Medical information processing system based on cloud platform

Abstract

The invention relates to the field of information processing, and discloses a medical information processing system based on a cloud platform, the system comprises a user terminal, an in-hospital server and the cloud platform, the user terminal, the in-hospital server and the cloud platform are connected through a network, and sub-pages are configured on an input interface, according to user attribute information and hospital attributes, dynamic treatment information pushing is carried out, a user comprehensively generates a diagnosis and treatment scheme according to pushing of the treatment information, the diagnosis and treatment scheme and a standard diagnosis and treatment guide are triggered on a cloud platform for verification, and different verification processes are executed according to different attribute information. And the stored and labeled diagnosis and treatment schemes are subjected to cross sharing, so that the use experience of different users is improved while the utilization rate of the diagnosis and treatment data is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing, and in particular to a medical information processing system based on a cloud platform. Background Art

[0002] At present, the communication capacity and efficiency of network communication quality have been greatly improved, and various enterprise cloud platforms have been widely deployed. Cloud service platforms are provided to users as public products. Each user accesses the cloud platform through the network, and uses the cloud platform's containers to scale up and down and schedule resources. It can realize the comprehensive scheduling of user access request resources and improve the information processing capacity of the internal network system in a single local area network.

[0003] At present, the systems in traditional single networks such as hospitals have submitted the practical processing of part of the information to third-party cloud platforms, and processed their existing data resources by purchasing services. However, most of the above processing is reflected in storage access and does not involve the integrated application of diagnosis and treatment resources. At the same time, there are many existing network search engines and information is scattered on various platforms. Many search engines and other related questions and answers and news information cannot be fully utilized. The corresponding information of diagnosis and treatment services is closed in their respective hospital systems, and there are individual differences in difficult diagnosis and treatment plans. At the moment when diagnosis and treatment guidelines are vigorously promoted, how to integrate various existing diagnosis and treatment data resources, integrate existing medical data, connect information from other platforms, improve the comprehensive utilization rate of medical information, and improve user experience has become a problem that needs attention. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the present application provides a medical information processing system based on a cloud platform, the system comprising a user terminal, an in-hospital server and a cloud platform, the user terminal, the in-hospital server and the cloud platform are connected via a network, and the user terminals of the same hospital are connected to the cloud platform via a unified interface of the in-hospital server.

[0005] The hospital server stores the diagnosis and treatment information of the hospital. The diagnosis and treatment information of the hospital is annotated by multiple types of indexes. The diagnosis and treatment information is connected to the cloud platform in an authorized sharing manner.

[0006] The cloud platform obtains the diagnosis and treatment information input by the user terminal based on the authorization information of the user terminal, and pushes the treatment suggestion information to the user terminal in real time. The treatment suggestion information is displayed on the sub-interface of the user terminal interface; the user terminal selects the suggestion information and inputs it to generate a diagnosis and treatment information plan by itself, and matches and verifies the diagnosis and treatment information plan submitted by the user terminal with the diagnosis and treatment guideline specifications of the cloud platform, and determines whether to push the pending confirmation message based on the verification result.

[0007] Preferably, the diagnosis and treatment information scheme submitted by the user terminal is matched and verified with the diagnosis and treatment guideline specifications of the cloud platform, including: obtaining the diagnosis subject type, extracting the drug dosage information in the diagnosis and treatment information scheme, and when it exceeds the preset value, performing a search association verification based on the attribute information of the user corresponding to the user terminal.

[0008] Preferably, search association verification is performed based on the attribute information of the user corresponding to the user terminal, including: when the user's attribute information is an expert attribute, triggering a search for related academic literature in the cloud platform background, and accessing the historical diagnosis and treatment information schemes between corresponding hospitals through the cloud platform according to the authorization rules between hospitals. When the number of search results is higher than the preset value, the current diagnosis and treatment information scheme is verified as true and stored in the cloud platform database; if the number of search results is lower than the preset value, a confirmation message is sent to the corresponding user terminal. When the feedback information obtained is true, the diagnosis and treatment information scheme is marked as true and stored in the cloud platform database.

[0009] Preferably, a search association check is performed based on the attribute information of the user corresponding to the user terminal, including: when the attribute level of the user is low, a message push is directly triggered, and the message push includes at least information on the diagnosis and treatment guideline specifications, and the information of the current diagnosis and treatment information plan is marked, and the confirmation information is sent to require the user to confirm.

[0010] Preferably, diagnosis and treatment information input by the user terminal is obtained, and treatment recommendation information is pushed to the user terminal in real time, including: extracting information on the medical history input by the user terminal to form structured information, the cloud platform adaptively performs matching search based on the structured information, generates summary information of the diagnosis and treatment plan corresponding to the structured information, and pushes it to the corresponding user terminal sub-interface.

[0011] Preferably, obtaining diagnosis and treatment information input by the user terminal and pushing treatment suggestion information to the user terminal in real time also includes: the cloud platform sets different weighting values ​​according to the user attributes of different user terminals and the attributes of the diagnosis and treatment hospital, and jointly recommends treatment information.

[0012] Preferably, the cloud platform sets different weighting values ​​according to the user attributes of different treating doctors and the attributes of the treating hospitals, and jointly recommends treatment information, further including: the cloud platform comprehensively accesses the user's knowledge structure background, and pushes the related diagnosis and treatment information plan in the form of a summary in a substitute search manner.

[0013] Preferably, obtaining diagnosis and treatment information input by the user terminal and pushing treatment suggestion information to the user terminal in real time also includes: displaying a link to the search reasoning process in a sub-interface of the push summary, and displaying the key steps of the search reasoning process in the form of diagrams and text descriptions to the user terminal in the page corresponding to the link to the search reasoning process.

[0014] Preferably, the cloud platform obtains query information during the process of the user terminal inputting diagnosis and treatment information, and performs dynamic interaction with the cloud platform, performs dynamic intent recognition during the query interaction, and pushes diagnosis and treatment related information.

[0015] Preferably, dynamic intent recognition is performed in query interaction, including: the cloud platform constructs an association graph between user queries and clicked documents, uses the association graph to mine similarities between queries, obtains candidate expansion words, and extracts features of clicked documents for each query as features of the query.

[0016] The present invention requires a medical information processing system based on a cloud platform, wherein the system includes a user terminal, an in-hospital server and a cloud platform, wherein the user terminal, the in-hospital server and the cloud platform are connected via a network, and the user terminals of the same hospital are connected to the cloud platform via a unified interface of the in-hospital server, and dynamic treatment information is pushed according to user attribute information and hospital attributes by configuring a sub-page on an input interface, and the user generates a diagnosis and treatment plan based on the pushed treatment information, and the diagnosis and treatment plan is triggered on the cloud platform to be verified with the standard diagnosis and treatment guidelines, and different verification processes are executed according to different attribute information, and the marked diagnosis and treatment plans are stored for cross-sharing, thereby effectively improving the utilization rate of diagnosis and treatment data while improving the user experience of different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a schematic diagram of this system. DETAILED DESCRIPTION

[0020] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] Example 1

[0023] In the existing medical information system, the information of doctors can only be interacted within the hospital and is mostly limited to the department. In the existing consultation system, in the writing of medical records, the diagnosis and treatment plan can be handled by project selection, but the above treatment plan handling does not take into account the needs of different hospital attributes and user attributes and the need for real-time interaction.

[0024] In the diagnosis and treatment process of the hospital, generally speaking, different doctors in the hospital have different attribute information, such as trainee doctors, commissioned doctors, chief doctors, special experts, etc. The needs of each doctor are not the same. Different doctors have different needs for prompt information in determining and verifying the diagnosis and treatment information plan.

[0025] Furthermore, there is a need to obtain real-time information outside the hospital. The attributes of different hospitals correspond to different diagnosis and treatment information. For example, specialized hospitals, etc., have personalized clinical practices for various indicators and medication responses for specialized symptoms. How to achieve the integration and efficient full utilization and limited sharing of the above information, improve user experience, and reduce unnecessary push. This application proposes a diagnosis and treatment information processing system based on a cloud platform.

[0026] like Figure 1 As shown: the system includes a user terminal, an in-hospital server and a cloud platform. The user terminal, the in-hospital server and the cloud platform are connected via a network. The user terminals of the same hospital are connected to the cloud platform via a unified interface of the in-hospital server.

[0027] The hospital server stores the diagnosis and treatment information of the hospital. The diagnosis and treatment information of the hospital is annotated by multiple types of indexes. The diagnosis and treatment information is connected to the cloud platform in an authorized sharing manner.

[0028] The cloud platform obtains the diagnosis and treatment information input by the user terminal based on the authorization information of the user terminal, and pushes the treatment suggestion information to the user terminal in real time. The treatment suggestion information is displayed on the sub-interface of the user terminal interface; at the same time, the diagnosis and treatment information plan submitted by the user terminal is matched and verified with the diagnosis and treatment guideline specifications of the cloud platform, and it is determined whether to push the pending confirmation message based on the verification result.

[0029] In an exemplary manner, matching and verifying the diagnosis and treatment information scheme of the user terminal with the diagnosis and treatment guideline specifications of the cloud platform includes: obtaining the diagnosis subject type, extracting the drug dosage information in the diagnosis and treatment information scheme, and when it exceeds the preset value, performing a search association verification based on the attribute information of the user corresponding to the user terminal.

[0030] In an exemplary manner, a search association verification is performed based on the attribute information of the user corresponding to the user terminal, including: when the user's attribute information is an expert attribute, a related academic literature search is triggered in the cloud platform background, and according to the authorization rules between hospitals, the historical diagnosis and treatment information schemes between corresponding hospitals are accessed through the cloud platform. When the number of search results is higher than the preset value, the current diagnosis and treatment information scheme is verified as true and stored in the cloud platform database; if the number of search results is lower than the preset value, a confirmation message is sent to the corresponding user terminal. When the feedback information obtained is true, the diagnosis and treatment information scheme is marked as true and stored in the cloud platform database.

[0031] Performing association verification based on the attribute information of the user corresponding to the user terminal includes: when the attribute level of the user is low, directly triggering a message push, the message push at least includes information on diagnosis and treatment guideline specifications, and annotates the information on the current diagnosis and treatment information plan, and requires user confirmation.

[0032] In an exemplary manner, obtaining diagnosis and treatment information input by a user terminal and pushing treatment information to the user terminal includes: extracting information on the course of disease input by the user terminal to form structured information, the cloud platform adaptively performs matching searches based on the structured information, generates summary information for the diagnosis and treatment plan corresponding to the structured information, and pushes the summary information to the corresponding user terminal sub-interface.

[0033] In an exemplary manner, the real-time acquisition of diagnosis and treatment information input by the user terminal and the pushing of treatment information to the user terminal further include: the cloud platform sets different weighting values ​​according to the user attributes of different user terminals and the attributes of the diagnosis and treatment hospital, and jointly recommends treatment information. The cloud platform comprehensively accesses the user's knowledge structure background, and pushes the related diagnosis and treatment information plan in the form of a summary in a substitute search manner.

[0034] The method of obtaining diagnosis and treatment information input by a user terminal and pushing treatment information to the user terminal also includes: displaying a link to the search and reasoning process in a sub-interface of the push summary, and displaying the key steps of the search and reasoning process in the form of diagrams and text descriptions to the user terminal in a page corresponding to the link to the search and reasoning process.

[0035] The cloud platform obtains the query information during the process of the user terminal inputting the diagnosis and treatment information and performs dynamic interaction, performs dynamic intent recognition in the query interaction and pushes the diagnosis and treatment related information. The dynamic intent recognition in the query interaction includes: the cloud platform constructs an association graph between the user query and the clicked document, uses the association graph to mine the similarity between the queries, obtains candidate expansion words, and extracts the features of the clicked document of each query as the features of the query.

[0036] In other implementations, the hospital server stores the diagnosis and treatment information of the hospital itself, and the diagnosis and treatment information of the hospital is annotated by multiple types of indexes. The diagnosis and treatment information is shared with the diagnosis and treatment information disposal plan marked as true stored in the cloud platform in accordance with the cross-access authorization between different hospitals, and the user terminal of the hospital that is subject to verification access is set to access the diagnosis and treatment information disposal plan. The above settings can promote the sharing of personalized data diagnosis and treatment plans between hospitals and improve the verification efficiency. Optionally, when there are similar diagnosis and treatment plans that deviate from the norm, they can be directly recommended and annotated through the cloud platform to simplify the verification process. Furthermore, the diagnosis and treatment disposal plans associated with the verification are associated and stored. When the user terminal accesses the corresponding diagnosis and treatment information disposal plan, the corresponding associated information is pushed. The user terminal can access the associated diagnosis and treatment information disposal plans of other hospital servers through a separate authorized access method.

[0037] Exemplarily, the diagnosis and treatment information in the hospital is annotated by multiple types of indexes, and can be annotated by hospital, department, doctor attributes or diagnostic topics. For the diagnosis and treatment information input by the in-hospital doctors, the cloud platform can use classification to compare with the text information or diagnostic topic type in the diagnosis and treatment guide data of the cloud platform according to the authorization rules. Exemplarily, for the same disease, the diagnosis and treatment guidelines are standardized and matched with the diagnosis and treatment information disposal plan in the hospital by matching. Exemplarily, the diagnosis and treatment guidelines in the corresponding rule diagnosis and treatment guidelines can also be determined according to the text similarity. According to the structured processing method, the key processes or medications in the current diagnosis and treatment disposal plan are verified and matched. Exemplarily, when the disposal process and the amount of drugs exceed the preset warning value, the next process is forwarded for processing.

[0038] The next process includes: the cloud server in the cloud platform further queries the attribute information of the attending physician, and verifies it according to the knowledge tracking query of the academic search accessed by the search engine of the cloud platform. Exemplarily, when the attribute information of the user is an expert in a certain field, if the diagnosis and treatment deviates from the diagnosis and treatment standard, the expert attribute can trigger the search of related academic literature, and verify it according to the historical diagnosis and treatment message processing scheme of other related hospital attribute information accessed to the cloud platform.

[0039] For example, when the diagnosis type of the marked subject is tumor, the historical diagnosis and treatment information of the corresponding tumor hospital can be extracted for verification. If there are similar search results and the number of search results is higher than the preset value, it is stored as true; if the number of search results is lower than the preset value, a confirmation message is sent to the expert of the corresponding attribute. When feedback information is obtained, the diagnosis and treatment process is indexed and stored in the cloud platform server as cross-authorized shared data.

[0040] The cloud server further includes triggering different information processing processes based on the user's attribute information. When there is a deviation in the treatment process and the attribute level of the attending hospital is low, a message push can be directly triggered. The message push pushes standard diagnosis and treatment specification information according to the diagnosis and treatment process, and waits for user feedback information, exemplarily providing a multi-level interactive query window to the low-level user terminal interface.

[0041] In an exemplary manner, the cloud server uses a standardized processing format for the historical medical information and input medical information of different hospitals. The cloud platform parses the pushed medical record information of the hospital and the medical information input by the user terminal based on the hierarchical medical record structure.

[0042] In an optional manner, based on the existing basic standard model of medical record information in each hospital, the cloud platform differentiates the medical record information according to different diagnosis types, and treats the segmentation problem of medical records as a text classification problem. For example, the descriptive information text of the medical record can be divided into sentences by line breaks, and all sentences are pre-processed by word segmentation, part-of-speech tagging, and feature selection to represent feature vectors. For example, the SVM algorithm is used to divide all sentences into predefined general categories, which can be divided into the patient's basic diagnosis and treatment information, course of disease, diagnosis type, complications, diagnosis and treatment medication, etc.

[0043] The cloud platform can extract detailed information from the above classification results and extract user attributes such as name, age, duration of illness, historical medication and disposal through field templates.

[0044] After information extraction is performed on the course of disease in the medical record to form structured information, the cloud platform adaptively performs matching search based on the structured information, generates summary information of the diagnosis and treatment plan corresponding to the structured information, and pushes it to the corresponding user terminal sub-interface.

[0045] In an optional manner, the type of summary information pushed can comprehensively access the user's knowledge structure background, and the knowledge structure background can be based on the medical record information data pushed and uploaded by the treating physician or the registered information of the treating physician for portrait processing. Exemplarily, substitute search recommendations are made based on the portrait-related information of the treating physician. Exemplary doctors have cardiology attributes. When the query is for cardiovascular medicine methods, cardiovascular surgery treatment methods can be pushed, that is, corresponding to the same type of diagnosis, alternative treatments are pushed based on the same diagnosis type. The treatment recommendation association relationship can be based on the interactive data substitute search method of the course of disease description to make summary recommendations of related treatment plans.

[0046] Exemplarily, in the recommendation of the treatment plan for diagnosis and treatment information, it further includes the reasoning process of the search hits, and the key steps of the search reasoning are presented to the user terminal in the form of diagrams and text descriptions. The reasoning process is used to explain the reason why the recommendation result is generated. When the corresponding diagnosis and treatment plan cannot be obtained, the reason for the failure is fed back to the user terminal, and an interactive guidance interface can be set at the user interface of the user terminal to guide the user to make constraint corrections.

[0047] For example, the diagnosis and treatment information of the corresponding disease is recommended, and further associated with the search of the web crawler. The cloud platform searches for drug news, academic articles, experimental data, etc. based on the web crawler search.

[0048] In the example, the pushed information is filtered based on the attribute information of the treating doctor, and sorted in the corresponding sub-interface to present different types of diagnosis and treatment information. For example, for expert doctors, diagnosis and treatment guidelines are already common knowledge for expert doctors, so summary information such as academic frontiers is mainly pushed; while for trainee doctors or residents, summary information of corresponding treatment plans is pushed based on diagnosis and treatment guidelines. The pushed summary information includes the associated treatment plan and attached examination information.

[0049] In the preferred method, during the doctor's diagnosis and treatment process, the cloud platform dynamically interacts with the user's query information, and performs dynamic intent recognition in the interactive query interaction to accurately push information related to the disease. In the optional method, the medical terminal is configured with an interactive query interface, and the cloud platform obtains candidate query words based on the query content, clicked web links, disease course diagnosis information, etc., and obtains corresponding information related to the disease.

[0050] In a preferred embodiment, the cloud platform constructs an association graph between user queries and clicked documents, uses the association graph to mine similarities between queries, obtains candidate expansion terms, and extracts features of clicked documents for each query as features of the query.

[0051] In a preferred manner, the cloud platform mines and expands candidate words based on the association relationship of historical query information. For example, based on historical query information, if two queries tend to click on the same network link corresponding to the treatment plan information, it can be confirmed that the two queries have similar meanings, and the query words can be expanded through historical queries.

[0052] In an exemplary manner, the cloud platform pushes the extracted diagnosis and treatment summary information to the medical terminal. The cloud platform further adjusts the weight value of the corresponding document based on the browsing time and dwell time of the diagnosis and treatment summary information clicked by the user terminal, and comprehensively selects the features of documents with different weight values ​​for expansion, so as to improve the efficiency and pertinence of pushing diagnosis and treatment information on the cloud platform.

[0053] In an exemplary manner, after the user logs into the system through the medical terminal, when entering medical record and treatment data, when the user enters the treatment information in the user terminal system input interface, the system automatically captures the corresponding key fields and diagnosis information, stores and sends it to the in-hospital server. The in-hospital server feeds back the corresponding diagnosis and treatment specifications to the medical terminal based on the diagnosis information, and performs auxiliary verification of the patient's main statement.

[0054] For example, when a patient has a history of drug allergy, the drug and treatment process will be automatically verified and warned during diagnosis and treatment. When there is a conflict in the doctor's medication, a direct message prompt warning will be sent.

[0055] Optionally, the diagnosis and treatment specifications in the hospital server are synchronized with the database in the cloud platform. Different early warning trigger mechanisms are configured according to the attribute information of the doctor, that is, the diagnosis and treatment plan of the trainee doctor is synchronized with the treatment of the diagnosis and treatment standard guide. When the similarity deviates from the preset value, a secondary verification is performed and the corresponding treatment plan is pushed to the department management terminal for verification.

[0056] The comparison of the deviation value of the similarity can be, in a preferred manner, a text matching process of the diagnosis and treatment plan, extracting the keyword fields in the treatment plan, such as medication category, key process of the treatment plan, medication dosage, etc., and matching them by category. An early warning mechanism is triggered based on the size of the text similarity. Optionally, the similarity can be calculated using a cosine similarity algorithm.

[0057] In one embodiment, the features related to the method steps can be implemented by a computer device / or system provided by the present invention, and the computer device / system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any one of the methods in the above embodiments is implemented.

[0058] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0059] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0060] In several embodiments provided by the present invention, it should be understood that the disclosed device can be implemented in other ways.

[0061] The present invention also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program can be executed when it is run. Figure 1 The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. The storage medium may also include a non-volatile memory or a non-transitory memory, etc.

[0062] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means.

[0063] The embodiments of the present invention are described in detail above. The present invention is described in detail using specific implementation methods herein. The description of the above embodiments is only used to help understand the method and system of the present invention. It is only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should belong to the scope of protection of the present invention, and the content of this specification should not be understood as limiting the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A medical information processing system based on a cloud platform, characterized in that: The system includes a user terminal, an in-hospital server and a cloud platform, wherein the user terminal, the in-hospital server and the cloud platform are connected via a network, and user terminals in the same hospital are connected to the cloud platform via a unified interface of the in-hospital server. The hospital server stores the diagnosis and treatment information of the hospital. The diagnosis and treatment information of the hospital is annotated by multiple types of indexes. The diagnosis and treatment information is connected to the cloud platform in an authorized sharing manner. The cloud platform obtains the diagnosis and treatment information input by the user terminal based on the authorization information of the user terminal, and pushes the treatment suggestion information to the user terminal in real time. The treatment suggestion information is displayed on the sub-interface of the user terminal interface; the user terminal selects the suggestion information and inputs it to generate a diagnosis and treatment information plan by itself, and matches and verifies the diagnosis and treatment information plan submitted by the user terminal with the diagnosis and treatment guideline specifications of the cloud platform, and determines whether to push the pending confirmation message based on the verification result.

2. The system according to claim 1, characterized in that: The diagnosis and treatment information plan submitted by the user terminal is matched and verified with the diagnosis and treatment guideline specifications of the cloud platform, including: obtaining the diagnosis subject type, extracting the drug dosage information in the diagnosis and treatment information plan, and when it exceeds the preset value, performing a search association verification based on the attribute information of the user corresponding to the user terminal.

3. The system according to claim 2, characterized in that: Search association verification is performed based on the attribute information of the user corresponding to the user terminal, including: when the user's attribute information is an expert attribute, a search for related academic literature is triggered in the cloud platform background, and according to the authorization rules between hospitals, the historical diagnosis and treatment information schemes between corresponding hospitals are accessed through the cloud platform. When the number of search results is higher than the preset value, the current diagnosis and treatment information scheme is verified to be true and stored in the cloud platform database; if the number of search results is lower than the preset value, a confirmation message is sent to the corresponding user terminal. When the feedback information obtained is true, the diagnosis and treatment information scheme is marked as true and stored in the cloud platform database.

4. The system according to claim 2, characterized in that: Search association verification is performed based on the attribute information of the user corresponding to the user terminal, including: when the user's attribute level is low, a message push is directly triggered, and the message push includes at least information on diagnosis and treatment guideline specifications, and the information of the current diagnosis and treatment information plan is marked, and pending confirmation information is sent to require user confirmation.

5. The system of claim 4, further characterized in that: Obtain the diagnosis and treatment information input by the user terminal, and push the treatment suggestion information to the user terminal in real time, including: extracting the medical experience input by the user terminal to form structured information, the cloud platform adaptively performs matching search based on the structured information, and generates summary information of the diagnosis and treatment plan corresponding to the structured information, and pushes it to the corresponding sub-interface of the user terminal.

6. The system of claim 5, further characterized in that: Obtaining diagnosis and treatment information input by the user terminal, and pushing treatment suggestion information to the user terminal in real time, also includes: the cloud platform sets different weighted values ​​according to the user attributes of different user terminals and the attributes of the diagnosis and treatment hospital, and jointly recommends treatment information.

7. The system of claim 6, further characterized in that: The cloud platform sets different weighting values ​​according to the user attributes of different treating doctors and the attributes of the treating hospitals, and jointly recommends treatment information, further including: the cloud platform comprehensively accesses the user's knowledge structure background, and pushes the related diagnosis and treatment information plan in the form of summary information in a substitute search manner.

8. The system of claim 7, further characterized in that: Obtaining diagnosis and treatment information input by a user terminal, and pushing treatment suggestion information to the user terminal in real time, also includes: displaying a link to the search reasoning process in the sub-interface for pushing summary information, and displaying the key steps of the search reasoning process in the form of diagrams and text descriptions to the user terminal in the page corresponding to the link to the search reasoning process.

9. The system of claim 8, further characterized in that: The cloud platform obtains query information during the process of user terminal inputting diagnosis and treatment information, and performs dynamic interaction with the cloud platform. During the query interaction, dynamic intent recognition is performed and diagnosis and treatment related information is pushed.

10. The system of claim 9, further characterized in that: Dynamic intent recognition is performed in query interaction, including: the cloud platform constructs an association graph between user queries and clicked documents, uses the association graph to mine similarities between queries, obtains candidate expansion words, and extracts features of clicked documents for each query as features of the query.

Images