Clinical medicine examination data classification system and method

Abstract

The invention provides a clinical medicine examination data classification system and method, and belongs to the technical field of data classification. The method comprises the following steps: S100, acquiring a to-be-classified clinical medical examination data set; s200, determining a data classification standard; and S300, classifying the clinical medical examination data set based on the determined data classification standard. The system comprises a man-machine interaction unit, a data acquisition unit, a data attribute identification unit, an interaction instruction analysis unit and a classification standard determination unit. According to the technical scheme of the invention, subjective requirements of users and objective attributes of the to-be-classified data can be fully considered during clinical medical examination data classification, so that classification standards can be determined more accurately; and the classification standard can be diversified, so that the later data screening requirement can be met, and the data utilization requirement of the user can be maximized, quickly, timely and quickly met.

Description

Technical Field

[0001] The present invention belongs to the technical field of data classification, and particularly relates to a clinical medical test data classification system and method, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device. Background Art

[0002] Clinical medical test data, as an important supporting technical discipline of medical science, plays an important role in the early diagnosis of diseases, condition monitoring, prognosis judgment, and risk assessment. With the improvement of the hospital's automation and modernization technology level, clinical medical test data has grown rapidly, accumulating a vast amount of data resources over time. Among them, there are a large number of known and unknown clinical-related laws, commercial laws, and data change laws, which can provide references for hospital medical research, personnel scheduling, drug procurement, etc. However, clinical medical test data not only has a huge volume and a wide variety of types, but also has characteristics such as high dimensionality and redundancy of features. Traditional data storage and statistical analysis methods are no longer sufficient to handle the increasingly large amount of clinical medical test data, and it is necessary to first perform targeted classification and screening processing on it.

[0003] Chinese Patent Application CN202211020064.9 proposes a clinical medical test data classification system and method based on big data analysis. By crawling a large amount of historical clinical medical test data to establish a data classification model, it realizes the automatic classification of clinical medical test data, without relying on manual labor, reducing the workload and time cost investment, improving the classification efficiency, and laying a foundation for the progress of the medical industry.

[0004] However, for a set of clinical medical test data, different user groups have different data utilization requirements, and different data utilization requirements correspond to different data classification and processing processes. For example, for the managers of hospital inspection departments, they need to statistically analyze the laboratory test data of their own departments on a weekly / monthly basis, including the number of tests, the number of patients tested, the peak test period, etc., so as to make early resource scheduling and personnel allocation for the next cycle of inspection work. For the managers of the hospital's entire data management department, they need to statistically analyze the number of hospital visits, drug usage record data, etc. of the entire hospital on a monthly / quarterly basis, including the number of times of using vital sign detection equipment, the number of cycles, the issued / consumed quantity of a certain drug, the number of patients with a certain disease, the peak drug usage period, the peak hospital visit period, the peak test period, etc. In other scenarios, for example, for internal or external researchers in the hospital, they may need to classify and compare data from different dimensions, such as classifying and screening the diagnosed disease types with the largest drug usage according to the drug usage amount, and classifying and screening the primary care doctors with the largest test volume according to the test volume.

[0005] The methods of the prior art determine the classification criteria based on the objective attributes of the data, without considering the subjective needs of users, and without placing subjective needs in a high-priority position, which may lead to the classification results not meeting the user's expectations, or the classification criteria not being within the user's expected range. In addition, the existing data classification methods usually only provide one classification criterion each time to perform a classification process. When the user's need is to compare the classification results under multiple-dimensional classifications to filter out target value data, multiple operations or manual operations are usually required, resulting in poor user experience, insufficient timely satisfaction of the need, slow response speed, and cumbersome process. Summary of the Invention

[0006] In view of the above technical problems, the present invention provides a clinical medical test data classification system and method, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device.

[0007] In the first aspect of the present invention, a clinical medical test data classification method is provided, and the method is applied to a human-computer interaction terminal;

[0008] The method includes the following steps:

[0009] S100: Obtain a set of clinical medical test data to be classified;

[0010] S200: Determine the data classification criteria;

[0011] S300: Classify the set of clinical medical test data based on the determined data classification criteria; wherein, the step S200 of determining the data classification criteria specifically includes:

[0012] S201: Determine the data source, data format, and data generation time range of the set of clinical medical test data to be classified;

[0013] S202: Analyze the human-computer interaction instructions input by the user through the human-computer interaction terminal;

[0014] S203: Determine the data classification criteria based on at least one of the data source, data format, data generation time range, and human-computer interaction instructions.

[0015] The set of clinical medical test data includes laboratory test data, vital sign monitoring data, and medication record data;

[0016] The data source includes the drug circulation process and the patient's visit process;

[0017] The data format includes text, image, and video frame.

[0018] The step S203 specifically includes:

[0019] S2031: Determine whether at least one classification criterion can be determined from the parsing result of the human-computer interaction instruction;

[0020] If so, proceed to step S2033;

[0021] Otherwise, proceed to step S2032;

[0022] S2032: Recommend at least one classification criterion based on the data source, data format, and data generation time range;

[0023] S2033: Receive the feedback result of the user on the at least one classification criterion;

[0024] S2034: Determine the data classification criterion based on the feedback result.

[0025] When the data classification criterion determined in step S203 includes at least a first classification criterion and a second classification criterion, step S300 further includes:

[0026] S301: Perform a first classification operation on the clinical medical test data set based on the determined first classification criterion to obtain a first classification result; perform a second classification operation on the clinical medical test data set based on the determined second classification criterion to obtain a second classification result;

[0027] S302: Compare the first classification result and the second classification result;

[0028] S303: Based on the comparison result, filter out the target subset of clinical medical test data.

[0029] The feedback result of the user on the at least one classification criterion in step S2033 includes:

[0030] When the at least one classification criterion includes only one classification criterion, determine whether a confirmation operation of the user is received within a preset time. If so, determine the feedback result; otherwise, proceed to step S2032.

[0031] The feedback result of the user on the at least one classification criterion in step S2033 includes:

[0032] When the at least one classification criterion includes at least two classification criteria,

[0033] If the at least two classification criteria are recommended based on step S2032, prompt the user to check at least one classification criterion, and confirm the feedback result based on the user's check operation;

[0034] If the at least two classification criteria are obtained based on the parsing in step S2031, determine whether a confirmation operation from the user is received within a preset time. If so, determine the feedback result; otherwise, return to step S202.

[0035] In a second aspect of the present invention, to implement the method in the first aspect, a clinical medical test data classification system is proposed. The system includes a human-computer interaction unit, a data acquisition unit, a data attribute recognition unit, an interaction instruction parsing unit, and a classification criterion determination unit.

[0036] The specific functions of each unit are as follows:

[0037] The data acquisition unit is used to acquire a set of clinical medical test data to be classified.

[0038] The data attribute recognition unit is used to recognize the data attributes of the set of clinical medical test data to be classified.

[0039] The interaction instruction parsing unit is used to parse the human-computer interaction instructions input by the user through the human-computer interaction unit.

[0040] The classification criterion determination unit is used to determine the data classification criteria based on the data attributes recognized by the data attribute recognition unit and / or the parsing result of the interaction instruction parsing unit for the human-computer interaction instructions.

[0041] The classification result output unit is used to output the classification result after classifying the set of clinical medical test data based on the data classification criteria.

[0042] Among them, the set of clinical medical test data includes laboratory test data, vital sign monitoring data, and medication record data.

[0043] The data attributes of the set of clinical medical test data to be classified include data source, data format, and data generation time range; the data source includes the drug circulation process and the patient visit process; the data format includes text, image, and video frame.

[0044] The system further includes a data screening unit.

[0045] When the data classification criteria determined by the classification criterion determination unit include at least a first classification criterion and a second classification criterion, activate the data screening unit.

[0046] The data screening unit screens out a target subset of clinical medical test data based on the classification result output by the classification result output unit.

[0047] The data screening unit screens out a target subset of clinical medical test data based on the classification result output by the classification result output unit, specifically including:

[0048] The classification result output unit performs a first classification operation on the set of clinical medical test data based on the determined first classification criterion to obtain a first classification result; and performs a second classification operation on the set of clinical medical test data based on the determined second classification criterion to obtain a second classification result.

[0049] The data screening unit compares the first classification result and the second classification result; and based on the comparison result, screens out a target subset of clinical medical test data.

[0050] The aforementioned clinical medical test data classification method can be automatically implemented through computer program instructions by various forms of electronic devices; the computer program instructions can be stored in different forms of storage media and loaded into computer electronic devices for execution.

[0051] Therefore, in the third aspect of the present invention, there is also provided a computer-readable storage medium for storing computer instructions, which when run on an electronic device, cause the electronic device to execute a clinical medical test data classification method according to the first aspect.

[0052] In the fourth aspect of the present invention, there is also provided a computer device, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the computer device executes a clinical medical test data classification method according to the aforementioned first aspect.

[0053] In the fifth aspect of the present invention, there is also provided a computer program product, which includes a computer program. When the computer program is executed, a clinical medical test data classification method according to the aforementioned first aspect is implemented.

[0054] The technical solution of the present invention can fully consider the subjective needs of users and the objective attributes of the data to be classified when classifying clinical medical test data, so as to more accurately determine the classification criteria; and the classification criteria can be diversified to meet the needs of subsequent data screening, enabling users to maximize the utilization of data and quickly and timely meet their needs.

[0055] The further advantages of the present invention will be further detailed in the specific embodiment part in combination with the accompanying drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0057] Figure 1 It is a schematic diagram of the main process of a method for classifying clinical medical test data according to an embodiment of the present invention.

[0058] Figure 2 is Figure 1 The specific implementation principle diagram for determining the data classification standard in the method.

[0059] Figure 3 is Figure 1 The schematic diagram of the human-computer interaction judgment process included in determining the data classification standard in the method.

[0060] Figure 4 It is a schematic diagram of the functional structure of a system for classifying clinical medical test data according to an embodiment of the present invention.

[0061] Figure 5 It is a schematic diagram of the functional structure of a system for classifying clinical medical test data according to another preferred embodiment of the present invention. Detailed implementation manners

[0062] First, it should be pointed out that Figures 1-3 The embodiments of the method for classifying clinical medical test data shown can be implemented through a computer program on an electronic device or system configured with a memory and a processor. The manifestation forms of the electronic device or system can be a physical machine, a virtual machine, a server, a cluster, or any combination thereof.

[0063] Preferably, the specific form of the electronic device can also be a human-computer interaction terminal, and the human-computer interaction terminal can be a desktop terminal with a human-computer interaction interface, a smart handheld terminal, a mobile terminal, etc.

[0064] First, refer to Figure 1 , Figure 1 It is a schematic diagram of the main process of a method for classifying clinical medical test data according to an embodiment of the present invention.

[0065] Figure 1 It shows that the method includes steps S100 - S300, and the specific implementation of each step is as follows:

[0066] S100: Obtain the set of clinical medical test data to be classified;

[0067] S200: Determine the data classification standard;

[0068] S300: Classify the clinical medical examination data set based on the determined data classification criteria.

[0069] Next, in combination with Figure 2 and Figure 3 , expand and explain each implementation step of Figure 1 the method.

[0070] Step S100: Obtain a clinical medical examination data set to be classified.

[0071] In specific implementation, the clinical medical examination data set includes laboratory test data, vital sign monitoring data, and medication record data.

[0072] Laboratory test data is mainly obtained through clinical test procedures. Clinical testing is to detect in vitro specimens (samples) such as a patient's blood, body fluids, secretions, excretions, and exfoliations through visual observation, physical, chemical, instrumental, or molecular biological methods, so as to provide valuable experimental data and relevant data for clinical practice and patients.

[0073] Schematic examples of laboratory test data include specimen (sample) name, specimen (sample) collection time, specimen (sample) submission time, specimen (sample) size (volume, quantity), test method, test result, etc. Due to the existence of different laboratories, different test procedures, and different test items, etc., laboratory test data is usually unstructured data.

[0074] Vital sign monitoring data is relevant monitoring data obtained by directly acting on the human body through vital sign monitoring devices, including blood pressure, pulse, heart rate, pupil status, respiratory status, X-ray scan results, magnetic resonance results, etc.;

[0075] Vital sign monitoring data usually has a unified format template, such as a predetermined monitoring index sequence like monitoring index 1 - value 1; monitoring index 2 - value 2;... monitoring index N - value N, etc. Vital sign monitoring data usually appears as structured standard data.

[0076] Medication record data is used to record the medication situation of a specific user within a certain period of time, including medication time nodes, medication names, medication methods, and medication amounts, etc. Usually, medication record data can be generated by manual recording in combination with automated form generation. Therefore, medication record data has both structured and unstructured characteristics.

[0077] After a certain data generation cycle, the clinical medical examination data set usually includes laboratory test data, vital sign monitoring data, and medication record data at the same time.

[0078] With respect to the above clinical medical test data set, different user groups have different data utilization requirements, and different data utilization requirements correspond to different data classification and processing processes.

[0079] For example, managers of hospital testing departments need to compile statistics on laboratory testing data of their departments on a weekly / monthly basis, including the number of tests, number of test subjects, peak testing period, etc., so as to make resource scheduling and personnel allocation in advance for the next cycle of testing work;

[0080] For managers of the data management department of the entire hospital, it is necessary to compile statistics on the number of patients visiting the entire hospital and medication record data every month / quarter, including the number of times vital signs detection equipment is used, the number of cycles, the issuance / consumption of certain drugs, the number of patients with a certain disease, the peak period of medication, the peak period of visits, the peak period of testing, etc.

[0081] In other scenarios, such as for internal or external researchers in a hospital, it may be necessary to classify and compare data from different dimensions. For example, classify by medication dosage to filter out the types of diseases with the largest medication dosage, classify by test volume to filter out the first-visit doctors with the largest test volume, etc.

[0082] To this end, it is first necessary to determine a classification standard for the clinical medical test data set, that is, enter step S200: determine the data classification standard.

[0083] For further implementation of step S200, please refer to Figure 2 and Figure 3 .

[0084] The step S200 determines the data classification standard, which specifically includes:

[0085] S201: Determine the data source, data format, and data generation time range of the clinical medical test data set to be classified;

[0086] S202: parsing a human-computer interaction instruction input by a user through the human-computer interaction terminal;

[0087] S203: Determine the data classification standard based on at least one of the data source, data format, data generation time range, and human-computer interaction instructions.

[0088] In the clinical medical test data classification method proposed in this application, the determination of data classification standards takes into account two aspects: the user's subjective intention and the objective attributes of the data, and the user's subjective intention has a higher priority than the objective attributes of the data, so that the determination of the classification standards is more in line with user expectations.

[0089] Specifically, the data sources include the drug circulation process and the patient consultation process. Obviously, the drug circulation process can at least generate medication record data, while the patient consultation process is usually accompanied by the generation of laboratory test data and vital signs monitoring data.

[0090] The data formats include text, images and video frames; an image refers to a single generated picture; a video frame refers to one of multiple video frames constituting a certain video clip.

[0091] In order to reflect the priority of the user's subjective will over the objective attributes of the data, see Figure 4 , the step S203 specifically includes:

[0092] S2031: Determine whether at least one classification standard can be determined through the analysis result of the human-computer interaction instruction;

[0093] If yes, proceed to step S2033;

[0094] Otherwise, proceed to step S2032;

[0095] S2032: Recommend at least one classification standard based on the data source, data format, and data generation time range;

[0096] S2033: receiving feedback from the user on the at least one classification standard;

[0097] S2034: Determine the data classification standard based on the feedback result.

[0098] It can be seen that if at least one classification standard can be determined based on the analysis results of the human-computer interaction instructions, the data will be classified according to the classification standard in the future, and the basic attributes of the data to be classified will no longer be considered. The analysis results of the human-computer interaction instructions reflect the user's subjective classification intention.

[0099] To better describe the implementation process of the above embodiment, a specific implementation scenario of the above steps is summarized below with a simple schematic example:

[0100] Step 1: Obtain a set of clinical medical test data to be classified, including laboratory test data, vital signs monitoring data, and medication record data;

[0101] Step 2: Determine the data source, data format, and data generation time range of each data in the clinical medical test data set to be classified; the data source includes the drug circulation process and the patient consultation process; the data format includes text, image, and video frame;

[0102] For example: The first set of data, SetA, generation time: Monday; data format: image; data source: patient visits; the second set of data, SetB, generation time: Wednesday; data format: text; data source: drug circulation; the third set of data, SetC, generation time: Wednesday; data format: video frame; data source: patient visits.

[0103] Step 3: Parse the human-computer interaction instruction input by the user through the human-computer interaction terminal;

[0104] After obtaining the above-mentioned set of clinical medical test data to be classified, the user may input corresponding human-computer interaction instructions according to their own needs.

[0105] For example, the user inputs the text instruction "Classify the data according to different formats and different data sources"; the user can also issue an instruction by voice "I need to obtain the data generated during the circulation process of drug A on Wednesdays"; or, the user can select a classification instruction from the preset classification options provided in the human-computer interaction interface of the human-computer interaction terminal.

[0106] At this time, assuming that the user inputs a human-computer interaction instruction, it is determined whether at least one classification criterion can be determined through the parsing result of the human-computer interaction instruction;

[0107] If so, after receiving the feedback result of the user on the at least one classification criterion, determine the data classification criterion based on the feedback result.

[0108] Specifically, for the text instruction "Classify the data according to different formats and different data sources" input by the user, the parsing result is:

[0109] The user hopes to classify the data according to different formats (the first classification criterion);

[0110] The user hopes to classify the data according to different sources (the second classification criterion);

[0111] Then the determined classification criteria are the above-mentioned first classification criterion and second classification criterion.

[0112] For the voice instruction issued by the user "I need to obtain the data generated during the circulation process of drug A on Wednesdays", the parsing result is:

[0113] Classify the data according to the data generation time period (time classification criterion - the first classification result: A (Wednesdays));

[0114] Classify the data according to the data generation source (source classification criterion - the second classification result: B (drug A - circulation process)).

[0115] If the user believes that the parsing result is accurate, then confirming the parsing result means confirming the classification criteria.

[0116] If the user believes that the parsing result is inaccurate, then re-parsing or returning is required.

[0117] Of course, if it is determined that at least one classification criterion cannot be determined through the parsing result of the human-computer interaction instruction. For example, if the instruction input by the user is "display the data classification result", it means that the user does not have a specific classification expectation. At this time, it enters the link of determining the classification criterion based on the basic attributes of the data, that is, step S2032: Recommend at least one classification criterion based on the data source, data format, and data generation time range.

[0118] At this time, the recommended classification criteria may include:

[0119] Classify by data source;

[0120] Classify by data format;

[0121] Classify by data generation time range;

[0122] ……;

[0123] On this basis, it is still possible to receive the feedback result of the user on the at least one classification criterion, and then determine the data classification criterion based on the feedback result. The user can select one or more of the recommended classification criteria.

[0124] It should be noted that although there are similar methods for determining data classification criteria in the prior art, these methods all determine the classification criteria based on the objective attributes of the data, without considering the subjective needs of the user, and without placing the subjective needs in a high-priority position, which may lead to the classification result not meeting the user's expectations, or the classification criterion not being within the user's expected range.

[0125] In addition, the existing data classification methods usually only provide one classification criterion each time to perform a classification process. When the user's requirement is to compare the classification results under multiple-dimensional classifications to screen out target value data, multiple operations or manual operations are usually required, resulting in a poor user experience and insufficient satisfaction of the demand.

[0126] Therefore, the present invention provides the following further preferred embodiments:

[0127] When the data classification criterion determined in step S203 can at least include a first classification criterion and a second classification criterion, step S300 further includes:

[0128] S301: Perform a first classification operation on the clinical medical test data set based on the determined first classification criterion to obtain a first classification result; perform a second classification operation on the clinical medical test data set based on the determined second classification criterion to obtain a second classification result;

[0129] S302: Compare the first classification result and the second classification result;

[0130] S303: Based on the comparison result, filter out the target subset of clinical medical test data.

[0131] The instruction "I need to obtain the data generated during the circulation process of drug A on Wednesdays" is issued in the voice of the aforementioned user, and the parsing result is:

[0132] Classify the data according to the data generation time period (time classification criterion - first classification result: A (Wednesdays));

[0133] Classify the data according to the data generation source (source classification criterion - second classification result: B (drug A - circulation process)).

[0134] If the user deems the parsing result accurate, then confirm the parsing result, that is, execute the first classification according to the classification criterion to obtain the first classification result, and execute the second classification to obtain the second classification result;

[0135] At this time, compare the first classification result and the second classification result. It can be to obtain the intersection part of the first classification result and the second classification result, so as to filter out the target subset of clinical medical test data, that is, "the data generated during the circulation process of drug A on Wednesdays".

[0136] Of course, the user feedback on the feedback result of the classification criterion also provides more flexibility, which can further improve the above data processing process and take into account the user's expectations. Therefore, the method further includes:

[0137] The feedback result of the user on the at least one classification criterion in step S2033 includes:

[0138] When the at least one classification criterion includes only one classification criterion, determine whether a confirmation operation from the user is received within a preset time. If so, determine the feedback result; otherwise, go to step S2032.

[0139] The feedback result of the user on the at least one classification criterion in step S2033 includes:

[0140] When the at least one classification criterion includes at least two classification criteria,

[0141] If the at least two classification criteria are recommended based on step S2032, prompt the user to check at least one classification criterion, and confirm the feedback result based on the user's check operation.

[0142] If the at least two classification criteria are parsed based on step S2031, determine whether a confirmation operation from the user is received within a preset time. If so, determine the feedback result; otherwise, return to step S202.

[0143] The above introduced various preferred implementation manners and schematic implementation examples of the method embodiments of the present invention. It can be understood that the above examples are only examples and do not represent all implementation manners of the technical solutions of this application. For example, classification criteria, interactive instructions input by users, etc. can all be selected and changed according to actual situations, and the technical solutions of the present invention can be applied to these selections and changes.

[0144] Based on the method embodiments, Figures 4-5 a corresponding functional architecture diagram of the clinical medical examination data classification system is given.

[0145] Figure 4 A clinical medical examination data classification system is shown. The system includes a human-computer interaction unit, a data acquisition unit, a data attribute recognition unit, an interactive instruction parsing unit, and a classification criterion determination unit.

[0146] The specific functions of each unit are as follows:

[0147] The data acquisition unit is used to acquire a set of clinical medical examination data to be classified.

[0148] The data attribute recognition unit is used to recognize the data attributes of the set of clinical medical examination data to be classified.

[0149] The interactive instruction parsing unit is used to parse the human-computer interaction instructions input by the user through the human-computer interaction unit.

[0150] The classification criterion determination unit is used to determine the data classification criterion based on the data attributes recognized by the data attribute recognition unit and / or the parsing result of the interactive instruction parsing unit for the human-computer interaction instructions.

[0151] The classification result output unit is used to output the classification result after classifying the set of clinical medical examination data based on the data classification criterion.

[0152] Among them, the set of clinical medical examination data includes laboratory test data, vital sign monitoring data, and medication record data.

[0153] The data attributes of the clinical medical examination data set to be classified include data source, data format, and data generation time range; the data source includes the drug circulation process and the patient visit process; the data format includes text, images, and video frames.

[0154] Considering the scenario of determining multiple classification criteria at one time to obtain target screening data, Figure 5 the preferred embodiment of Figure 4 On this basis, the system further includes a data screening unit;

[0155] When the data classification criteria determined by the classification criteria determination unit include at least a first classification criterion and a second classification criterion, the data screening unit is activated;

[0156] The data screening unit screens out a target clinical medical examination data subset based on the classification result output by the classification result output unit.

[0157] The data screening unit screens out a target clinical medical examination data subset based on the classification result output by the classification result output unit, specifically including:

[0158] The classification result output unit performs a first classification operation on the clinical medical examination data set based on the determined first classification criterion to obtain a first classification result; and performs a second classification operation on the clinical medical examination data set based on the determined second classification criterion to obtain a second classification result;

[0159] The data screening unit compares the first classification result and the second classification result; and based on the comparison result, screens out a target clinical medical examination data subset.

[0160] In summary, it can be seen that the technical solution of the present invention can fully consider the subjective needs of users and the objective attributes of the data to be classified when classifying clinical medical examination data, so as to more accurately determine the classification criteria, and focuses on the subjective needs of users; at the same time, the classification criteria can be diversified to meet the needs of later data screening, so that the user's data utilization needs can be maximized and quickly and timely satisfied. It is convenient to operate and saves the user's time, improving the user experience.

[0161] The aforementioned clinical medical examination data classification method can be automatically implemented through various forms of electronic devices by computer program instructions; the computer program instructions can be stored in different forms of storage media and loaded into a computer electronic device for execution.

[0162] Therefore, more embodiments further provide a computer-readable storage medium for storing computer instructions, which when run on an electronic device, cause the electronic device to execute Figures 1-3All or part of the steps of a clinical medical test data classification method.

[0163] More embodiments also propose a computer device, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the computer device executes Figures 1-3 All or part of the steps of a clinical medical test data classification method.

[0164] More embodiments also propose a computer program product, which includes a computer program. When the computer program is executed, Figures 1-3 All or part of the steps of a clinical medical test data classification method are implemented.

[0165] At the same time, in the specific implementation of the present application, if it involves user-related data, when the embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0166] For other technologies, principles, algorithms, or models not detailed in the present application, reference can be made to the prior art. The prior art cited in the embodiment part is an integral part of the disclosure of the present invention.

[0167] The method embodiments and systems of the present invention have been shown and described above. However, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for classifying clinical medical examination data, the method being applied to a human-computer interaction terminal, characterized in that, The method includes the following steps: S100: Obtain a set of clinical medical test data to be classified; S200: Determine the data classification criteria; S300: Classify the set of clinical medical test data based on the determined data classification criteria; Among them, the step S200 of determining the data classification criteria specifically includes: S201: Determine the data source, data format, and data generation time range of the set of clinical medical test data to be classified; S202: Parse the human-computer interaction instructions input by the user through the human-computer interaction terminal; S203: Determine the data classification criteria based on at least one of the data source, data format, data generation time range, and human-computer interaction instructions.

2. The clinical medical test data classification method according to claim 1, wherein, The set of clinical medical test data includes laboratory test data, vital sign monitoring data, and medication record data; The data source includes the drug circulation process and the patient visit process; The data format includes text, images, and video frames.

3. A method for classifying clinical medical examination data according to claim 1, characterized in that, The step S203 specifically includes: S2031: Determine whether at least one classification criterion can be determined through the parsing result of the human-computer interaction instructions; If so, proceed to step S2033; Otherwise, proceed to step S2032; S2032: Recommend at least one classification criterion based on the data source, data format, and data generation time range; S2033: Receive the feedback result of the user on the at least one classification criterion; S2034: Determine the data classification criteria based on the feedback result.

4. A method for classifying clinical medical examination data according to claim 1, characterized in that, When the data classification criteria determined by the step S203 include at least a first classification criterion and a second classification criterion, the step S300 further includes: S301: Perform a first classification operation on the set of clinical medical test data based on the determined first classification criterion to obtain a first classification result; perform a second classification operation on the set of clinical medical test data based on the determined second classification criterion to obtain a second classification result; S302: Compare the first classification result and the second classification result; S303: Based on the comparison result, screen out the target subset of clinical medical test data.

5. The method for classifying clinical medical examination data according to claim 3, wherein The feedback result of the user on the at least one classification criterion in the step S2033 includes: When the at least one classification criterion includes only one classification criterion, determine whether a confirmation operation from the user is received within a preset time. If so, determine the feedback result; otherwise, proceed to step S2032.

6. The method for classifying clinical medical examination data according to claim 3, wherein The feedback result of the user on the at least one classification criterion in the step S2033 includes: When the at least one classification criterion includes at least two classification criteria, If the at least two classification criteria are recommended based on step S2032, prompt the user to check at least one classification criterion, and confirm the feedback result based on the user's check operation; If the at least two classification criteria are parsed based on step S2031, determine whether a confirmation operation from the user is received within a preset time. If so, determine the feedback result; otherwise, return to step S202.

7. A clinical medical test data classification system, the system comprising a human-computer interaction unit, characterized in that, The system further includes: A data acquisition unit for obtaining a set of clinical medical test data to be classified; A data attribute recognition unit for recognizing the data attributes of the set of clinical medical test data to be classified; An interaction instruction parsing unit for parsing the human-computer interaction instructions input by the user through the human-computer interaction unit; A classification criterion determination unit for determining data classification criteria based on the data attributes recognized by the data attribute recognition unit and / or the parsing results of the interaction instruction parsing unit for the human-computer interaction instructions; A classification result output unit for outputting a classification result after classifying the set of clinical medical test data based on the data classification criteria; Among them, the set of clinical medical test data includes laboratory test data, vital sign monitoring data, and medication record data.

8. A clinical medical test data classification system according to claim 7, characterized in that, The data attributes of the set of clinical medical test data to be classified include data source, data format, and data generation time range; the data source includes the drug circulation process and the patient visit process; the data format includes text, image, and video frame.

9. A clinical medical test data classification system according to claim 7, characterized in that, The system further includes a data screening unit; When the data classification criteria determined by the classification criterion determination unit include at least a first classification criterion and a second classification criterion, the data screening unit is activated; The data screening unit screens out a target subset of clinical medical test data based on the classification result output by the classification result output unit.

10. A clinical medical test data classification system according to claim 9, characterized in that, The data screening unit screens out a target subset of clinical medical test data based on the classification result output by the classification result output unit, specifically including: The classification result output unit performs a first classification operation on the set of clinical medical test data based on the determined first classification criterion to obtain a first classification result; performs a second classification operation on the set of clinical medical test data based on the determined second classification criterion to obtain a second classification result; The data screening unit compares the first classification result and the second classification result; based on the comparison result, screens out a target subset of clinical medical test data.

Images