Classification Method, Device and System for Information Related to Treatment of Sleep Disorders

Abstract

The present invention discloses a method, a system and a system for classifying information related to sleep disorders. Information is extracted from the materials provided by the user and organized into a structured data list. According to the historical user data set and the information database, the association relationships co-occurring in each disease are obtained through Bayesian structure learning, a Bayesian network structure is constructed, the pre- and post-order diseases belonging to the same type are aggregated in the Bayesian network to obtain the corresponding disease classification, and a corresponding strategy plan is formed according to the expert experience knowledge graph to output the analysis result to the user. Based on Bayesian structure learning, the present invention extracts information from materials such as user medical records and performs structured processing, combines the historical data set and the information database to obtain the association relationships of each disease, and forms a corresponding reference strategy plan in combination with the expert experience knowledge graph, which can become an important reference information for doctors to assist in judgment and save processing time.

Description

[0001] This application is a divisional application of a Chinese invention patent application with an application date of July 14, 2021, an application number of CN20210792815.8, and an invention title of "Information Classification Method, Device and System Based on Bayesian Structure Learning". Technical Field

[0002] The present invention relates to the field of artificial intelligence technology, and in particular, to a method, device and system for classifying information related to the treatment of sleep disorders. Background Art

[0003] The classification and analysis of diseases is an essential step in many scenarios. Currently, the classification of diseases mainly relies on manual judgment. The uneven professional capabilities of professionals lead to chaotic classification. For example, the classification of a certain disease may be inaccurate due to insufficient medical expertise. For example, there are many causes of cancer, and doctors may have different descriptions of thyroid cancer when issuing a diagnosis certificate, such as thyroid mass, thyroid malignant tumor, thyroid papillary malignant tumor, etc. These description methods correspond to certain specific periods or specific types of thyroid cancer, but if the professional quality is insufficient, it is easy to cause classification errors. This classification difficulty is more obvious in mental diseases. Therefore, it is necessary to assist in reasonable disease classification through a data-driven method to improve the reliability of auxiliary reference. Summary of the Invention

[0004] Aiming at the above defects, the technical problem to be solved by the present invention is how to use scientific and technological means to solve the data analysis and classification problem of sleep disorders.

[0005] Aiming at the above defects, the purpose of the present invention is to provide a method, system, electronic device, computer storage medium and program product for classifying information related to the treatment of sleep disorders.

[0006] According to one aspect of the embodiments of the present specification, a method for classifying information related to the treatment of sleep disorders is provided. Information is extracted from the materials provided by the user and organized into a structured data list. The co-occurrence association relationships of each disease are obtained through Bayesian structure learning based on the historical user dataset and the information database, a Bayesian network structure is constructed, the pre- and post-order diseases belonging to the same type are aggregated in the Bayesian network to obtain the corresponding disease classification, and a corresponding policy plan is formed according to the expert experience knowledge graph and the analysis result is output to the user.

[0007] In some embodiments, the Bayesian network structure has multiple nodes, the nodes correspond to random variables, and the edges correspond to the dependence or correlation relationships of the random variables.

[0008] In some embodiments, the edges include directed edges and undirected edges.

[0009] In some embodiments, the node includes a random factor or inducement that causes sleep disorders.

[0010] In some embodiments, a directed edge represents a unidirectional dependency, and an undirected edge represents a correlative dependency relationship.

[0011] In some embodiments, structure learning, given a network and static slice samples of each node, finds the optimal network structure, thereby using the conditional independence of the Bayesian network to explain the causal relationship between nodes.

[0012] According to one aspect of the embodiments of the present specification, there is provided a method for classifying information related to the treatment of sleep disorders, which is applied to an Internet medical platform and includes:

[0013] Receiving a user request, performing structured processing on the materials provided by the user and extracting information to form a structured data list, obtaining the correlation relationship of co-occurring diseases of the user through Bayesian structure learning based on the historical database and the user's information, constructing a Bayesian network structure, aggregating the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and forming a corresponding policy solution according to the expert experience knowledge graph to output the analysis result to the user.

[0014] In some embodiments, the Internet medical platform performs Bayesian structure learning based on the collected historical data, learns the probability of co-occurrence of disease combinations in the disease list, constructs a Bayesian network structure, finds the optimal network structure, and uses the conditional independence of the Bayesian network to explain the causal relationship between nodes.

[0015] In some embodiments, greedy search is used to find the optimal solution to avoid falling into a local optimum.

[0016] In some embodiments, the specific process of finding the optimal solution includes:

[0017] S1. Select an initial structure;

[0018] S2. When the local optimum is not reached or the maximum number of steps is not reached, change all possible structures;

[0019] S3. Update the score of the corresponding node. If the score increases, use the adjacent structure as the alternative structure for the next step;

[0020] S4. If the alternative structure is empty, among all alternative structures, select the structure with the largest increase in score as the current structure. Otherwise, it is determined that the local optimum has been reached, and the current structure is returned;

[0021] S5. Execute S1 to S4 until all structures are traversed.

[0022] According to another aspect of the embodiments of the present specification, there is provided a method for classifying disease cause information based on Bayesian structure learning, including:

[0023] The user provides materials of symptoms, medical history and examination information. The third-party Internet medical platform structures the materials and extracts information to organize them into a list of structured pathological data. According to the user's historical data and the relevant disease database established by the third-party Internet medical platform, through Bayesian structure learning, an association relationship of the co-occurrence of one or more diseases is obtained, a Bayesian network structure is constructed, the pre- and post-order diseases of the same type are aggregated in the Bayesian network to obtain corresponding disease classifications, and a corresponding policy solution is formed according to the expert experience knowledge graph and the analysis result is output to the user.

[0024] In some embodiments, the third-party Internet medical platform structures the materials through OCR and / or image recognition and / or semantic analysis to obtain data in a standard format.

[0025] In some embodiments, the Bayesian network structure has multiple nodes, and the nodes correspond to random variables.

[0026] According to another aspect of the embodiments of the present specification, there is provided a system for classifying information related to the treatment of sleep disorders, including: a user terminal and an Internet medical platform, wherein,

[0027] The user terminal is used for the user to provide materials, including but not limited to providing pictures, documents and standardized examination reports;

[0028] The Internet medical platform structures the materials and extracts information to organize them into a list of structured pathological data. According to the user's historical data and the relevant disease database established by the third-party Internet medical platform, through Bayesian structure learning, an association relationship of the co-occurrence of one or more diseases is obtained, and a Bayesian network structure is constructed;

[0029] The Internet medical platform aggregates the pre- and post-order diseases of the same type in the Bayesian network to obtain corresponding disease classifications, and forms a corresponding policy solution according to the expert experience knowledge graph and outputs the analysis result to the user through the user terminal.

[0030] In some embodiments, the third-party Internet medical platform structures the materials through the OCR, image recognition and semantic analysis function modules in the background to obtain data in a standard format.

[0031] According to another aspect of the embodiments of the present specification, there is provided an electronic device, including:

[0032] A processor; and

[0033] A memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations:

[0034] Receive a user request, perform structured processing on the materials provided by the user, extract information, form a structured data list, obtain the co-occurrence correlation relationships of user diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output the analysis result to the user.

[0035] According to another aspect of the embodiments of the present specification, there is provided a computer-readable storage medium having stored thereon a computer program / instructions that, when executed by a processor, implement the following steps: extract information from the materials provided by the user, organize it into a structured data list, obtain the co-occurrence correlation relationships of each disease through Bayesian structure learning based on the historical user dataset and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output the analysis result to the user.

[0036] According to another aspect of the embodiments of the present specification, there is provided a computer program product including a computer program / instructions, characterized in that the computer program / instructions, when executed by a processor, implement the following steps: extract information from the materials provided by the user, organize it into a structured data list, obtain the co-occurrence correlation relationships of each disease through Bayesian structure learning based on the historical user dataset and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output the analysis result to the user.

[0037] According to another aspect of the embodiments of the present specification, there is provided an electronic device, including:

[0038] A processor; and

[0039] A memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations:

[0040] Extract information from the materials provided by the user, organize it into a structured data list, obtain the co-occurrence correlation relationships of each disease through Bayesian structure learning based on the historical user dataset and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output the analysis result to the user.

[0041] According to another aspect of the embodiments of the present specification, there is provided a computer-readable storage medium, on which a computer program / instructions are stored, characterized in that when the computer program / instructions are executed by a processor, the following steps are implemented:

[0042] Receive a user request, perform structured processing on the materials provided by the user and extract information to form a structured data list, obtain the co-occurrence association relationship of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0043] According to another aspect of the embodiments of the present specification, there is provided a computer program product, including a computer program / instructions, characterized in that when the computer program / instructions are executed by a processor, the following steps are implemented:

[0044] Receive a user request, perform structured processing on the materials provided by the user and extract information to form a structured data list, obtain the co-occurrence association relationship of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0045] According to another aspect of the embodiments of the present specification, there is provided an electronic device, including:

[0046] A processor; and

[0047] A memory configured to store computer-executable instructions, and when the executable instructions are executed, the processor is caused to perform the following operations:

[0048] Receive a user request, perform structured processing on the materials provided by the user and extract information to form a structured data list, obtain the co-occurrence association relationship of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0049] Based on Bayesian structure learning, the present invention extracts information from materials such as user medical records and performs structured processing, combines historical data sets and information databases to obtain the association relationships of each disease, and forms corresponding reference strategy solutions in combination with an expert experience knowledge graph, which can become important reference information for doctors to assist in judgment and save processing time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly introduced below. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0051] Figure 1 FIG. shows a schematic structural diagram of an embodiment of the method for classifying information related to the treatment of sleep disorders according to the present invention;

[0052] Figure 2 FIG. shows a schematic structural diagram of another embodiment of the method for classifying information related to the treatment of sleep disorders according to the present invention;

[0053] Figure 3 FIG. shows a schematic structural diagram of another embodiment of the method for classifying information related to the treatment of sleep disorders according to the present invention;

[0054] Figure 4 FIG. shows a schematic architecture diagram of an embodiment of the system for classifying information related to the treatment of sleep disorders according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without some of these specific details. The following description of the embodiments is only provided to provide a better understanding of the present invention by showing examples of the present invention.

[0056] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0057] As Figure 1 shown, an information classification method related to the treatment of sleep disorders provided by an embodiment of this specification extracts information from materials provided by a user, organizes it into a structured data list, obtains the co-occurrence association relationships of each disease through Bayesian structure learning based on a historical user dataset and an information database, constructs a Bayesian network structure, aggregates the pre- and post-order diseases of the same type in the Bayesian network to obtain corresponding disease classifications, and forms a corresponding strategy plan according to an expert experience knowledge graph to output an analysis result to the user.

[0058] In some embodiments, the Bayesian network structure has multiple nodes, the nodes correspond to random variables, and the edges correspond to the dependencies or correlations of the random variables.

[0059] In some embodiments, the edges include directed edges and undirected edges.

[0060] In a specific example, the nodes include random factors or incentives that cause sleep disorders.

[0061] In some embodiments, the directed edges represent one-way dependencies, and the undirected edges represent correlation dependencies.

[0062] In some embodiments, structure learning gives a network and static slice samples of each node, and finds the optimal network structure, so as to explain the causal relationship between nodes with the conditional independence of the Bayesian network.

[0063] Another information classification method related to the treatment of sleep disorders provided by an embodiment of this specification is applied to an Internet medical platform and includes:

[0064] Upon receiving a user request, structured processing is performed on the materials provided by the user, information is extracted, a list of structured data is formed, the associated relationships of co-occurring diseases of the user are obtained through Bayesian structure learning based on the historical database and the user's information, a Bayesian network structure is constructed, the pre- and post-order diseases belonging to the same type are aggregated in the Bayesian network to obtain the corresponding disease classification, and a corresponding strategy plan is formed according to the expert experience knowledge graph to output the analysis result to the user.

[0065] In some embodiments, the Internet medical platform performs Bayesian structure learning based on the collected historical data, learns the probability of co-occurrence of disease combinations in the disease list, constructs a Bayesian network structure, finds the optimal network structure, and uses the conditional independence of the Bayesian network to explain the causal relationship between nodes.

[0066] In a specific example, greedy search is used to find the optimal solution to avoid falling into a local optimum.

[0067] As Figure 2 shown, in a specific example, the specific process of finding the optimal solution includes:

[0068] S1. Select an initial structure;

[0069] S2. When the local optimum is not reached or the maximum number of steps is not reached, make changes to all possible structures;

[0070] S3. Update the scores of the corresponding nodes. If the score increases, use the adjacent structure as the alternative structure for the next step;

[0071] S4. If the alternative structure is empty, among all alternative structures, select the structure with the largest increase in score as the current structure. Otherwise, it is determined that the local optimum has been reached, and the current structure is returned;

[0072] S5. Execute S1 to S4 until all structures are traversed.

[0073] As Figure 3 shown, another embodiment of this specification provides a method for classifying information related to sleep disorders, including:

[0074] The user provides materials of symptoms, medical history, and examination information. The third-party Internet medical platform performs structured processing on the materials, extracts information, and organizes it into a list of structured pathological data. Based on the user's historical data and the relevant disease database established by the third-party Internet medical platform, the associated relationships of one or more co-occurring diseases are obtained through Bayesian structure learning, a Bayesian network structure is constructed, the pre- and post-order diseases belonging to the same type are aggregated in the Bayesian network to obtain the corresponding disease classification, and a corresponding strategy plan is formed according to the expert experience knowledge graph to output the analysis result to the user.

[0075] In some embodiments, a third-party Internet medical platform performs structured processing on materials through OCR and / or image recognition and / or semantic analysis to obtain data in a standard format.

[0076] In some embodiments, a Bayesian network structure has multiple nodes, and the nodes correspond to random variables.

[0077] As Figure 4 shown, a system for classifying information related to sleep disorders provided by another embodiment of this specification includes: a user terminal and an Internet medical platform, where

[0078] the user terminal is used for the user to provide materials, including but not limited to providing pictures, documents, and standardized inspection reports;

[0079] the Internet medical platform performs structured processing on the materials and extracts and organizes the information into a list of structured pathological data. According to the historical data of the user and the relevant disease database established by the third-party Internet medical platform, one or more co-occurrence association relationships of diseases are obtained through Bayesian structure learning, and a Bayesian network structure is constructed;

[0080] the Internet medical platform aggregates the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and forms a corresponding policy solution according to the expert experience knowledge graph and outputs the analysis result to the user through the user terminal.

[0081] In some embodiments, a third-party Internet medical platform performs structured processing on materials through the OCR, image recognition, and semantic analysis function modules in the background to obtain data in a standard format.

[0082] In a specific example, the Internet medical platform can be a comprehensive Internet health medicine and medical platform, such as Ali Health and JD Health, or a medical health consultation platform dedicated to medical services, such as Chunyu Doctor and Dingxiangyuan, or a specialized medical platform, such as the Good Mood Mobile Medical, a professional mobile medical platform focusing on the central nervous system field.

[0083] According to an embodiment of another aspect, a computer-readable storage medium is further provided, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the following steps are implemented:

[0084] Extract information according to the materials provided by the user, organize it into a list of structured data, obtain the co-occurrence association relationships of each disease through Bayesian structure learning according to the historical user data set and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph and output the analysis result to the user.

[0085] According to an embodiment of another aspect, there is also provided a computer program product including a computer program / instructions, which when executed by a processor, implement the following steps:

[0086] Extract information from the materials provided by the user, organize it into a structured data list, obtain the co-occurrence association relationships of each disease through Bayesian structure learning based on the historical user data set and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0087] According to another aspect of the embodiments of the present specification, there is also provided an electronic device, including:

[0088] A processor; and

[0089] A memory configured to store computer-executable instructions, and the executable instructions, when executed, cause the processor to perform the following operations:

[0090] Extract information from the materials provided by the user, organize it into a structured data list, obtain the co-occurrence association relationships of each disease through Bayesian structure learning based on the historical user data set and the information database, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0091] According to another aspect of the embodiments of the present specification, there is also provided a computer-readable storage medium having stored thereon a computer program / instructions, which when executed by a processor, implement the following steps:

[0092] Receive a user request, perform structured processing on the materials provided by the user and extract information to form a structured data list, obtain the co-occurrence association relationships of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution according to the expert experience knowledge graph to output an analysis result to the user.

[0093] According to another aspect of the embodiments of the present specification, there is provided a computer program product including a computer program / instructions, which when executed by a processor, implement the following steps:

[0094] Upon receiving a user request, perform structured processing on the materials provided by the user, extract information, form a list of structured data, obtain the co-occurrence correlation relationships of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution based on the expert experience knowledge graph to output the analysis result to the user.

[0095] According to another aspect of the embodiments of the present specification, there is provided an electronic device, including:

[0096] A processor; and

[0097] A memory configured to store computer-executable instructions, and when the executable instructions are executed, the processor performs the following operations:

[0098] Upon receiving a user request, perform structured processing on the materials provided by the user, extract information, form a list of structured data, obtain the co-occurrence correlation relationships of the user's diseases through Bayesian structure learning based on the historical database and the user's information, construct a Bayesian network structure, aggregate the pre- and post-order diseases of the same type in the Bayesian network to obtain the corresponding disease classification, and form a corresponding policy solution based on the expert experience knowledge graph to output the analysis result to the user.

[0099] In some embodiments, the Internet medical platform performs Bayesian structure learning based on the collected historical data, learns the probability of co-occurrence of disease combinations in the disease list, constructs a Bayesian network structure, finds the optimal network structure, and uses the conditional independence of the Bayesian network to explain the causal relationship between nodes.

[0100] Use greedy search to find the optimal solution and avoid falling into local optima.

[0101] In some embodiments, the specific process of finding the optimal solution includes:

[0102] S1. Select an initial structure;

[0103] S2. When the local optimum is not reached or the maximum number of steps is not reached, make changes to all possible structures;

[0104] S3. Update the scores of the corresponding nodes. If the score increases, use the adjacent structure as the alternative structure for the next step;

[0105] S4. If the alternative structure is empty, among all alternative structures, select the structure with the largest increase in score as the current structure. Otherwise, it is determined that the local optimum has been reached, and return the current structure;

[0106] S5. Execute S1 - S4 until all structures are traversed.

[0107] The third-party Internet medical platform performs structured processing on the materials through OCR and / or image recognition and / or semantic analysis to obtain data in a standard format.

[0108] In some embodiments, the Bayesian network structure has multiple nodes, and the nodes correspond to random variables.

[0109] Based on Bayesian structure learning, the present invention extracts information from materials such as user medical records and then performs structured processing, combines the historical data set and the information database to obtain the association relationship of each disease, and combines the expert experience knowledge graph to form a corresponding reference strategy plan, which can become an important reference for doctors to assist in judgment and save processing time.

[0110] For the convenience of description, when describing the above device, it is divided into various units according to functions and described separately. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0111] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 a block or multiple blocks.

[0113] The present application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

[0114] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the flowchart Figure 1 one or more of the flowcharts and / or boxes Figure 1 specified in the box or boxes.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in the flowchart Figure 1 one or more of the flowcharts and / or boxes Figure 1 specified in the box or boxes.

[0116] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0117] Memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0118] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media do not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0119] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0120] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0121] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for classifying information related to sleep disorders, which sorts the materials of sleep disorder symptoms, medical history, and examination information provided by users into a structured data list, obtains the co-occurrence association relationships of sleep disorders through Bayesian structure learning based on the historical user dataset and the information database, constructs a Bayesian network structure, aggregates the pre- and post-order sleep disorders of the same type in the Bayesian network to obtain the corresponding sleep disorder classification, forms a corresponding strategy plan according to the expert experience knowledge graph, outputs the analysis results to the user, searches for the optimal solution, avoids falling into a local optimum, selects an initial structure, and makes changes to all possible structures when the local optimum is not reached or the maximum number of steps is not reached; Update the scores of the corresponding nodes. If the score increases, use the adjacent structures as the alternative structures for the next step. If the alternative structures are empty, among all the alternative structures, select the structure with the largest increase in score as the current structure. Otherwise, it is determined that the local optimum has been reached, and return the current structure; Traverse all structures; specifically including: Use greedy search to find the optimal solution and avoid falling into the local optimum. The specific process includes: S1. Select an initial structure; S2. When the local optimum has not been reached or the maximum number of steps has not been reached, make changes to all possible structures; S3. Update the scores of the corresponding nodes. If the score increases, use the adjacent structures as the alternative structures for the next step; S4. If the alternative structures are empty, among all the alternative structures, select the structure with the largest increase in score as the current structure. Otherwise, it is determined that the local optimum has been reached, and return the current structure; S5. Execute S1 to S4 until all structures have been traversed.

2. The method for classifying information related to sleep disorder treatment according to claim 1, wherein the Bayesian network structure has multiple nodes, the nodes correspond to random variables, and the edges correspond to the dependencies or correlations of the random variables.

3. The method for classifying information related to sleep disorder treatment according to claim 2, wherein the edges include directed edges and undirected edges.

4. The method for classifying information related to sleep disorder treatment according to claim 2, wherein the nodes include random factors or incentives that cause sleep disorders.

5. The method for classifying information related to sleep disorder treatment according to claim 3, wherein the directed edges represent one-way dependencies, and the undirected edges represent correlated dependencies.

6. The method for classifying information related to sleep disorder treatment according to claim 5, wherein the structure learning, given a network and static slice samples of each node, finds the optimal network structure, so as to explain the causal relationship between nodes using the conditional independence of the Bayesian network.

7. A classification system for information related to treating sleep disorders, comprising: A user terminal and an Internet medical platform, wherein, The user terminal is used to provide materials on sleep disorder symptoms, medical history, and examination information provided by the user, including but not limited to providing pictures, documents, and standardized examination reports; The Internet medical platform performs structured processing on the materials, extracts information, and organizes it into a structured pathological data list. According to the user's historical data and the sleep disorder database established by a third-party Internet medical platform, the association relationships of co-occurring sleep disorders are obtained through Bayesian structure learning, and a Bayesian network structure is constructed; The Internet medical platform aggregates the pre- and post-order sleep disorders of the same type in the Bayesian network to obtain the corresponding sleep disorder classification, and forms a corresponding strategy plan according to the expert experience knowledge graph, and outputs the analysis result to the user through the user terminal; specifically including: Use greedy search to find the optimal solution and avoid falling into the local optimum. The specific process includes: S1. Select an initial structure; S2. When the local optimum has not been reached or the maximum number of steps has not been reached, make changes to all possible structures; S3. Update the scores of the corresponding nodes. If the score increases, use the adjacent structures as the alternative structures for the next step; S4. If the alternative structure is empty, among all alternative structures, select the structure with the largest increase in score as the current structure; otherwise, it is determined that the local optimum has been reached and the current structure is returned. S5. Execute S1 - S4 until all structures are traversed.

8. The system according to claim 7, wherein the third-party Internet medical platform performs structured processing on the materials through the OCR, image recognition, and semantic analysis function modules in the background to obtain data in a standard format.

9. A computer-readable storage medium having computer programs / instructions stored thereon, characterized in that, When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 - 6 are implemented.

10. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 - 6 are implemented.

Images