during subsequent data iteration, the "occurrence time" can be extracted again and then supplemented. In this way, there may be a situation where the values are different, but the two do not affect each other.

[0061] Furthermore, for data readout events, the server 104 can obtain the "article publication date" in the "clinical trial result structured" and "drug clinical result v2" data as the actual occurrence time of the data readout event. The actual command executed can be: "paper_release_time AS event_date". Generally speaking, a clinical trial mainly focuses on the safety and effectiveness of a certain drug under a specific indication through a specific therapy. During the trial treatment process, there may be various combinations of medications and therapies, and there may also be trials on biomarkers. The resulting trial results such as: whether it passes, evaluation (positive, non-inferior, poor, terminated, etc.), relative risk, effectiveness of the optimal dose, whether it is a key result, etc. These information may ultimately be released at a certain release time through media such as conferences and papers, and then be collected and stored separately based on different attributes in "clinical trial result structured" and "clinical result". In this application, since the clinical trial result structured stores the data of the visual results of clinical trials, which is only part of the clinical result data, and the other part is stored in the clinical result, which stores the data of a drug pipeline's clinical trial from clinical application filing to the final passing of the clinical trial, union analysis can be performed based on the data integrity.

[0062] Finally, for termination events, the server 104 can obtain the historical data of clinical status changes, and associate it with the data obtained from the first-step field cleaning through the NCT number, and then take the minimum value of the "start date" as the actual occurrence time of the termination event. The actual command executed can be: min(start_date) AS event_date.

[0063] In one embodiment, the occurrence time also includes the actual occurrence time. When the target event is a transaction merger and acquisition, the steps to determine the occurrence time of the transaction merger and acquisition include: for the merger event in the transaction merger and acquisition, perform a time field analysis on the pharmaceutical company merger and acquisition information in the catalyst-related information, and determine the latest announcement date as the actual occurrence time of the merger event; for the transaction event in the transaction merger and acquisition, perform a time field analysis on the drug transaction information in the catalyst-related information, and determine the release time as the actual occurrence time of the transaction event.

[0064] In a specific implementation, the server 104 can use the Seatunnel tool to pull the data tables required for transaction mergers and acquisitions from Elasticsearch (ES), and then perform subsequent logical processing based on these. For transaction mergers and acquisitions, new merger and acquisition events can be obtained through the index "Company Merger and Acquisition (np_company_ma)", and new transaction events can be obtained through the index "Project Transaction (drug_deal)". The data under the Company Merger and Acquisition (np_company_ma) index can include: acquirer identifier (acquiror_id), acquiree identifiers (acquiree_ids), the latest merger and acquisition phase of the company (company_ma_phase_latest), and the latest announcement date (announced_date_latest). The data under the Project Transaction (drug_deal) index can include: transferor, transferee, deal status (deal_status), deal ID (deal_id), and published time (published_time).

[0065] Thus, the server 104 can use the latest announcement date (announced_date_latest) as the actual occurrence time of the merger and acquisition event, and the published time (published_time) as the actual occurrence time of the transaction event.

[0066] In one embodiment, the method for constructing a pharmaceutical research and investment database further includes: if the future occurrence time of the target event is empty, analyze the historical similar data in the catalyst-related information to obtain the estimated occurrence time as the future occurrence time.

[0067] In a specific implementation, the embodiments of the present application propose that when the future occurrence time of the target event is empty, that is, when the future occurrence time of the corresponding event cannot be obtained, it can be estimated so that the research and investment users can make forward-looking investment strategy deployments based on the future occurrence time of the target event.

[0068] For example, the stock price / market value of a certain pharmaceutical company has shown significant fluctuations due to changes in the progress of ActRIIA antibody LAE102, and on February 29, 2024, it announced that LAE102 for the treatment of obesity pipeline has been accepted clinically. However, before this, the database platform built by the embodiments of the present application monitored the review progress of the pharmaceutical company's pipeline in real time and pushed this review information one week in advance. If the research and investment users mastered this information through the platform built by the present application and bought on the first working day after the festival, compared with buying after the announcement date, they could directly lock in an investment return of 66%.

[0069] Furthermore, for the registration progress and its sub-events, the server 104 can screen out all historical data of the same type as the event from the catalyst-related information database. These historical data should include various characteristic information of the event and the corresponding occurrence time. Then, perform data cleaning operations on the collected historical data of the same type, including but not limited to removing duplicate data, handling missing values (missing values of other necessary information except for the occurrence time of the target event to be predicted being empty), and detecting and handling outliers. Furthermore, analyze the common characteristics that may affect the occurrence time between the target event and historical events of the same type, and perform feature encoding on the historical data of the same type and the target event according to the selected characteristics. Finally, according to the data characteristics and prediction requirements, select a suitable prediction model, and use the historical data of the same type to train the selected model to obtain a trained prediction model. After that, input the feature data of the registration progress and its sub-events into the trained prediction model, and the model will output the predicted occurrence time of the corresponding event as the future occurrence time.

[0070] Of course, if the future occurrence time of other events except for the registration progress and its sub-events is also empty, the server 104 can analyze the historical data in the above manner when obtaining historical data of the same type as the event.

[0071] S204, summarize the occurrence time of the target events to construct a pharmaceutical research and investment database; the pharmaceutical research and investment database can be used to construct a pharmaceutical research and investment information retrieval platform for users to retrieve the research and investment information of listed pharmaceutical companies.

[0072] Among them, the purpose of this step is to summarize the occurrence time of each target event to construct a pharmaceutical research and investment database that can be used by users to retrieve the research and investment data of listed pharmaceutical companies, which can also be called a catalyst library.

[0073] In specific implementation, in the financial market, industry catalyst events often have a crucial impact on stock price fluctuations. These events are like key "fuses" that can trigger changes in market sentiment and then drive the rise or fall of stock prices. Therefore, by deeply studying and analyzing the internal relationship between industry catalyst events and stock price fluctuations in this embodiment of the application, valuable reference information can be provided for investors to help them better grasp the market dynamics and make wise investment decisions.

[0074] Specifically, the server 104 can store the data associated with various target events, including the actual occurrence time and / or the future occurrence time, in a tabular and summarized manner, and then associate the tables to build a pharmaceutical research and investment database. With the support of the pharmaceutical research and investment database, a user-friendly retrieval interface is designed to build a pharmaceutical research and investment information retrieval platform, which can facilitate the retrieval of research and investment data of listed pharmaceutical companies by research and investment users. In this way, the pharmaceutical research and investment information retrieval platform can record the real-time situation of each link from industry events to company operations and give early warnings, which can not only enable customers to gain insights into trends, identify opportunities and risks, and maintain a leading position in terms of cognition, but also improve the decision-making efficiency of pharmaceutical investors.

[0075] In one embodiment, step S204 includes: for each target event of each target listed pharmaceutical company, summarizing the occurrence time and / or the estimated occurrence time to generate a first fact table; based on the catalyst-related information, cleaning the target pipelines and associated targets of each target event to improve the first fact table and obtain a second fact table; associating the second fact table with a preset company relationship table to build a pharmaceutical research and investment database.

[0076] Among them, the target pipeline can refer to drugs that a pharmaceutical company is researching, developing, or planning. The associated target can refer to specific biomolecules that a drug acts on in the body, and these biomolecules are usually proteins (such as enzymes, receptors, etc.), nucleic acids (such as DNA, RNA), or other biological macromolecules. Drugs regulate physiological or pathological processes in the body by binding to or interacting with these targets, so as to achieve the purpose of treating diseases. Here, both the target pipeline and the associated target can be obtained by entity recognition of the catalyst-related information.

[0077] In specific implementation, the granularity of the first fact table can be each target event of each target listed pharmaceutical company. The second fact table can be obtained by supplementing the first fact table with two types of information, namely the target pipeline and the associated target. The third fact table can be a catalyst listed company and subsidiary relationship table. Subsequently, the second fact table is associated to form a business table and written into the doris database for subsequent retrieval and use.

[0078] In the method for building the pharmaceutical research and investment database in the above embodiment, the server obtains the catalyst-related information that can reflect the business trends of target listed pharmaceutical companies, and based on the catalyst-related information, analyzes the correlation between various events and the stock prices of pharmaceutical companies to determine the target events that affect stock price fluctuations, and then determines the occurrence time corresponding to the target events, including the future occurrence time. Finally, by summarizing the occurrence times of all target events, a pharmaceutical research and investment database that can build a pharmaceutical research and investment information retrieval platform can be built. In this way, this application shows future events and corresponding times for users to query by obtaining and analyzing the relationship between industry catalyst events and stock price fluctuations, enabling users to anticipate favorable or major risks in advance.

[0079] It should be understood that although Figure 2 the steps in the flowchart are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 at least a part of the steps in

[0080] can include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps. Figure 3 As shown in the pharmaceutical investment research database construction device 300 includes: An information acquisition module 310, configured to acquire catalyst-related information that can reflect the business trends of target listed pharmaceutical companies; An event determination module 320, configured to analyze the correlation between various events and the stock price of a pharmaceutical company based on the catalyst-related information, so as to determine the events that affect the abnormal change of the stock price as target events; A time determination module 330, configured to determine the occurrence time of the target event, where the occurrence time includes the future occurrence time;

[0081] An information aggregation module 340, configured to aggregate the occurrence times of the target events to construct a pharmaceutical investment research database; the pharmaceutical investment research database can be used to construct a pharmaceutical investment research information retrieval platform for users to retrieve investment research information of listed pharmaceutical companies.

[0082] In one embodiment, the occurrence time further includes the actual occurrence time. When the target event is the registration progress, the time determination module 330 is further configured to analyze the time field of the registration library data in the catalyst-related information for the first key event in the registration progress to obtain the actual occurrence time and / or the future occurrence time of each first key event; for the second key event in the registration progress, associate the drug approval application number in the catalyst-related information with the drug time axis after window sorting and sort by the start time, so as to use the sorted start time sequence as the actual occurrence time of each second key event; wherein, the first key event includes at least one of the following: applying for clinical trial, clinical approval, applying for listing, listing approval, and unapproved listing; the second key event includes the completion of the first round of supplementary review and inclusion in the priority review, and at least one of the following: the completion of the second round of supplementary review, the completion of the third round of supplementary review, the completion of the fourth round of supplementary review, and the completion of the fifth round of supplementary review.

[0083] In one embodiment, the occurrence time further includes the actual occurrence time. When the target event is the pipeline progress, the time determination module 330 is further configured to take the minimum value of the clinical start date, the first domestic recruitment date, and the first foreign recruitment date in the catalyst-related information as the actual occurrence time of the first patient enrollment event in the pipeline progress; take the minimum value of the estimated start date in the catalyst-related information as the future occurrence time of the first patient enrollment event in the pipeline progress; take the maximum value of the clinical preliminary completion date in the catalyst-related information as the actual occurrence time of the last patient enrollment event in the pipeline progress; take the maximum value of the estimated preliminary completion date in the catalyst-related information as the future occurrence time of the last patient enrollment event in the pipeline progress; take the maximum value of the clinical completion date in the catalyst-related information as the actual occurrence time of the trial end event in the pipeline progress; take the maximum value of the estimated completion date in the catalyst-related information as the future occurrence time of the trial end event in the pipeline progress; determine the article publication date in the catalyst-related information as the actual occurrence time of the data readout event in the pipeline progress; determine the minimum value of the start date of the clinical status change history in the catalyst-related information as the actual occurrence time of the termination event in the pipeline progress.

[0084] In one embodiment, the occurrence time further includes the actual occurrence time. When the target event is a transaction merger and acquisition, the time determination module 330 is further configured to perform a time field analysis on the pharmaceutical company merger and acquisition information in the catalyst-related information for the merger and acquisition event in the transaction merger and acquisition, and determine the latest announcement date as the actual occurrence time of the merger and acquisition event; for the transaction event in the transaction merger and acquisition, perform a time field analysis on the drug transaction information in the catalyst-related information, and determine the release time as the actual occurrence time of the transaction event.

[0085] In one embodiment, the method for constructing a pharmaceutical investment research database further includes a time prediction module, configured to analyze historical similar data in the catalyst-related information to obtain an estimated occurrence time as the future occurrence time in response to the future occurrence time of the target event being empty.

[0086] In one embodiment, the information aggregation module 340 is further configured to aggregate the occurrence time and / or the estimated occurrence time for each target event of each target listed pharmaceutical company to generate a first fact table; based on the catalyst-related information, clean the target pipeline and associated targets of each target event to improve the first fact table and obtain a second fact table; associate the second fact table with a pre-set company relationship table to construct a pharmaceutical investment research database.

[0087] In the above embodiment, the server obtains catalyst-related information that can reflect the business trends of target listed pharmaceutical companies, and based on the catalyst-related information, analyzes the correlation between various events and the stock prices of pharmaceutical companies to determine the target events that affect stock price fluctuations, and then determines the occurrence time corresponding to the target events, including the future occurrence time. Finally, by aggregating the occurrence times of each target event, a pharmaceutical investment research database that can build a pharmaceutical investment research information retrieval platform can be constructed. In this way, the pharmaceutical investment research information retrieval platform built based on the pharmaceutical investment research database can be used by investment research users to retrieve investment research data of listed pharmaceutical companies, which not only solves the investment research users' needs for timely and comprehensive acquisition of pharmaceutical investment research information, but also improves the investment research efficiency and saves labor costs.

[0088] It should be noted that the specific limitations on the device for constructing a pharmaceutical investment research database can refer to the limitations on the method for constructing a pharmaceutical investment research database in the above text, which will not be elaborated here. Each module in the above device for constructing a pharmaceutical investment research database can be implemented in whole or in part by software, hardware, and their combinations. The above modules can be embedded in the processor of the electronic device in hardware form or be independent of it, or can be stored in the memory of the electronic device in software form for the processor to call and execute the operations corresponding to the above modules.

[0089] In some embodiments of the present application, the device 300 for constructing a pharmaceutical investment research database can be implemented in the form of a computer program, and the computer program can be run on, for example Figure 4running on the computer device shown. In the memory of the computer device, various program modules constituting the medical research database construction device 300 can be stored. For example, Figure 3 the information acquisition module 310, event determination module 320, time determination module 330, and information aggregation module 340 shown; the computer program composed of each program module enables the processor to execute the steps in the medical research database construction method of each embodiment of the present application described in this specification. For example, Figure 4 the computer device shown can execute step S201 through the information acquisition module 310 in the medical research database construction device 300 as shown in Figure 3 . The computer device can execute step S202 through the event determination module 320. The computer device can execute step S203 through the time determination module 330. The computer device can execute step S204 through the information aggregation module 340. Among them, the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external computer device through a network connection. When the computer program is executed by the processor, it implements a medical research database construction method.

[0090] Those skilled in the art can understand that Figure 4 the structure shown in

[0091] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0092] In some embodiments of the present application, a computer device is provided, including one or more processors; a memory; and one or more application programs, where one or more of the application programs are stored in the memory and configured to be executed by the processor to perform the steps of the above-mentioned medical research database construction method. The steps of the medical research database construction method here may be the steps in the medical research database construction method of the above-mentioned various embodiments.

[0093] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0094] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0095] The above has introduced in detail a method, device, computer device, and computer-readable storage medium for constructing a pharmaceutical research and investment database provided by the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for constructing a pharmaceutical research and investment database, characterized in that, Including: Obtaining catalyst-related information that can reflect the business trends of target listed pharmaceutical companies; Based on the catalyst-related information, analyzing the correlation between various events and the stock prices of pharmaceutical companies to determine the events that affect stock price fluctuations as target events; Determining the occurrence time of the target event, where the occurrence time includes future occurrence time; Summarizing the occurrence times of the target events to construct a pharmaceutical research and investment database; the pharmaceutical research and investment database can be used to construct a pharmaceutical research and investment information retrieval platform for users to retrieve research and investment information of listed pharmaceutical companies.

2. The method according to claim 1, wherein The step of analyzing the correlation between various events and the stock prices of pharmaceutical companies based on the catalyst-related information to determine the events that affect stock price fluctuations as target events includes: Based on the catalyst-related information, analyzing the correlation between various events and the stock prices of pharmaceutical companies to screen out the key events that affect abnormal stock price changes; According to the event attributes of the key events, aggregating each of the key events to obtain target events in the form of an event set; Among them, the target events include at least one of the following: registration progress, pipeline progress, transaction and merger, pharmaceutical conference, medical insurance shortlisting, centralized procurement, clinical result disclosure, and major industry policies.

3. The method according to claim 2, characterized in that, The occurrence time also includes the actual occurrence time. When the target event is the registration progress, the steps of determining the occurrence time of the registration progress include: For the first key event in the registration progress, analyzing the time field of the registration database data in the catalyst-related information to obtain the actual occurrence time and / or future occurrence time of each of the first key events; For the second key event in the registration progress, correlating the drug approval application number in the catalyst-related information with the sorted drug time axis by window opening and sorting by the start time, and taking the sorted start time sequence as the actual occurrence time of each of the second key events; Among them, the first key event includes at least one of the following: applying for clinical trial, clinical approval, applying for listing, listing approval, and unapproved listing; the second key event includes the completion of the first round of supplementary review and inclusion in the priority review, and at least one of the following: the completion of the second round of supplementary review, the completion of the third round of supplementary review, the completion of the fourth round of supplementary review, and the completion of the fifth round of supplementary review.

4. The method according to claim 2, wherein The occurrence time also includes the actual occurrence time. When the target event is the pipeline progress, the steps of determining the occurrence time of the pipeline progress include: For the first patient enrollment event in the pipeline progress, taking the minimum value of the clinical start date, the first domestic recruitment date, and the first foreign recruitment date in the catalyst-related information as the actual occurrence time of the first patient enrollment event; For the first patient enrollment event in the pipeline progress, taking the minimum value of the estimated start date in the catalyst-related information as the future occurrence time of the first patient enrollment event; For the last patient enrollment event in the pipeline progress, taking the maximum value of the preliminary clinical completion date in the catalyst-related information as the actual occurrence time of the last patient enrollment event; For the last subject enrollment event in the pipeline progress, take the maximum value of the estimated preliminary completion date in the catalyst-related information as the future occurrence time of the last subject enrollment event; For the trial end event in the pipeline progress, take the maximum value of the clinical completion date in the catalyst-related information as the actual occurrence time of the trial end event; For the trial end event in the pipeline progress, take the maximum value of the estimated completion date in the catalyst-related information as the future occurrence time of the trial end event; For the data readout event in the pipeline progress, determine the article publication date in the catalyst-related information as the actual occurrence time of the data readout event; For the termination event in the pipeline progress, determine the minimum value of the start date of the clinical status change history in the catalyst-related information as the actual occurrence time of the termination event.

5. The method according to claim 2, wherein The occurrence time also includes the actual occurrence time. When the target event is a transaction merger and acquisition, the steps to determine the occurrence time of the transaction merger and acquisition include: For the merger event in the transaction merger and acquisition, perform a time field analysis on the pharmaceutical company merger information in the catalyst-related information, and determine the latest announcement date as the actual occurrence time of the merger event; For the transaction event in the transaction merger and acquisition, perform a time field analysis on the drug transaction information in the catalyst-related information, and determine the release time as the actual occurrence time of the transaction event.

6. The method according to any one of claims 1 to 5, characterized in that The method further includes: If the future occurrence time of the target event is empty, analyze the historical similar data in the catalyst-related information to obtain the estimated occurrence time as the future occurrence time.

7. The method according to claim 1, wherein The steps to summarize the occurrence time of the target event and construct a pharmaceutical investment research database include: For each target event of each target listed pharmaceutical company, summarize the occurrence time to generate a first fact table; Based on the catalyst-related information, clean out the target pipeline and associated targets of each target event to improve the first fact table and obtain a second fact table; Perform an association process on the second fact table and a pre-set company relationship table to construct the pharmaceutical investment research database.

8. A device for constructing a pharmaceutical research and investment database, characterized in that, It includes: An information acquisition module for acquiring catalyst-related information that can reflect the business trends of target listed pharmaceutical companies; An event determination module for analyzing the correlation between various events and the stock price of pharmaceutical companies based on the catalyst-related information to determine the event that affects the stock price movement as the target event; A time determination module for determining the occurrence time of the target event, where the occurrence time includes the future occurrence time; An information summary module for summarizing the occurrence time of the target event and constructing a pharmaceutical investment research database; the pharmaceutical investment research database can be used to construct a pharmaceutical investment research information retrieval platform for users to retrieve investment research information of listed pharmaceutical companies.

9. A computer device, characterized in that, The computer device includes: One or more processors; A memory; and one or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the processor to implement the method for constructing a pharmaceutical research database according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps of the method for constructing a pharmaceutical research database according to any one of claims 1 to 7.

Images