Hospital library retrieval system and method

Abstract

The invention relates to a hospital library retrieval method, the hospital library communicates with at least one superior digital library, and the method comprises the following steps: obtaining a first retrieval result from the superior digital library according to retrieval content information; obtaining a second retrieval result from an identity book list library according to the retrieval content information and the retrieval identity information, wherein the identity book list library is constructed based on medical staff associated book data and case data; the medical staff associated book data comprises educational book data and academic book data; and fusing the first retrieval result and the second retrieval result to obtain a user retrieval result. According to the retrieval result of the hospital library retrieval method, the diagnosis and treatment calendar of the patient and the knowledge structure of the medical staff of the hospital are considered, and the medical staff and the patient can be benefited while the retrieval performance and the recording range of the hospital digital library are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of information retrieval, and in particular relates to a hospital library retrieval system and method. Background Art

[0002] Digital library is a distributed information system (Distributed Software Systems). In order to meet the clinical and scientific research needs of medical staff, many hospitals have built hospital digital libraries. However, the current search results of hospital digital libraries only consider the search efficiency, search accuracy and search comprehensiveness, without considering the diagnosis and treatment history of patients in the hospital and the knowledge structure of medical staff in the hospital. As a result, the hospital has improved the search performance and coverage of the hospital digital library, but it may not benefit the hospital, medical staff and patients. Summary of the invention

[0003] In order to solve at least one technical problem proposed by the present invention, the present invention proposes a hospital library search method, wherein the hospital library communicates with at least one superior digital library, and the method comprises the following steps:

[0004] Acquire a first search result ordered set from the superior digital library according to the search content information;

[0005] Obtaining a second ordered set of search results from an identity book list library according to the search content information and the search identity information; the identity book list library is constructed based on medical staff-related book data and case data, and the medical staff-related book data includes academic book data and academic book data;

[0006] An intersection of the first search result ordered set and the second search result ordered set is calculated to generate a first user search result ordered set.

[0007] In order to solve at least one technical problem raised by the present invention, the present invention also proposes a hospital library retrieval system, which includes at least one processor; and a memory storing instructions, which, when executed by at least one processor, implement the steps of the aforementioned method.

[0008] In order to solve at least one technical problem proposed by the present invention, the present invention further proposes a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the aforementioned method when the computer program / instruction is executed by a processor.

[0009] In order to solve at least one technical problem proposed by the present invention, the present invention further proposes a computer program product, including a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0010] The beneficial effect of the present invention is that the search results of the hospital library search method of the present invention take into account the medical records of the patients in the hospital and the knowledge structure of the medical staff of the hospital, and while improving the search performance and coverage of the hospital digital library, it can benefit the hospital, medical staff and patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a topological map of the superior digital library and the hospital library;

[0012] Figures 2 to 4 A flowchart of the search method for hospital libraries;

[0013] Figure 5 is a schematic diagram of an ordered set of first search results;

[0014] Figure 6 is a schematic diagram of an ordered set of second search results;

[0015] Figure 7 A schematic diagram of an ordered set of search results for the first user;

[0016] Figure 8 A schematic diagram of an ordered set of search results for a second user;

[0017] Fig. 9 Sorting matching results indicates intent;

[0018] Fig.10 This is a schematic diagram of the correction set;

[0019] Fig.11 A schematic diagram of the ordered set of search results for the second user (after correction);

[0020] Fig.12 Sorting matching results indicates intent;

[0021] Fig.13 This is a schematic diagram of the search results of related books with negative cases deleted. DETAILED DESCRIPTION

[0022] In some embodiments, a hospital library search method is provided, such as Figure 1 As shown, the hospital library 1 communicates with at least one superior digital library 2, such as Figure 2 As shown, the method comprises the following steps:

[0023] S1: Acquire a first ordered set of search results from the superior digital library according to the search content information;

[0024] S2: obtaining a second ordered set of search results from an identity book list library according to the search content information and the search identity information; the identity book list library is constructed based on medical staff-related book data and case data, and the medical staff-related book data includes academic book data and academic book data;

[0025] S3: Calculate the intersection of the first search result ordered set and the second search result ordered set to generate a first user search result ordered set.

[0026] Combine the following Figures 5 to 7 These embodiments are further described. Figure 5 As shown, the first search result ordered set 10 is recorded as {A, B, C, D, E, F, G, H, I}, including 9 ordered search results 11, each of which includes a title 12 and an abstract 13. Figure 6 As shown, the second search result ordered set 20 is recorded as {A, B, o, p, E, F, q, r, i}, including 9 search results 21 arranged in order, each search result 21 including a title 22 and an abstract 23. Figure 7 As shown, the first user search result ordered set 30 is the intersection of the above two sets, recorded as {A, B, E, F}, including 4 ordered search results 31, each search result 31 includes a title 32 and an abstract 33.

[0027] "Retrieval content information" refers to the information input by the user into the retrieval system. The modalities of retrieval content information include written (such as keywords) or spoken natural language signals (such as voice), pictures and video signals, etc. It can be a single-modal retrieval or a cross-modal retrieval. The latter is generally used in multimedia digital libraries.

[0028] "Superior digital library" refers to a digital library whose retrieval system can perform combined retrieval on a large number of databases and display unified retrieval results. Taking university digital libraries as an example, they usually purchase a large number of shared databases (such as MedSci, Pubmed, CNKI, China Biomedical Literature Database (CBM), China Science Citation Database (CSCD), Wanfang Data, Duxiu Academic Search, Weipu Information, SuperStar Digital Library, TANet, PubChem, JSTOR, IEEE Xplore, EBSCOhost, ScienceDirect, SpringerLink, Web of Science, NSSD, etc.) or build several school databases (such as library collections). In order to improve retrieval efficiency, its retrieval system can perform combined retrieval on a large number of databases and display unified retrieval results; in the present invention, the retrieval system of the superior digital library is a known technology, such as the retrieval system of Chinese patent CN118170816 A that obtains a target database combination by weight screening based on user retrieval history data. Compared with the university digital library, the affiliated hospital digital library is a subordinate digital library. The affiliated hospital digital library can obtain search results by accessing the university digital library interface instead of accessing the shared database interface, thus avoiding duplicate construction of digital libraries.

[0029] "Search results" refers to the search results that meet the search requirements obtained by the user after the search tool or search system executes the search process, including titles, abstracts, image thumbnails, etc.

[0030] An “ordered set of search results” refers to a data structure such as a table or array that is a combination of ordered search results (data / elements).

[0031] "Retrieval identity information" includes medical and nursing role information, medical and nursing education information, work experience information (such as clinical research papers published or guided during work, academic conferences attended), and other registration information that can distinguish the user's knowledge structure; the medical and nursing role information includes doctor identity information and nurse identity information. The hospital library retrieval system can collect retrieval identity information through the user registration form.

[0032] “Academic book data” refers to a book data set or book catalog data set that represents the knowledge structure of medical staff during their study period, obtained through computer search or manually sorted based on the academic information of medical staff, including but not limited to textbook data, degree theses and their citation data, etc. For example, the textbook data of Doctor B who graduated from University A with a master's degree in clinical medicine, the textbooks used by this class include Physiology (X Publishing House Y Edition), Internal Medicine (X Publishing House Y Edition), Surgery (X Publishing House Y Edition), Preventive Medicine (X Publishing House Y Edition), Neurology (X Publishing House Y Edition), Biochemistry and Molecular Biology (X Publishing House Y Edition), Pharmacology (X Publishing House Y Edition), Pathology (X Publishing House Y Edition), Pathophysiology (X Publishing House Y Edition), Diagnostics (X Publishing House Y Edition), Medical Microbiology (X Publishing House Y Edition), Traditional Chinese Medicine (X Publishing House Y Edition), Obstetrics and Gynecology (X Publishing House Y Edition), Histology and Embryology (X Publishing House Y Edition), Pediatrics (X Publishing House Y Edition), Advanced Mathematics for Medical Use (X Publishing House Y Edition), and Doctor-Patient Communication 》(Y edition of X Publishing House), Organic Chemistry (Y edition of X Publishing House), Medical Biology (Y edition of X Publishing House), Basic Chemistry (Y edition of X Publishing House), Medical Genetics (Y edition of X Publishing House), Medical Psychology (Y edition of X Publishing House), Anesthesiology (Y edition of X Publishing House), Internal Medicine (Y edition of X Publishing House), Surgery (Y edition of X Publishing House), Preventive Medicine (Y edition of X Publishing House), Neurology (Y edition of X Publishing House), Forensic Medicine (Y edition of X Publishing House), Medical Statistics (Y edition of X Publishing House), Ophthalmology (Y edition of X Publishing House), Clinical Epidemiology and Evidence-Based Medicine (Y edition of X Publishing House), Human Parasitology (Y edition of X Publishing House), Dermatology (Y edition of X Publishing House), Systematic Anatomy (Y edition of X Publishing House), Pathophysiology (Y edition of X Publishing House).

[0033] "Academic book data" refers to a book data set that represents the knowledge structure of medical staff during their working period, obtained through computer search or manually sorted based on the academic information of medical staff. The academic book data includes post-work paper data and its citation data, academic conference data, etc.

[0034] The "academic book data" and "academic book data" of the present invention are obtained using well-known computer technologies, such as data crawling (such as DFS, BFS crawlers, etc.), data screening, text description supplementation, data annotation, etc., to establish a data set that can be used in a digital library.

[0035] "Medical staff-related book data" refers to a data set that reflects the relationship between "retrieval identity information" and "book data" after data preprocessing by merging "academic book data" and "academic book data", which represents the sum of the knowledge structure of medical staff. The data preprocessing method includes one or more steps of data cleaning, data standardization, data normalization, category coding, feature selection, etc.

[0036] "Case data" includes but is not limited to digital biochemical test reports, discharge records, imaging test reports, case records, emergency medical records, admission records, case surveys, case study reports, etc. The "case data" of the present invention can be directly obtained from a digital hospital system or obtained using machine learning technology. The digital hospital system includes but is not limited to a hospital information system (HIS), a telemedicine system (Tele medicine), an online business processing system (OLTP), a clinical information system (CIS), an online analytical processing system (OLAP), an Internet system (Intranet / Internet), etc. Healthcare information technology refers to information and communication technologies specifically used to handle or process medical or health data, such as ICT technologies for medical simulation or medical data mining based on patient-specific data (such as electronic medical records). There is no report in the prior art on the combination of hospital digital libraries and healthcare information technology. In order to solve the technical problems of the present invention, multiple embodiments of the present application combine digital libraries with healthcare information technology.

[0037] “Intersection” means that the elements of the intersection (search results) belong to both the first search result ordered set and the second search result ordered set, and the elements of the intersection are also ordered.

[0038] Based on the above embodiments, a digital library platform is provided that is based on the current hospital resource situation and takes clinical needs into consideration. Since the search results take into account the diagnosis and treatment cases of patients in the hospital and the knowledge structure of the medical staff of the hospital, the hospital can benefit the hospital, medical staff and patients when improving the search performance and coverage of the hospital digital library. The hospital does not have to blindly pursue search efficiency, search accuracy and search comprehensiveness, and does not need to waste medical funds (if a database that does not match the knowledge structure of the medical staff of the hospital is purchased, it is equivalent to the investment of the hospital in the library not being reflected in the patient service). The search results obtained by medical staff are more targeted and available (reduce information redundancy, such as the search results obtained by nurses, which will not include certain foreign books and books with high professional depth; the search results obtained by doctors will not include books that record poor diagnosis and treatment plans.), and patients can obtain more advanced treatment services.

[0039] In some other embodiments of the present invention, it also relates to a hospital library search method, such as Figure 3As shown, the method further comprises the following steps:

[0040] S4: Calculate the relative complement of the second search result ordered set in the first search result ordered set to generate a second user search result ordered set, and the first user search result ordered set is outputted in priority to the second user search result ordered set.

[0041] “The relative complement of the second search result ordered set in the first search result ordered set” means that the elements of the relative complement belong to the first search result ordered set but not to the second search result ordered set.

[0042] "The first user's ordered set of search results is outputted before the second user's ordered set of search results" means that in the matching result sorting table presented to the user, the search results (data / elements) in the first user's ordered set of search results are ranked first, while the search results (data / elements) in the second user's ordered set of search results are ranked later.

[0043] "Matching result ranking table" refers to a visual form presented to the user through a human-computer interaction interface (GUI), including a single-modal matching result ranking table and a mixed-modal matching result ranking table. Among them, for traditional digital libraries, it is usually a single-modal matching result ranking table, such as a ranking table of excerpt information of digitized journals, dissertations or books. For multimedia digital libraries, it is usually a mixed-modal matching result ranking table, such as a mixed ranking of journals, papers or books with videos. The way in which the aforementioned matching result ranking table presents data belongs to known technology.

[0044] Combine the following Figures 5 to 9 These embodiments are further described. Figure 5 As shown, the first search result ordered set 10 is recorded as {A, B, C, D, E, F, G, H, I}, including 9 ordered search results 11, each of which includes a title 12 and an abstract 13. Figure 6 As shown, the second search result ordered set 20 is recorded as {A, B, o, p, E, F, q, r, i}, including 9 search results 21 arranged in order, each search result 21 including a title 22 and an abstract 23. Figure 7 As shown, the first user search result ordered set 30 is the intersection of the above two sets, recorded as {A, B, E, F}, including 4 ordered search results 31, each search result 31 includes a title 32 and an abstract 33. Figure 8As shown, the second user search result ordered set 40 is the relative complement of the second search result ordered set in the first search result ordered set, recorded as {C, D, G, H, I}, and includes 5 search results 41 arranged in order, each search result 41 includes a title 42 and an abstract 43. Fig. 9 As shown, in the matching result sorting table 50, the retrieval results (data / elements) in the first user retrieval result ordered set {A, B, E, F} are ranked higher, while the retrieval results (data / elements) in the second user retrieval result ordered set {C, D, G, H, I} are ranked lower.

[0045] Based on the above embodiment, the technical effect of making the search results obtained by medical staff more targeted and available is retained based on the first user search result ordered set, and the user's in-depth browsing needs for the superior digital library are guaranteed based on the second user search result ordered set.

[0046] In some other embodiments of the present invention, it also relates to a hospital library search method, such as Figure 4 As shown, the method further comprises the following steps:

[0047] S5: Calculate the relative complement of the first search result ordered set in the second search result ordered set to generate a revised set;

[0048] S6: Based on the element relationship between the revised set and the second user search result ordered set, adjust the order of the search results in the second user search result ordered set.

[0049] “Calculating the relative complement of the first search result ordered set in the second search result ordered set” means that the elements of the relative complement belong to the second search result ordered set but do not belong to the first search result ordered set.

[0050] "The correlation between the revised set and the ordered set of the second user's search results" refers to the correlation between the elements (search results) in the two sets, specifically the correlation between the titles and abstracts. The algorithm for determining the correlation between the titles and abstracts of the two search results is a known technology. For example, the ordered set of the second user's search results includes "Epidemiology (9th edition) published by People's Medical Publishing House", and the revised set includes "Epidemiology (8th edition) published by People's Medical Publishing House". The two are only different in version and have a high similarity. For another example, the ordered set of the second user's search results includes "Cell Biology (4th edition) published by Higher Education Press", and the search results in the revised set include nursing books such as "Introduction to Nursing (5th edition)" and "Surgical Nursing (7th edition)", and the two have a low similarity.

[0051] Combine the following Figures 5 to 8 , Figures 10-12 These embodiments are further described. Figure 5 As shown, the first search result ordered set 10 is recorded as {A, B, C, D, E, F, G, H, I}, including 9 ordered search results 11, each of which includes a title 12 and an abstract 13. Figure 6 As shown, the second search result ordered set 20 is recorded as {A, B, o, p, E, F, q, r, i}, including 9 search results 21 arranged in order, each search result 21 including a title 22 and an abstract 23. Figure 7 As shown, the first user search result ordered set 30 is the intersection of the above two sets, recorded as {A, B, E, F}, including 4 ordered search results 31, each search result 31 includes a title 32 and an abstract 33. Figure 8 As shown, the second user search result ordered set 40 is the relative complement of the second search result ordered set in the first search result ordered set, recorded as {C, D, G, H, I}, and includes 5 search results 41 arranged in order, each search result 41 includes a title 42 and an abstract 43. Fig.10 As shown, the modified set 60 is the relative complement of the first search result ordered set in the second search result ordered set, recorded as {o, p, q, r, i}, including 5 ordered search results 61, each search result 61 including a title 62 and an abstract 63. In this embodiment, the total relevance score of each search result of the second user search result ordered set {C, D, G, H, I} and each search result of the modified set {o, p, q, r, i} is calculated. First, the search result C is respectively calculated with the search result o, the search result p, the search result q, the search result r, and the search result i for the total similarity score, recorded as {Co, Cp, Cq, Cr, Ci}->{34 points, 65 points, 28 points, 96 points, 18 points}->C total score: 241 points. Then the total similarity scores of D, G, H, and I are obtained in turn, which are: D total score: 414 points; G total score: 119 points; H total score: 208 points; I total score: 239 points. like Fig.11 As shown, the second user search result ordered set (corrected) 40' is formed by adjusting the order of the search results of the second user search result ordered set {C, D, G, H, I}, recorded as {D, C, I, H, G}, and each search result 41' includes a title 42' and an abstract 43'. Fig.12 As shown, in the matching result sorting table 70, the retrieval results (data / elements) in the first user retrieval result ordered set {A, B, E, F} are ranked higher, and the retrieval results (data / elements) in the second user retrieval result ordered set (corrected) {D, C, I, H, G} are ranked lower.

[0052] Based on the above embodiment, the technical effect of making the search results obtained by medical staff more targeted and available is retained based on the first user search result ordered set, and the user's in-depth search needs for the superior digital library are guaranteed based on the second user search result ordered set.

[0053] In some other embodiments of the present invention, a hospital library search method is also provided, wherein:

[0054] Splitting the first search result ordered set into a plurality of first search result ordered subsets;

[0055] Splitting the second search result ordered set into a plurality of second search result ordered subsets;

[0056] The intersection of the first search result ordered subset and the second search result ordered subset corresponding to the search result is calculated to generate a first user search result ordered subset.

[0057] "The first search result ordered set splitting" is based on the set partitioning technology. According to the number n (of search results (elements) presented in the sorted table of matching results on each page of the user's search device, and the number m (of search results (elements) of the first search result ordered set of this search, the first search result ordered set is split into m / n rounded up (pieces). For example, if a user's search device is a desktop computer and its sorted table of matching results on each page can present 15 search results (elements), and the first search result ordered set of a certain search includes 144 search results (elements), then the first search result ordered set is split into 10 first search result ordered subsets. For another example, if a user's search device is a mobile phone and its sorted table of matching results on each page can present 9 search results (elements), and the first search result ordered set of a certain search includes 144 search results (elements), then the first search result ordered set is split into 16 first search result ordered subsets.

[0058] "Splitting of the second ordered set of search results" is also based on set partitioning technology. According to the number n of search results (elements) presented in the matching result sorting table on each page of the user's search device, and the number m of search results (elements) of the second ordered set of search results in this search, the second ordered set of search results is split into m / n (rounded up).

[0059] "Calculate the corresponding intersection of the first ordered subset of search results and the second ordered subset of search results" means taking the intersection of a first ordered subset of search results and a second ordered subset of search results (1 to 1), or taking the intersection of a first ordered subset of search results and multiple second ordered subsets of search results (1 to many).

[0060] In the above embodiment, when the data volume of the first search result ordered set and the second search result ordered set is large, the sets are divided into subsets and then the intersection operation is performed, which greatly reduces the processing time. Among them, when an ordered subset of the first search result is corresponding to multiple ordered subsets of the second search result, the ordered subset of the second search result is given priority to present the elements that meet the conditions in advance as much as possible. For example, there are 7 ordered subsets of the first search result and 16 ordered subsets of the second search result. According to the 1-to-2 relationship, 14 elements of the ordered subset of the second search result can be used to take the intersection, while according to the 1-to-1 relationship, only 7 elements of the ordered subset of the second search result can be used to take the intersection. The former gives priority to the ordered subset of the second search result.

[0061] In some other embodiments of the present invention, a hospital library search method is also provided, wherein the method further comprises the following steps:

[0062] The relative complement of the second ordered subset of search results in the corresponding ordered subset of the first search results is calculated to generate a second user ordered subset of search results, and the first user ordered subset of search results is outputted in priority to the second user ordered subset of search results.

[0063] In the above embodiment, the difference from the previous embodiment of "the relative complement of the second search result ordered set in the first search result ordered set" is that the elements of the relative complement of the previous embodiment consider all elements that belong to the first search result ordered set but do not belong to the second search result ordered set. The elements of the relative complement of this embodiment only consider the elements that belong to the first search result ordered set but do not belong to the second search result ordered set in each page of the matching result sorting table, which can reduce the amount of calculation when the amount of data is large.

[0064] In some other embodiments of the present invention, a hospital library search method is also provided, wherein the method further comprises the following steps:

[0065] Calculating the relative complement of the first ordered subset of the search results in the second ordered subset of the search results to generate a modified subset;

[0066] Based on the correlation between the modified subset and a plurality of the second user search result ordered subsets including the corresponding second user search result ordered subsets, the order of the search results in the second user search result ordered subsets is adjusted.

[0067] In the above embodiment, the difference from the previous embodiment "based on the element relationship between the modified set and the second user search result ordered set" is that the elements of the relative complement set in the previous embodiment consider all elements that belong to the second search result ordered set but do not belong to the first search result ordered set. The elements of the relative complement set in this embodiment only consider the elements of the matching result sorting table on each page, which can reduce the amount of calculation when the amount of data is large.

[0068] In some other embodiments of the present invention, a hospital library search method is also involved, which constructs a case-irrelevant book data set based on the case data, and deletes the search results that are identical to the case-irrelevant book data set in the ordered set of search results of the second user.

[0069] "Constructing a case-independent book dataset based on case data" means constructing a dataset based on negative case data (such as medical accident cases) and the book data that matches it.

[0070] In the above embodiment, the probability of medical staff obtaining wrong information is reduced. Fig.13 As shown, if the associated book of a negative case is "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" (2018), the search results containing "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" (2018) are deleted in the ordered set of search results of the second user, but "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" 2016, "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" 2017, "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" 2019, and "Guidelines for Diagnosis, Treatment and Rehabilitation of Cervical Spondylosis" 2022 are still retained.

[0071] Some other embodiments of the present invention also involve a hospital library search method, wherein the correlation between the revised set and the ordered set of search results of the second user is recorded each time the search is performed, and the high-frequency and low-correlation search results in the revised set are used to generate an ordered set of candidate books for the hospital library.

[0072] In the above embodiment, "high-frequency and low-correlation search results in the revised set" refers to search results (elements) that appear multiple times in the ordered set of search results of the second user, but each time have a low correlation with the revised set. The books corresponding to these search results are books that the medical staff of this hospital are interested in, but are not included in the corresponding database of the superior digital library. Therefore, the ordered set of candidate books for the hospital library can serve as a reference for the hospital to improve the scope of the hospital digital library in the future.

[0073] In some other embodiments of the present invention, a hospital library search method is also involved, wherein the method of constructing the identity book list library according to the medical staff associated book data and the case data comprises the following steps:

[0074] 1. Construct a medical staff-related book data set based on the medical staff-related book data;

[0075] 2. Construct a case-related book dataset based on the case data;

[0076] 3. The medical staff-associated book dataset and the case-associated book dataset are merged to obtain the identity book list library.

[0077] These embodiments are described below in conjunction with Table 1.

[0078] Table 1 Data and data set element attributes

[0079]

[0080]

[0081] Furthermore, “constructing a medical staff-related book data set based on medical staff-related book data” includes the following steps:

[0082] 1.1 Obtain the hospital's educational and academic data;

[0083] The educational background data includes the educational background information (school, major, year of admission, etc.) of all current and historical medical staff of the hospital, and multiple educational backgrounds of each medical staff are entered into multiple pieces of educational background information; for example, XXX, a neurosurgeon, studied clinical medicine (undergraduate) at University A in 1996 and studied neurosurgery (master) at University B in 2002, which is recorded as two pieces of educational background information: {XXX-1, University A, clinical medicine, 1996}, {XXX-2, University B, neurosurgery, 2002}.

[0084] The academic data includes the academic information of all current and historical medical staff of the hospital (published papers, published books, conference papers, etc.), and the same academic resume of different medical staff may be recorded as multiple pieces of academic information; for example, Doctor XXX and Doctor YYY jointly published Paper S in 2010, which is recorded as two pieces of academic information: {XXX, Paper S}, {YYY, Paper S}.

[0085] 1.2 Academic book data representing the knowledge structure of medical personnel during their study period obtained through computer search or manually sorted based on the deduplicated academic information of medical personnel; academic book data representing the knowledge structure of medical personnel's academic research obtained through computer search or manually sorted based on the deduplicated academic information of medical personnel;

[0086] For example, continuing with the previous example, XXX neurosurgeon studied clinical medicine (undergraduate) at A University in 1996, and YYY cardiac surgeon has the same first degree as XXX neurosurgeon, then the search system only needs to search for books related to "1996 A University Clinical Medicine (undergraduate)" (deduplicated academic information).

[0087] For example, continuing with the previous example, since Doctor XXX and Doctor YYY jointly published Paper S in 2010, the search system only needs to use the relevant citation books of "Paper S" (without duplicate academic information).

[0088] 1.3 After cleaning the academic book data, the data is standardized and the educational background impact factor is given to obtain the academic-related book data set. After cleaning the academic book data, the data is standardized and the academic resume impact factor is given to obtain the academic-related book data set.

[0089] The educational background impact factor α is determined according to the number of times the book is repeated; for example, continuing the previous example, the relevant books of "Clinical Medicine Major (Undergraduate) of A University in 1996" include M books. Since XXX neurosurgeon and YYY cardiac surgeon have both studied M books, the impact value of the educational background impact factor α of M books is increased. For another example, continuing the previous example, the physical diagnosis doctor studied medical imaging major (undergraduate) of C University in 1989, and its relevant books also include M books, then the impact value of the educational background impact factor α of M books is increased.

[0090] The academic resume impact factor β is also determined according to the number of times the book is repeated; for example, continuing the previous example, for example, the search system needs to search for the relevant citation book "Paper T" with "Paper S" (without duplicate academic information). Since XXX neurosurgeon and YYY cardiac surgeon have both paid attention to Paper T, the impact value of the academic resume impact factor β of Paper T is increased. For another example, continuing the previous example, if "Paper O" published by a physical diagnosis doctor cites "Paper T", the impact value of the academic resume impact factor β of "Paper T" is increased.

[0091] 1.4 After deduplication, the academic qualification-related book dataset and the academic qualification-related book dataset are merged to obtain a medical staff-related book dataset. In a specific embodiment, as shown in Table 1, the merged academic qualification-related book dataset can simultaneously represent the relationship between the academic qualification, academic qualification and books of the medical staff of the hospital.

[0092] Furthermore, “constructing a case-related book dataset based on case data” includes the following steps:

[0093] 2.1 Obtain case data from the digital hospital system, extract high-level semantic information from the case to obtain empirical data;

[0094] The experience data includes all the experience information (medical care plans, medical care results, etc.) of the hospital in which all the medical staff of the hospital currently and historically participated in the diagnosis and treatment, and multiple cases of each patient include multiple pieces of experience information. The digital hospital system includes but is not limited to hospital information system (HIS), telemedicine system (Tele medicine), online business processing system (OLTP), clinical information system (CIS), online analytical processing system (OLAP) Internet system (Intranet / Internet), etc. When extracting high-level semantic information, well-known feature extraction techniques are used, including but not limited to clustering algorithms (such as K-MEANS), natural language processing (NPL), machine learning (Machine Learning, ML), etc.

[0095] For example, patient a with cervical spondylosis visited the orthopedics department of the hospital in 2001 and was treated by doctor b. His case data includes case records, imaging test reports, biochemical test reports, case study reports, etc. The extracted high-level semantic information of patient a is {b, doctor, treatment plan (vertebral artery type cervical spondylosis; dizziness and headache, partial blood stasis should be treated with blood stasis removal, meridian dredging, dampness removal and liver calming; Xuefu Zhuyu Decoction treatment; treatment results (basically normal; evaluation of spinal cord function status of patients with cervical spondylosis (40-point method); I. Upper limb function is basically normal; II. Lower limb function is basically normal; III. Sphincter function is basically normal; VI. Limb sensation is basically normal; V. Band sensation is basically normal}.

[0096] 2.2 Experience book data representing the knowledge structure of the medical staff's clinical experience obtained by computer search based on the deduplicated experience information of the medical staff or by matching with the medical staff-related book data set;

[0097] For example, continuing the previous example, the search system uses "vertebral artery type cervical spondylosis; dizziness and headache, partial blood stasis should be treated with blood stasis, meridians, dampness and liver; Xuefu Zhuyu Decoction", "treatment results (basically normal; evaluation of spinal cord function status of patients with cervical spondylosis (40-point method); I. Upper limb function is basically normal; II. Lower limb function is basically normal; III. Sphincter function is basically normal; VI. Limb sensation is basically normal; V. Band sensation is basically normal" as search text to crawl related book information;

[0098] For another example, continuing with the previous example, the matching system "Vertebral artery type cervical spondylosis; dizziness accompanied by headache, partial blood stasis should be treated with blood stasis, unblocking meridians, removing dampness and calming the liver; Xuefu Zhuyu Decoction for treatment", "Treatment results (basically normal; Assessment of spinal cord function status of patients with cervical spondylosis (40-point method); I. Upper limb function is basically normal; II. Lower limb function is basically normal; III. Sphincter function is basically normal; VI. Limb sensation is basically normal; V. Girdle sensation is basically normal" are used as reference texts for semantic matching with the book abstract text information of the medical staff associated book dataset.

[0099] 2.3 After data cleaning, the experience book data is standardized and given a work experience impact factor to obtain the case-related book data set;

[0100] The work experience influence factor γ is determined according to the number of times the book is repeated; for example, continuing the previous example, the books related to doctor b’s “basically normal” patient a’s high-level semantic information include N books, and the books related to doctor b’s “basically normal” patient c’s high-level semantic information also include N books. Since both patient a and patient c benefit from doctor b’s study of N books, the influence value of the work experience influence factor γ of the N books is increased. For another example, continuing the previous example, the books related to doctor b’s “basically normal” patient a’s high-level semantic information include N books, and the books related to doctor d’s “basically normal” patient medical staff associated book data set also include N books. Since both patient a and patient c benefit from the hospital’s doctors (doctor b, doctor d)’s study of N books, the influence value of the work experience influence factor γ of the N books is increased. In addition, the “abnormal” doctor’s experience information on the diagnosis and treatment of patients will be included in the case-irrelevant book data set.

[0101] Furthermore, “merging the medical staff-related book dataset and the case-related book dataset to obtain the identity book list library” includes the following steps:

[0102] 3.1 Obtain the medical staff-related book dataset and case-related book dataset;

[0103] 3.2 The medical staff-associated book dataset and the case-associated book dataset are merged to obtain the identity book list library.

[0104] In a specific embodiment, the greater the influence value of the education background influence factor α, the academic resume influence factor β, and the work experience influence factor γ on a certain book, the higher the ranking of the book in the identity book list library. However, the present invention does not limit the way in which the education background influence factor α, the academic resume influence factor β, and the work experience influence factor γ affect the ranking. Any technology that adjusts the way in which the ranking is affected, such as by introducing weights and machine learning, is within the scope of the present invention.

[0105] In the above embodiment, the patients of a hospital are fixed, and the information that a hospital can obtain from the digital library is fixed. Some of this information is wrong, and some is useful. The construction of the identity book list library fully reflects the relationship between the identity (education, academic, experience) of the medical staff of a hospital and the books. The identity book list library of the present invention is the knowledge graph of the medical staff and the case knowledge graph of the hospital. In order to optimize the matching results, any known knowledge graph construction technology is within the selection scope of the present invention.

[0106] The implementation and functional operation of the subject matter described in this specification can be implemented in the following: digital electronic circuits, tangibly implemented computer software or firmware, computer hardware, including the structures disclosed in this specification and their structural equivalents, or a combination of more than one of the above. The implementation of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules of computer program instructions encoded on one or more tangible non-transitory program carriers, for being executed by a data processing device or controlling the operation of a data processing device. Computer programs (which may also be referred to or described as programs, software, software applications, modules, software modules, scripts or codes) can be written in any form of programming language, including compiled languages ​​or interpreted languages ​​or declarative languages ​​or procedural languages, and computer programs can be expanded in any form, including as independent programs or as modules, components, subroutines or other units suitable for use in a computing environment. Computer programs may, but do not necessarily, correspond to files in a file system. Programs may be stored in a portion of a file that stores other programs or data, for example, one or more scripts stored in the following: in a markup language document; in a single file dedicated to a related program; or in multiple collaborative files, for example, files storing one or more modules, subroutines or code portions. A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

Claims

1. A hospital library search method, wherein the hospital library communicates with at least one superior digital library, characterized in that: The method comprises the following steps: Acquire a first search result ordered set from the superior digital library according to the search content information; Obtaining a second ordered set of search results from an identity book list library according to the search content information and the search identity information; the identity book list library is constructed based on medical staff-related book data and case data, and the medical staff-related book data includes academic book data and academic book data; An intersection of the first search result ordered set and the second search result ordered set is calculated to generate a first user search result ordered set.

2. The hospital library search method according to claim 1, characterized in that: The method further comprises the steps of: The relative complement of the second retrieval result ordered set in the first retrieval result ordered set is calculated to generate a second user retrieval result ordered set, and the first user retrieval result ordered set is outputted in priority to the second user retrieval result ordered set.

3. The hospital library search method according to claim 2, characterized in that: The method further comprises the steps of: Calculating the relative complement of the first search result ordered set in the second search result ordered set to generate a revised set; Based on the correlation between the revised set and the second user search result ordered set, the order of the search results in the second user search result ordered set is adjusted.

4. The hospital library search method according to any one of claims 1 to 3, characterized in that: Splitting the first search result ordered set into a plurality of first search result ordered subsets; Splitting the second search result ordered set into a plurality of second search result ordered subsets; The intersection of the first search result ordered subset and the second search result ordered subset corresponding to the search result is calculated to generate a first user search result ordered subset.

5. The hospital library search method according to claim 4, characterized in that: The method further comprises the steps of: The relative complement of the second ordered subset of search results in the corresponding ordered subset of the first search results is calculated to generate a second user ordered subset of search results, and the first user ordered subset of search results is outputted in priority to the second user ordered subset of search results.

6. The hospital library search method according to claim 5, characterized in that: The method further comprises the steps of: Calculating the relative complement of the first ordered subset of the search results in the second ordered subset of the search results to generate a modified subset; Based on the correlation between the modified subset and a plurality of the second user search result ordered subsets including the corresponding second user search result ordered subsets, the order of the search results in the second user search result ordered subsets is adjusted.

7. The hospital library search method according to claim 2, characterized in that: A case-irrelevant book data set is constructed based on the case data, and search results identical to the case-irrelevant book data set in the ordered set of search results of the second user are deleted.

8. The hospital library search method according to claim 3, characterized in that: The correlation between the revised set and the ordered set of search results of the second user is recorded each time a search is performed, and the search results with high frequency and low correlation in the revised set are used to generate an ordered set of candidate books for the hospital library.

9. The hospital library search method according to any one of claims 1 to 3, characterized in that: The method for constructing the identity book list library according to the medical staff associated book data and the case data comprises the following steps: Constructing a medical staff-associated book data set according to the medical staff-associated book data; Constructing a case-related book data set based on the case data; The identity book list library is obtained by performing feature extraction and fusion on the medical staff-associated book dataset and the case-associated book dataset.

10. A hospital library search system, characterized in that: The system comprises at least one processor; and a memory storing instructions, which, when executed by the at least one processor, implement the steps of the method according to any one of claims 1 to 9.

Images