A general method, device, electronic device and storage medium for reporting a single disease

Abstract

The present application relates to a general method, device, electronic device and storage medium for reporting a single disease, the method comprising: obtaining a rule text and a pre-set rule file; splitting the pre-set rule file to obtain the precondition of each sub-rule and the postcondition of each sub-rule; sequentially processing the rule text corresponding to the precondition of the sub-rule to obtain multiple processing results; regularizing the multiple processing results to obtain multiple regularized processing results; determining the processing result corresponding to the precondition of the sub-rule according to the postcondition of the sub-rule and the multiple regularized processing results; and synthesizing the processing results corresponding to the precondition of each sub-rule to obtain options for reporting a single disease. The present application can efficiently and quickly locate the keywords / words in the rule text through the rule file, thereby providing the correct options for reporting a single disease, making up for the inaccurate prediction of the model due to capacity bottlenecks, insufficient data and other reasons.

Description

Technical Field

[0001] The present application relates to the technical field of single disease reporting, and in particular to a general method, device, electronic device and storage medium for reporting a single disease. Background Art

[0002] Single disease reporting is of great significance to improving the level of medical service supervision and ensuring patient safety. In this task, we need to extract key information from the hospital's medical record data to select answers to corresponding disease questions, such as obtaining information on whether the patient has a "smoking history" from the "past medical history". The current method is mainly machine learning models, such as using reading comprehension models to judge options.

[0003] The number of questions and options involved in reporting a single disease is large. It is resource-consuming to formulate a set of rule scripts for each question option, which is not very meaningful. The medical record data is too long and complicated, and the neural network cannot learn key information, resulting in inaccurate model prediction. The amount of available data is small and there is an imbalance in the distribution of options, which easily leads to the inability to fit the model. Summary of the invention

[0004] Based on the above problems, the present application provides a general method for reporting a single disease, an electronic device and a storage medium.

[0005] In a first aspect, the present application provides a general method for reporting a single disease, including:

[0006] Get the rule text and pre-set rule files;

[0007] Split the pre-set rule file to obtain the preconditions of each sub-rule and the postconditions of each sub-rule;

[0008] The rule text is processed in sequence according to the preconditions of the sub-rules to obtain multiple processing results;

[0009] Regularizing the multiple processing results to obtain multiple regularized processing results;

[0010] Determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and multiple regularization processing results;

[0011] The options for reporting problems of a single disease are obtained by combining the processing results corresponding to the preconditions of each sub-rule.

[0012] Furthermore, in the above-mentioned general method for reporting a single disease, the rule file at least includes:

[0013] R: Regular match of keywords, words, and formats, y: returns true if the match is successful, n: returns false if the match fails;

[0014] N: Search for numbers in the preset format, y: Return True if the search is successful, n: Return false if the search fails;

[0015] NC: Find a number in a fixed format and compare it with the standard value to get the comparison result, and judge whether the comparison result meets the comparison condition. y: If the comparison condition is met, it returns True, n: If the comparison condition is not met, it returns false;

[0016] C: Extract the specified text fragment and return the extracted text;

[0017] S: segment the text according to keywords and words, and return the segmented text;

[0018] Re: Replace the specified content in the text and return the replaced text.

[0019] Furthermore, in the above-mentioned general method for reporting a single disease, the preconditions of the sub-rules include: R, N, NC, C, S and Re; the post-conditions of the sub-rules include: 0 / 1 / y / n.

[0020] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is segmented to obtain the first letter of the rule text, including:

[0021] The rule text is segmented according to the symbols in the middle of the rule text.

[0022] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is processed in sequence according to the preconditions of the sub-rules to obtain multiple processing results; at least including:

[0023] If the precondition is R, regular matching of keywords, words, and formats is performed on the rule text;

[0024] If the precondition is N, search for numbers in the preset format;

[0025] If the precondition is NC, find the number in the fixed format and compare it with the standard value;

[0026] If the precondition is C, extract the required text fragment;

[0027] If the precondition is S, the rule text is segmented according to keywords and words;

[0028] If the precondition is Re, replace the specified content in the rule text.

[0029] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is processed in sequence corresponding to the preconditions of the sub-rules to obtain multiple processing results, which also includes: determining the corresponding processing method.

[0030] Furthermore, in the above-mentioned general method for reporting a single disease, determining the corresponding processing method includes:

[0031] Segment the rule text to obtain multiple first letters of the rule text;

[0032] The preconditions of the sub-rules are determined according to the first letters of the rule text, and the processing methods corresponding to the preconditions of the sub-rules are determined according to the corresponding relationships among the preconditions of the sub-rules.

[0033] In a second aspect, the embodiment of the present application further provides a general device for reporting a single disease, including:

[0034] Acquisition module: used to obtain rule text and pre-set rule files;

[0035] Segmentation module: used to segment the preset rule file to obtain the preconditions and postconditions of each sub-rule;

[0036] The first processing module is used to process the rule text in accordance with the preconditions of the sub-rules in sequence to obtain multiple processing results;

[0037] The second processing module is used for regularizing the multiple processing results to obtain multiple regularized processing results;

[0038] Determination module: used to determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and multiple regularization processing results;

[0039] Get module: It is used to obtain the options for reporting problems of a single disease by integrating the processing results corresponding to the preconditions of each sub-rule.

[0040] In a third aspect, an embodiment of the present application further provides an electronic device, characterized in that it includes: a processor and a memory;

[0041] The processor is used to execute the above-mentioned general method for reporting a single disease by calling the program or instruction stored in the memory.

[0042] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a program or instruction, and the program or instruction enables the computer to implement the above-mentioned general method for reporting a single disease.

[0043] The advantages of the embodiments of the present application are: the present application relates to a general method, device, electronic device and storage medium for reporting a single disease, the method comprising: obtaining a rule text and a pre-set rule file; splitting the pre-set rule file to obtain the preconditions of each sub-rule and the postconditions of each sub-rule; sequentially processing the rule text corresponding to the preconditions of the sub-rules to obtain multiple processing results; regularizing the multiple processing results to obtain multiple regularized processing results; determining the processing results corresponding to the preconditions of the sub-rules according to the postconditions of the sub-rules and the multiple regularized processing results; and synthesizing the processing results corresponding to the preconditions of each sub-rule to obtain options for reporting single disease problems. The present application can efficiently and quickly locate the keywords / words in the rule text through the rule file, thereby giving the correct options for reporting single disease problems, making up for the inaccurate predictions of the model due to capacity bottlenecks, insufficient data and other reasons. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A general method for reporting a single disease provided in the embodiment of the present application is shown in FIG. Figure 1 ;

[0046] Figure 2 A general method for reporting a single disease provided in the embodiment of the present application is shown in FIG. Figure 2 ;

[0047] Figure 3 A schematic diagram of a general device for reporting a single disease provided in an embodiment of the present application;

[0048] Figure 4 It is a schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0051] Figure 1 A general method for reporting a single disease provided in the embodiment of the present application is shown in FIG. Figure 1 .

[0052] In a first aspect, the present application embodiment provides a general method for reporting a single disease, including six steps from S101 to S106:

[0053] S101: Obtain a rule text and a preset rule file.

[0054] Specifically, in an embodiment of the present application, a rule text and a pre-set rule file are obtained. The rule text may be a text such as an admission diagnosis and medical history, and the pre-set rule file may be a rule file formulated for question-options based on the labeled data.

[0055] S102: Split the preset rule file to obtain the precondition of each sub-rule and the postcondition of each sub-rule.

[0056] Specifically, in an embodiment of the present application, the preset rule file is segmented to obtain the preconditions of each sub-rule and the postconditions of each sub-rule, such as the preconditions R / N / NC / C / S / Re, the postconditions 0 / 1 / y / n, etc.

[0057] S103: Processing the rule text in accordance with the preconditions of the sub-rules in sequence to obtain multiple processing results.

[0058] Specifically, in the embodiment of the present application, if the precondition is R, regular matching of keywords, words, and formats is performed on the rule text; if the precondition is N, numbers in a preset format are searched; if the precondition is NC, numbers in a fixed format are searched and compared with standard values; if the precondition is C, the required text fragments are extracted; if the precondition is S, the rule text is segmented according to keywords and words; if the precondition is Re, the specified content in the rule text is replaced.

[0059] S104: Regularize the multiple processing results to obtain multiple regularized processing results.

[0060] Specifically, in the embodiment of the present application, after the rule text is processed in sequence corresponding to the preconditions of the sub-rules to obtain multiple processing results, the rule text is regularized to obtain multiple regularized processing results.

[0061] S105: Determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and multiple regularization processing results.

[0062] Specifically, in an embodiment of the present application, after regularization processing is performed on the rule text to obtain multiple regularization processing results, the processing results corresponding to the sub-rule preconditions are output according to the postconditions of each sub-rule, such as 0 / 1 / y / n.

[0063] S106: The processing results corresponding to the preconditions of each sub-rule are combined to obtain options for reporting problems of a single disease.

[0064] Specifically, in the embodiment of the present application, the options for reporting problems of a single disease are determined by comprehensively considering all rule matching results.

[0065] Furthermore, in the above-mentioned general method for reporting a single disease, the rule file at least includes:

[0066] R: Regular match of keywords, words, and formats, y: returns true if the match is successful, n: returns false if the match fails.

[0067] N: Search for numbers in the preset format, y: Returns True if the search is successful, n: Returns false if the search fails.

[0068] NC: Find a number in a fixed format and compare it with a standard value to get a comparison result, and then determine whether the comparison result meets the comparison condition. y: If the comparison condition is met, True is returned; n: If the comparison condition is not met, false is returned.

[0069] C: Extract the specified text fragment and return the extracted text.

[0070] S: Split text according to keywords and words, and return the segmented text.

[0071] Re: Replace the specified content in the text and return the replaced text.

[0072] Specifically, in the embodiment of the present application, the above-mentioned rule file is a rule file formulated for questions-options based on the annotation data, and can also be other rule files, and the protection scope of the present application is not limited thereto.

[0073] Furthermore, in the above-mentioned general method for reporting a single disease, the preconditions of the sub-rules include: R, N, NC, C, S and Re; the post-conditions of the sub-rules include: 0 / 1 / y / n.

[0074] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is segmented to obtain the first letter of the rule text, including:

[0075] The rule text is segmented according to the symbols in the middle of the rule text.

[0076] Exemplary: C_Admission diagnosis(.*)_1S_Negative_0R_(pulmonary nodules|asthma|emphysema|multiple pulmonary nodules)_y is divided according to the symbol “_” in the middle.

[0077] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is processed in sequence according to the preconditions of the sub-rules to obtain multiple processing results; at least including:

[0078] If the precondition is R, regular matching of keywords, words, and formats is performed on the rule text.

[0079] If the precondition is N, search for a number in a preset format.

[0080] If the precondition is NC, a number in a fixed format is searched and compared with the standard value.

[0081] If the precondition is C, extract the required text fragment.

[0082] If the precondition is S, the rule text is segmented according to keywords and words.

[0083] If the precondition is Re, replace the specified content in the rule text.

[0084] Furthermore, in the above-mentioned general method for reporting a single disease, the rule text is processed in sequence corresponding to the preconditions of the sub-rules to obtain multiple processing results, which also includes: determining the corresponding processing method.

[0085] Specifically, in the embodiment of the present application, the corresponding processing method is determined based on steps S201 to S202, which will be introduced below in conjunction with specific steps and examples.

[0086] Figure 2 A general method for reporting a single disease provided in the embodiment of the present application is shown in FIG. Figure 2 .

[0087] Furthermore, in the above-mentioned general method for reporting a single disease, determining the corresponding processing method includes two steps from S201 to S202:

[0088] S201: Segment the rule text to obtain a plurality of first letters of the rule text.

[0089] S202: determining a precondition of a sub-rule according to a plurality of first letters of the rule text, and determining a processing method corresponding to the precondition of the sub-rule according to a corresponding relationship of the precondition of the sub-rule.

[0090] For example: C_admission diagnosis (.*)_1S_denied_0R_(pulmonary nodules|asthma|emphysema|multiple pulmonary nodules)_y is segmented according to the symbol “_” in the middle to obtain the first letters C, S, R of the regular text.

[0091] The first letter C of the rule text corresponds to the precondition C, and the required text fragment is extracted; the first letter S of the rule text corresponds to the precondition S, and the rule text is segmented according to keywords and words; the first letter R of the rule text and the precondition R perform regular matching of keywords, words, and formats on the rule text, output y, and return option c-respiratory diseases.

[0092] Figure 3 A schematic diagram of a general device for reporting a single disease provided in an embodiment of the present application.

[0093] In the second aspect, the embodiment of the present application also provides a general device for reporting a single disease, Figure 3 ,include:

[0094] Acquisition module 301: used to acquire rule text and preset rule files.

[0095] Specifically, in the embodiment of the present application, the acquisition module 301 acquires the rule text and the pre-set rule file. The rule text may be the text of the admission diagnosis, medical history, etc., and the pre-set rule file may be a rule file formulated for the question-options based on the labeled data.

[0096] Slicing module 302: used to slice the preset rule file to obtain the precondition of each sub-rule and the postcondition of each sub-rule.

[0097] Specifically, in an embodiment of the present application, the segmentation module 302 is used to segment the preset rule file to obtain the preconditions of each sub-rule and the postconditions of each sub-rule, such as the preconditions R / N / NC / C / S / Re, the postconditions 0 / 1 / y / n, etc.

[0098] The first processing module 303 is used to sequentially process the rule text corresponding to the preconditions of the sub-rules to obtain multiple processing results.

[0099] Specifically, in the embodiment of the present application, the first processing module 303 is used to perform regular matching of keywords, words, and formats on the rule text if the precondition is R; to search for numbers in a preset format if the precondition is N; to search for numbers in a fixed format and compare them with standard values ​​if the precondition is NC; to extract required text fragments if the precondition is C; to segment the rule text according to keywords and words if the precondition is S; and to replace specified content in the rule text if the precondition is Re.

[0100] The second processing module 304 is used for regularizing the multiple processing results to obtain multiple regularized processing results.

[0101] Specifically, in the embodiment of the present application, the second processing module 304 is used to perform processing corresponding to the preconditions of the sub-rules on the rule text in sequence to obtain multiple processing results, and then perform regularization processing on the rule text to obtain multiple regularization processing results.

[0102] Determination module 305: used to determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and multiple regularization processing results.

[0103] Specifically, in an embodiment of the present application, the determination module 305 is used to perform regularization processing on the rule text to obtain multiple regularization processing results, and then determine the processing result corresponding to the sub-rule precondition according to the postcondition of each sub-rule, such as 0 / 1 / y / n.

[0104] Obtaining module 306: is used to obtain the option of reporting a single disease type problem by integrating the processing results corresponding to each sub-rule precondition.

[0105] Specifically, in the embodiment of the present application, module 306 is used to comprehensively analyze all rule matching results to determine the option of reporting a single disease type problem.

[0106] In a third aspect, an embodiment of the present application further provides an electronic device, characterized in that it includes: a processor and a memory;

[0107] The processor is used to execute the above-mentioned general method for reporting a single disease by calling the program or instruction stored in the memory.

[0108] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a program or instruction, and the program or instruction enables the computer to implement the above-mentioned general method for reporting a single disease.

[0109] Figure 4 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure.

[0110] like Figure 4 As shown, the electronic device includes: at least one processor 401, at least one memory 402 and at least one communication interface 403. The various components in the electronic device are coupled together through a bus system 404. The communication interface 403 is used to transmit information between external devices. It can be understood that the bus system 404 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 404 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 4Various buses are labeled as bus system 404 .

[0111] It can be understood that the memory 402 in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0112] In some implementations, the memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system and application programs.

[0113] Among them, the operating system includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application program includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. A program that implements any method in a general method for reporting a single disease provided in an embodiment of the present application can be included in the application program.

[0114] In an embodiment of the present application, the processor 401 calls a program or instruction stored in the memory 402, specifically, a program or instruction stored in an application, and the processor 401 is used to execute the steps of each embodiment of a general method for reporting a single disease provided in an embodiment of the present application.

[0115] Get the rule text and pre-set rule files;

[0116] Split the pre-set rule file to obtain the preconditions of each sub-rule and the postconditions of each sub-rule;

[0117] The rule text is processed in sequence according to the preconditions of the sub-rules to obtain multiple processing results;

[0118] Regularizing the multiple processing results to obtain multiple regularized processing results;

[0119] Determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and multiple regularization processing results;

[0120] The options for reporting problems of a single disease are obtained by combining the processing results corresponding to the preconditions of each sub-rule.

[0121] Any method in a general method for reporting a single disease provided in an embodiment of the present application can be applied to the processor 401, or implemented by the processor 401. The processor 401 can be an integrated circuit chip having the ability to process signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 401 or instructions in the form of software. The above-mentioned processor 401 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0122] The steps of any method in a general method for reporting a single disease provided in an embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software units in a decoding processor. The software unit can be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402, and completes the steps of a general method for reporting a single disease in combination with its hardware.

[0123] Those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present application and to form different embodiments.

[0124] Those skilled in the art will appreciate that the description of each embodiment has its own emphasis, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A universal method for reporting a single disease. It is characterized in that include: Get the rule text and pre-set rule files; Splitting the preset rule file to obtain a precondition for each sub-rule and a postcondition for each sub-rule; Sequentially performing processing corresponding to the preconditions of the sub-rules on the rule text to obtain multiple processing results; Regularizing the multiple processing results to obtain multiple regularized processing results; Determine the processing result corresponding to the sub-rule pre-condition according to the sub-rule post-condition and the multiple regularization processing results; The processing results corresponding to the preconditions of each sub-rule are combined to obtain the options for reporting the problem of a single disease; The rule file at least includes: R: Regular match of keywords, words, and formats, y: returns true if the match is successful, n: returns false if the match fails; N: Search for numbers in the preset format, y: Return True if the search is successful, n: Return false if the search fails; NC: Find a number in a fixed format and compare it with a standard value to obtain a comparison result, and determine whether the comparison result meets the comparison condition. y: If the comparison condition is met, True is returned; n: If the comparison condition is not met, false is returned; C: Extract the specified text fragment and return the extracted text; S: segment the text according to keywords and words, and return the segmented text; Re: Replace the specified content in the text and return the replaced text; The preconditions of the sub-rules include: R, N, NC, C, S and Re; The post-conditions of the sub-rule include: 0 / 1 / y / n; The step of segmenting the rule text to obtain the first letter of the rule text includes: Segmenting the rule text according to symbols in the middle of the rule text; The processing of the rule text in sequence corresponding to the preconditions of the sub-rules to obtain multiple processing results at least includes: If the precondition is R, regular matching of keywords, words, and formats is performed on the rule text; If the precondition is N, search for numbers in the preset format; If the precondition is NC, find the number in the fixed format and compare it with the standard value; If the precondition is C, extract the required text fragment; If the precondition is S, the rule text is segmented according to keywords and words; If the precondition is Re, replace the specified content in the rule text; The step of sequentially performing the processing corresponding to the preconditions of the sub-rules on the rule text to obtain multiple processing results also includes: determining a corresponding processing method; The corresponding processing method for determining includes: Segmenting the rule text to obtain a plurality of first letters of the rule text; The preconditions of the sub-rules are determined according to the first letters of the rule text, and the processing methods corresponding to the preconditions of the sub-rules are determined according to the corresponding relationships among the preconditions of the sub-rules.

2. A general device for reporting a single disease, using the general method for reporting a single disease according to claim 1, It is characterized in that include: Acquisition module: used to obtain rule text and pre-set rule files; Slicing module: used for slicing the preset rule file to obtain the precondition of each sub-rule and the postcondition of each sub-rule; The first processing module is used to sequentially process the rule text corresponding to the preconditions of the sub-rules to obtain multiple processing results; A second processing module: used for regularizing the multiple processing results to obtain multiple regularized processing results; Determination module: used for determining the processing result corresponding to the precondition of the sub-rule according to the postcondition of the sub-rule and the multiple regularization processing results; Obtaining module: used to obtain the option of reporting a single disease type by comprehensively analyzing the processing results corresponding to the preconditions of each sub-rule.

3. An electronic device, It is characterized in that include: Processor and memory; The processor is used to execute the general method for reporting a single disease as described in claim 1 by calling the program or instruction stored in the memory.

4. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores programs or instructions, and the programs or instructions enable a computer to execute a general method for reporting a single disease as described in claim 1.

Images