Medical image label generation method, device, equipment and storage medium

Abstract

The application provides a medical portrait label generation method, device, equipment and storage medium. The method comprises the following steps: obtaining initial medical data of a resident, and preprocessing the initial medical data to obtain preprocessed data; establishing a multi-level label system and defining labels in each level of the label system; configuring corresponding data processing rules based on the multi-level label system, and performing data processing on the preprocessed data based on the data processing rules to obtain target labels and corresponding target data; and setting an evaluation model, and generating a medical portrait label of the resident based on the evaluation model and evaluation information, wherein the evaluation information comprises the target labels and the target data.

Description

Technical Field

[0001] This application relates to the field of medical data processing, and more specifically, to a method, apparatus, device, and storage medium for generating medical profile tags. Background Technology

[0002] With the development of medical and internet technologies, patient diagnostic process information can be completely recorded and saved, further used for personalized treatment, intelligent doctor-assisted diagnosis, and refined management of the healthcare industry. First, it is necessary to comprehensively and quantitatively abstract patient information to form a resident medical profile. This profile, centered on the patient, is based on massive amounts of real and comprehensive medical event data, depicting a feature chain spanning the patient's entire lifecycle. This results in a complete digital description of patient characteristics, covering basic demographic information, diseases treated, clinical medications, laboratory tests, surgical information, and health risks—a complete medical event profile. However, extracting tags from such vast amounts of medical information requires a large number of professionals and a considerable amount of time.

[0003] Currently, commonly used tag extraction techniques generally adopt the form of directly writing extraction scripts or calculation scripts. For each tag, developers need to write corresponding execution scripts. Among them, commonly used tag extraction techniques have the following shortcomings: (1) The tag extraction process is highly dependent on developers and inefficient: all tag extraction scripts need to be written by developers, which is inefficient and requires high technical skills from developers, resulting in strong dependence; (2) Poor flexibility: the tag extraction script is implemented through code. If a new data source is added later, the extraction script needs to be rewritten; (3) Difficult tag management: the relationship between tags and data sources, and the relationship between tags are defined in the extraction script, which cannot be displayed intuitively and is not conducive to management and subsequent maintenance.

[0004] Therefore, improving the efficiency of medical profile tag generation and enhancing its intuitiveness and flexibility are urgent problems to be solved. Summary of the Invention

[0005] Some embodiments of this application provide a method, apparatus, device, and storage medium for generating medical portrait tags that can at least partially solve the aforementioned problems existing in the prior art.

[0006] According to one aspect of this application, a method for generating medical profile tags is provided. The method may include: acquiring initial medical data of residents and preprocessing the initial medical data to obtain preprocessed data; establishing a multi-level tag system and defining tags in each level of the tag system; configuring corresponding data processing rules based on the multi-level tag system and processing the preprocessed data based on the data processing rules to obtain target tags and corresponding target data; and setting an evaluation model and generating medical profile tags of residents based on the evaluation model and evaluation information, wherein the evaluation information includes the target tags and the target data.

[0007] In one embodiment of this application, configuring corresponding data processing rules based on the multi-level tag system and processing the preprocessed data based on the data processing rules to obtain target tags and corresponding target data may include: filtering tags in the multi-level tag system to obtain a first target tag, wherein the first target tag is a directly extracted tag; configuring a first data extraction rule based on the first target tag; and extracting the preprocessed data based on the first data extraction rule to obtain the first target data.

[0008] In one embodiment of this application, the data processing rules are configured based on the multi-level tagging system, and the preprocessed data is processed based on the data processing rules to obtain target tags and corresponding target data. The method may further include: analyzing and processing the first target data to generate second target data; and selecting a second target tag associated with the second target data.

[0009] In one embodiment of this application, setting an assessment model and generating a resident's medical profile tag based on the assessment model and assessment information may include: obtaining parameter information corresponding to the assessment model and obtaining the corresponding assessment information based on the parameter information; setting an assessment period and generating the resident's medical profile tag based on the assessment model and the assessment information.

[0010] In one embodiment of this application, after filtering the tags in the multi-level tagging system to obtain the first target tag, the method may further include: setting the priority of the first target tag.

[0011] In one embodiment of this application, generating the medical profile tag for a resident based on the assessment model and assessment information may further include: determining necessary information in the parameter information and detecting the assessment information based on the necessary information; in response to the assessment information containing all the necessary information, determining the data saturation of the assessment information and comparing the data saturation of the assessment information with the data saturation threshold of the assessment model; and in response to the data saturation of the assessment information being greater than or equal to the data saturation threshold, generating the medical profile tag corresponding to the resident.

[0012] In one embodiment of this application, before generating the medical profile label of a resident based on the assessment model and the assessment information, the method may further include: acquiring time information in the target data; selecting the latest data acquisition time from the time information and comparing the latest data acquisition time with a preset time; in response to the latest data acquisition time being earlier than the preset time, detecting whether there is updated initial medical data; and in response to the existence of updated initial medical data, acquiring the target label corresponding to the updated initial medical data.

[0013] In one embodiment of this application, the method may further include: configuring the validity period of the target label, detecting the validity period of the target label, and if the validity period is greater than the validity period threshold, marking the corresponding target label as an expired label.

[0014] This application also provides a medical profile tag generation device, which may include: a preprocessing module for acquiring initial medical data of residents and preprocessing the initial medical data to obtain preprocessed data; a tag establishment module for establishing a multi-level tag system and defining tags in each level of the tag system; a data processing module for configuring corresponding data processing rules based on the multi-level tag system and processing the preprocessed data based on the data processing rules to obtain target tags and corresponding target data; and a medical profile tag generation module for setting an evaluation model and generating medical profile tags for residents based on the evaluation model and evaluation information, wherein the evaluation information includes the target tags and the target data.

[0015] In one embodiment of this application, the data processing module can be used to filter tags in the multi-level tag system to obtain a first target tag, wherein the first target tag is a directly extracted tag; configure a first data extraction rule based on the first target tag; and extract the preprocessed data based on the first data extraction rule to obtain the first target data.

[0016] In one embodiment of this application, the data processing module can also be used to analyze and process the first target data to generate second target data; and to select a second target label associated with the second target data.

[0017] In one embodiment of this application, the medical profile tag generation module can be used to obtain parameter information corresponding to the assessment model, and obtain the corresponding assessment information based on the parameter information; set the assessment period, and generate the resident's medical profile tag based on the assessment model and the assessment information.

[0018] In one embodiment of this application, the tag creation module can also be used to set the priority of the first target tag.

[0019] In one embodiment of this application, the medical profile tag generation module can be used to determine the necessary information in the parameter information and detect the evaluation information based on the necessary information; in response to the evaluation information containing all the necessary information, the module determines the data saturation of the evaluation information and compares the data saturation of the evaluation information with the data saturation threshold of the evaluation model; in response to the data saturation of the evaluation information being greater than or equal to the data saturation threshold, the module generates the medical profile tag corresponding to the resident.

[0020] In one embodiment of this application, the tag establishment module can also be used to obtain time information in the target data; select the latest data acquisition time in the time information and compare the latest data acquisition time with a preset time; in response to the latest data acquisition time being earlier than the preset time, detect whether there is updated initial medical data; in response to the existence of updated initial medical data, obtain the target tag corresponding to the updated initial medical data.

[0021] In one embodiment of this application, the tag creation module can also be used to configure the validity period of the target tag and detect the validity period of the target tag. If the validity period is greater than the validity period threshold, the corresponding target tag is marked as an expired tag.

[0022] In another aspect, this application provides an electronic device that may include: a processor adapted to execute a computer program; and a computer-readable storage medium storing a computer program that, when executed by the processor, implements the method described above.

[0023] In another aspect, this application provides a computer-readable storage medium for storing a computer program that causes a computer to perform any of the methods described above.

[0024] According to the exemplary implementation of this application, the initial medical data of residents is processed by configuring corresponding data processing rules based on a multi-level tag system to obtain target tags and target data, and medical profile tags of residents are generated based on an evaluation model. This can reduce the difficulty of obtaining medical profile tags of residents to a certain extent, improve the efficiency and accuracy of generating medical profile tags, and facilitate the management and maintenance of tags. Attached Figure Description

[0025] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. Wherein:

[0026] Figure 1 A flowchart of a method for generating medical profile tags according to an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a multi-level labeling system according to an exemplary embodiment of this application;

[0028] Figure 3 This is a schematic diagram of a label configuration according to an exemplary embodiment of this application;

[0029] Figure 4 This is a flowchart illustrating the acquisition of a first target tag and first target data according to an exemplary embodiment of this application;

[0030] Figure 5 This is a flowchart illustrating the acquisition of a second target label and second target data according to an exemplary embodiment of this application;

[0031] Figure 6 A flowchart illustrating further processing of residents' initial medical data according to an exemplary embodiment of this application;

[0032] Figure 7 This is a flowchart illustrating the generation of medical profile tags according to an exemplary embodiment of this application;

[0033] Figure 8 This is a schematic diagram of parameter information corresponding to the cardiovascular disease risk assessment model according to an exemplary embodiment of this application;

[0034] Figure 9 This is a flowchart illustrating the determination of the saturation of evaluation information according to an exemplary embodiment of this application;

[0035] Figure 10 A schematic diagram of a medical image tag generation apparatus 2000 according to an exemplary embodiment of this application;

[0036] Figure 11This is a schematic diagram of the structure of an electronic device 3000 adapted to implement embodiments of the present disclosure, according to an embodiment of the present disclosure. Detailed Implementation

[0037] To better understand this application, various aspects of this application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of this application and are not intended to limit the scope of this application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0038] In the accompanying drawings, the size, dimensions, and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustrative purposes only and are not strictly to scale. As used herein, the terms “approximately,” “about,” and similar terms are used to indicate approximation, not degree, and are intended to illustrate inherent deviations in measured or calculated values ​​that will be recognized by one of ordinary skill in the art. Furthermore, the order in which the steps are described in this application does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0039] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of this application, the word "may" is used to mean "one or more embodiments of this application." And the term "exemplary" is intended to refer to examples or illustrations.

[0040] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or overly formalized meaning.

[0041] It should be noted that, where there is no conflict, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0042] Figure 1This is a flowchart of a method 1000 for generating medical profile tags according to an embodiment of this application. Figure 1 As shown, the method 1000 for generating medical profile tags may include:

[0043] Step S100: Obtain the residents' initial medical data and preprocess the initial medical data to obtain preprocessed data;

[0044] Step S200: Establish a multi-level tag system and define the tags in each level of the tag system;

[0045] Step S300: Configure corresponding data processing rules based on the multi-level tagging system, and process the preprocessed data based on the data processing rules to obtain the target tags and corresponding target data; and

[0046] Step S400: Set up an assessment model and generate medical profile tags for residents based on the assessment model and assessment information, wherein the assessment information includes target tags and target data.

[0047] According to the exemplary implementation of this application, the initial medical data of residents is processed by configuring corresponding data processing rules based on a multi-level tag system to obtain target tags and target data, and medical profile tags of residents are generated based on an evaluation model. This can reduce the difficulty of obtaining medical profile tags of residents to a certain extent, improve the efficiency and accuracy of generating medical profile tags, and facilitate the management and maintenance of tags.

[0048] The following will detail the specific steps of the above-mentioned method 1000 for generating medical profile tags.

[0049] Step S100

[0050] In an exemplary embodiment of this application, initial medical data of residents is first obtained. This initial medical data may include multiple types of information, such as residents' medical treatment information, medical record information, and public health service information. Each type of information may include at least one business table; for example, medical record information may include a prescription business table, a test report business table, and an examination report business table. Exemplarily, the data source involving residents can be configured to obtain the corresponding initial medical data. The configuration includes the data source connection information, data model information, and data dictionary information. The data source connection information may include the database type, database IP address, port number, database instance name, username, and password; the data dictionary information is the value domain dictionary used in the data source.

[0051] In an exemplary embodiment of this application, after obtaining the initial medical data of residents, the initial medical data can be preprocessed to obtain preprocessed data. For example, the initial medical data can be divided into basic data and special data. The basic data is converted into standard data using a conversion script. Special data generally constitutes a very small proportion and requires separate processing by specialized personnel. For instance, the conversion script can perform multi-value field splitting, code association of specific meanings, code conversion, unstructured text segmentation, quantitative data conversion into qualitative data, presence / absence judgment, presence / absence of specific values ​​judgment, record count, etc., to convert the basic data into standard data. For example, the resident's gender in the initial data can be represented by codes 1 and 2 to indicate male and female, and the specific meaning needs to be associated with the codes to obtain the resident's gender; the medical data may come from different medical institutions, and different medical institutions may use different codes. Code conversion can unify the codes from different medical institutions; residents' blood pressure, blood sugar, etc., are generally fixed values. The fixed blood pressure and blood sugar values ​​are mapped to standard blood pressure or blood sugar ranges. By converting quantitative data into qualitative data, it is possible to better diagnose residents' diseases subsequently.

[0052] According to an exemplary embodiment of this application, by preprocessing the initial medical data to obtain preprocessed data, the accuracy of data label classification can be improved in subsequent processes.

[0053] Step S200

[0054] In an exemplary embodiment of this application, after obtaining the preprocessed data, a multi-level tagging system can be established, and the tags in each level of the tagging system can be defined. Figure 2 This is a schematic diagram of a multi-level labeling system according to an exemplary embodiment of this application. For example... Figure 2As shown, this application uses a two-level label classification system as an example. The first-level label can be labels of different categories, and the second-level label can be different medical labels within the same category. For example, the first-level label can include a code and a name. The code is AI, and the corresponding label names are Demographics and Socioeconomics, Health History, Health Risk Factor Table, Chief Complaint and Symptoms, Physical Examination, Clinical Auxiliary Examination, Laboratory Examination, Medical Diagnosis, and Medical Assessment, respectively. The second-level label can include a code and a name. Taking Health History as an example, the codes for the second-level labels corresponding to Health History are B01-B09, and the corresponding second-level label names are History of Infectious Diseases, History of Allergies, Surgical History, History of Trauma, History of Blood Transfusion, History of Illness, Disability Status, Reproductive History, and Menstrual History, respectively. The second-level label can also include multiple specific medical labels. Taking the second-level label Reproductive History as an example, it can include specific medical labels, where the codes for the specific medical labels are B0801-B0807, corresponding to parity, adverse pregnancy history, preterm birth history, ectopic pregnancy history, previous pregnancy information, previous delivery information, and pregnancy complications, respectively. The information corresponding to medical labels can generally be obtained directly from the preprocessed data. This application uses a two-level label as an example for illustration. Those skilled in the art will understand that label levels can be set according to actual circumstances, and this application does not impose any restrictions on this.

[0055] In an exemplary embodiment of this application, after establishing a two-level tagging system, tags in each level of the tagging system can be defined based on the tagging system. For example, basic information, composition information, and tag attributes can be configured for each tag. Figure 3 This is a schematic diagram illustrating a label configuration according to an exemplary embodiment of this application. For example... Figure 3 As shown, taking the specific medical tag B0302 surgical information as an example, the basic information and tag attributes configured for the tag can include: category, cardinality, gender restriction, age restriction, data type, validity rules, validity period, expiration handling, acquisition method, and search conditions. The composition information and tag attributes configured for the tag can include: node name, node meaning, data type, field length, encoding table, deduplication criteria, search conditions, and operations. Among these, data types can include simple tags and composite tags. Simple tags contain only one field, while composite tags can contain multiple fields.

[0056] According to the exemplary implementation of this application, by establishing a multi-level tagging system and defining the tags in each level of the multi-level tagging system, the relationship between tags and data, and the relationship between tags, can be better displayed, which is beneficial to the management and maintenance of tags.

[0057] Step S300

[0058] In an exemplary embodiment of this application, corresponding data processing rules are configured based on a multi-level tagging system, and preprocessed data is processed based on these rules to obtain target tags and corresponding target data. First, the preprocessed data can be directly extracted to obtain a first target tag and first target data. Figure 4 This is a flowchart illustrating the acquisition of a first target tag and first target data according to an exemplary embodiment of this application. Figure 4 As shown, obtaining the first target label and the first target data may include the following steps:

[0059] Step S310: Filter the tags in the multi-level tag system to obtain the first target tag, wherein the first target tag is the directly extracted class tag;

[0060] Step S320: Configure the first data extraction rule based on the first target label; and

[0061] Step S330: Extract the preprocessed data based on the first data extraction rule to obtain the first target data.

[0062] For example, direct extraction can directly extract relevant information from various business tables or only require simple data transformation to obtain the corresponding information. Therefore, the tags in the multi-level tag system can be filtered first, and tags that can be directly extracted can be selected as the first target tags. Then, the first data extraction rules can be configured based on the first target tags. The process of configuring the first data extraction rules is as follows: Select business table → Set extraction conditions (i.e., certain fields in the business table meet the extraction conditions, such as equal to, not equal to, greater than, or less than a certain value, before extraction can be performed) → Select mapping fields (select the mapping fields corresponding to the first target tags in the business tables) → Set data transformation method. Then, the preprocessed data is extracted based on the first data extraction rules to obtain the first target data. For example, surgical information in the business tables of the preprocessed data can be extracted using the first data extraction rules to obtain the corresponding first target data, such as surgical name, surgical date, surgical institution name, etc.

[0063] According to the exemplary implementation of this application, preprocessed data is directly extracted based on the first target label to obtain the corresponding first target data. Through simple data transformation and mapping, there is no need for developers to write scripts to extract data, which can reduce the difficulty of obtaining residents' medical profile labels to a certain extent.

[0064] In the exemplary embodiments of this application, the priority of the first target label can be further set. For example, a first target label of the resident identification category, such as name or ID number, is set as the first priority. During data extraction, data corresponding to the first target label with the first priority should be extracted first, and so on. By setting the priority of the first target label, the extraction progress of the first target data can be optimized, and the accuracy of the association between the first target data and the first target label can be improved.

[0065] In an exemplary embodiment of this application, after obtaining the first target label and the corresponding first target data, the first target data can be further processed to obtain the second target label and the second target data. Figure 5 This is a flowchart illustrating the acquisition of a second target label and second target data according to an exemplary embodiment of this application. Figure 5 As shown, obtaining the second target label and the second target data may include the following steps:

[0066] Step S340: Analyze and process the first target data to generate the second target data;

[0067] Step S350: Select the second target label associated with the second target data.

[0068] For example, by analyzing the first target data, the transformation method of the first target data can be determined. This transformation method can include basic data transformation methods and special data transformation methods, allowing the first target data to be transformed to obtain the second target data. Further, a second target tag associated with the second target data is selected in the tagging system. For instance, the first target data can be used to determine whether a resident has undergone surgery based on their surgical information (surgery name, surgery date, surgical institution name, etc.), thus obtaining the second target data, i.e., whether the resident has undergone surgery. Then, the corresponding surgical history is associated with the second target data in the tagging system. Figure 2 The second target data can be filtered based on the configuration information of the second target label. For example, the second target data can be filtered based on the time range specified by the second target label.

[0069] According to the exemplary implementation of this application, by analyzing and processing the first target data to obtain the second target data and associating it with the second target label, the first target data can be further simplified, which is beneficial to simplifying the subsequent data analysis process and can improve the efficiency of generating medical profile labels to a certain extent.

[0070] In an exemplary embodiment of this application, since residents' medical data is updated rapidly, it is necessary to obtain the latest medical data of residents to predict their medical profile labels in order to generate more accurate medical profile labels. Therefore, after obtaining the first target data, the second target data, the first target label, and the second target label, the residents' initial medical data can be further tested. Figure 6 This is a flowchart illustrating a further step in examining initial medical data of residents according to an exemplary embodiment of this application. Figure 6 As shown, further testing of residents' initial medical data may include the following steps:

[0071] Step S360: Obtain time information from the target data;

[0072] Step S370: Select the latest data acquisition time in the time information and compare the latest data acquisition time with the preset time;

[0073] Step S380: In response to the latest data acquisition time being earlier than the preset time, check whether there is an update to the initial medical data;

[0074] Step S390: In response to the existence of updated initial medical data, obtain the target label corresponding to the updated initial medical data.

[0075] For example, time information is acquired from the first target data and / or the second target data. The first target data and / or the second target data may contain multiple time information items. The latest data acquisition time is selected from these multiple time information items, and then compared with a preset time. The preset time can be set to 00:00 every day. If the latest data acquisition time is earlier than the preset time, an incremental data processing procedure can be performed, i.e., detecting whether there is an update to the initial medical data. If there is an update to the initial medical data, the first target label and / or the second target label corresponding to the updated initial medical data are acquired. The acquisition of the first target label and / or the second target label corresponding to the updated initial medical data has been described in detail above and will not be elaborated further here.

[0076] According to an exemplary implementation of this application, the system detects whether updated initial medical data exists based on a preset time interval. If updated initial medical data exists, the target tag corresponding to the updated initial medical data is obtained. By detecting the initial medical data through a preset time interval, the updated initial medical data only needs to be processed based on the original data processing rules. This improves the flexibility of tag management while ensuring that the target tag is obtained based on the latest medical data.

[0077] In an exemplary embodiment of this application, the validity period of the target label can also be configured and detected. If the validity period exceeds a threshold, the corresponding target label is marked as expired. For example, different labels can be set with different validity periods; for instance, one label may have a validity period of one year. If a generated label is detected to have expired after one year, this label is set as expired. By setting the validity period of the labels, the accuracy of the generated medical profile labels can be improved to some extent.

[0078] Step S400

[0079] In an exemplary embodiment of this application, after obtaining the target label and the corresponding target data, an evaluation model can be set up, and a medical profile label for the resident can be generated based on the evaluation model and the evaluation information, wherein the evaluation information includes the target label and the target data. Figure 7 This is a flowchart illustrating the generation of medical profile tags according to an exemplary embodiment of this application. Figure 7 As shown, generating medical profile tags may include the following steps:

[0080] Step S410: Obtain the parameter information corresponding to the evaluation model, and obtain the corresponding evaluation information based on the parameter information;

[0081] Step S420: Set the assessment cycle and generate medical profile tags for residents based on the assessment model and assessment information.

[0082] For example, a corresponding assessment model can be selected from the system's predefined assessment models, and the parameter information corresponding to the assessment model can be obtained. The requirements for the parameter information are analyzed to obtain the corresponding assessment information, which may include a first target label, a second target label, first target data, and second target data. This will be illustrated using a cardiovascular disease risk assessment model as an example. Figure 8 This is a schematic diagram of parameter information corresponding to a cardiovascular disease risk assessment model according to an exemplary embodiment of this application. For example... Figure 8As shown, the parameters of the cardiovascular disease risk assessment model include date of birth, systolic blood pressure, body mass index (BMI), total cholesterol, smoking status, and diabetes markers. Based on the data type requirements in the parameter information, a first or second target label is determined, and the corresponding first or second target data is obtained. Taking BMI as an example, it requires the resident's height and weight, calculated using the BMI formula. The first target label includes the resident's height and weight, obtaining the corresponding first target data. After analyzing and processing the first target data, the corresponding second target data (i.e., the resident's BMI index) can be obtained and associated with the corresponding second target label (BMI). Taking date of birth as an example, the resident's first target label (date of birth) can be directly associated, and the corresponding first target data (Year, Month, Day) can be obtained. Then, an assessment period is set, and the assessment information is filtered based on the assessment period to obtain the assessment information within that period. For example, if the assessment period for the cardiovascular disease risk assessment model is one year, then the assessment information for the resident within the past year will be filtered.

[0083] In an exemplary embodiment of this application, after obtaining the evaluation information, the saturation of the evaluation information can be further determined. Figure 9 This is a flowchart illustrating the determination of the saturation of evaluation information according to an exemplary embodiment of this application. Figure 9 As shown, determining the saturation of evaluation information may include the following steps:

[0084] Step S421: Determine the necessary information in the parameter information, and detect the evaluation information based on the necessary information;

[0085] Step S422: In response to the fact that the evaluation information contains all the necessary information, determine the data saturation of the evaluation information and compare the data saturation of the evaluation information with the data saturation threshold of the evaluation model;

[0086] Step S423: In response to the data saturation of the assessment information being greater than or equal to the data saturation threshold, generate medical profile labels corresponding to the residents.

[0087] For example, firstly, the necessary information in the parameter information is determined. This necessary information is indispensable for generating medical profile labels, such as the resident's identity information. Based on this necessary information, the evaluation information is checked. If the evaluation information does not contain all the necessary information, a prompt or marker can be generated, pausing the generation of the resident's medical profile label. If the evaluation information contains all the necessary information, the data saturation of the evaluation information can be further determined and compared with the data saturation threshold of the evaluation model. Since not all target data corresponding to the target label can be obtained when acquiring resident information, it is necessary to determine the data saturation of the evaluation information to ensure more accurate medical profile labels. For example, the data saturation threshold is 70%. When the data saturation of the evaluation information reaches 70%, the resident's medical profile label can be further generated. For example, a cardiovascular disease risk assessment model generates a resident's medical profile label by comprehensively analyzing the evaluation information. The resident's medical profile label can include various output formats; for example, the resident's medical profile label is the resident's risk level for cardiovascular disease.

[0088] According to the exemplary implementation of this application, by setting necessary information in the parameter information and detecting the evaluation information based on the necessary information, the evaluation information can be initially detected. If any necessary information is missing, no medical profile label for the resident will be generated, which can improve the accuracy and efficiency of generating the resident's medical profile label to a certain extent. Furthermore, after determining that the evaluation information contains all necessary information, further detecting the data saturation of the evaluation information can further ensure the accuracy of generating the resident's medical profile label.

[0089] This application also provides an apparatus for determining entity relationships. Figure 10 This is a schematic diagram of a medical image tag generation apparatus 2000 according to an exemplary embodiment of this application. Figure 10 As shown, the medical profile tag generation device may include: a preprocessing module 2100, a tag creation module 2200, a data processing module 2300, and a medical profile tag generation module 2400.

[0090] In an exemplary embodiment of this application, the preprocessing module 2100 can be used to acquire residents' initial medical data and preprocess the initial medical data to obtain preprocessed data. The initial medical data may include multiple types of information, such as residents' medical treatment information, medical record information, public health service information, etc. Each type of information may include at least one business table; for example, medical record information may include a prescription business table, a test report business table, an examination report business table, etc. Exemplarily, the data source involving residents can be configured to obtain the corresponding initial medical data. The configuration content includes the data source connection information, data model information, and data dictionary information. The data source connection information may include database type, database IP address, port number, database instance name, username, password, etc.; the data dictionary information is the value domain dictionary used in the data source.

[0091] In an exemplary embodiment of this application, after obtaining the initial medical data of residents, the initial medical data can be preprocessed to obtain preprocessed data. For example, the initial medical data can be divided into basic data and special data. The basic data is converted into standard data using a conversion script. Special data generally constitutes a very small proportion and requires separate processing by specialized personnel. For instance, the conversion script can perform multi-value field splitting, code association of specific meanings, code conversion, unstructured text segmentation, quantitative data conversion into qualitative data, presence / absence judgment, presence / absence of specific values ​​judgment, record count, etc., to convert the basic data into standard data. For example, the resident's gender in the initial data can be represented by codes 1 and 2 to indicate male and female, and the specific meaning needs to be associated with the codes to obtain the resident's gender; the medical data may come from different medical institutions, and different medical institutions may use different codes. Code conversion can unify the codes from different medical institutions; residents' blood pressure, blood sugar, etc., are generally fixed values. The fixed blood pressure and blood sugar values ​​are mapped to standard blood pressure or blood sugar ranges. By converting quantitative data into qualitative data, it is possible to better diagnose residents' diseases subsequently.

[0092] According to an exemplary embodiment of this application, by preprocessing the initial medical data to obtain preprocessed data, the accuracy of data label classification can be improved in subsequent processes.

[0093] In an exemplary embodiment of this application, the label creation module 2200 can be used to establish a multi-level label system and define the labels in each level of the label system. This application takes a two-level label classification system as an example; the first-level labels can be labels from different categories, and the second-level labels can be different medical labels within the same category. Figure 2As shown, the first-level labels can include codes and names. The code is AI, and the corresponding label names are Demographics and Socioeconomics, Health History, Health Risk Factors Table, Chief Complaint and Symptoms, Physical Examination, Clinical Auxiliary Examination, Laboratory Examination, Medical Diagnosis, and Medical Assessment. The second-level labels can also include codes and names. Taking health history as an example, the codes for the second-level labels corresponding to health history are B01-B09, and the corresponding second-level label names are infectious disease history, allergy history, surgical history, trauma history, blood transfusion history, disease history, disability status, reproductive history, and menstrual history. The second-level labels can also include multiple specific medical labels. Taking the second-level label reproductive history as an example, it can include specific medical labels, where the codes for specific medical labels are B0801-B0807, corresponding to parity, adverse pregnancy history, preterm birth history, ectopic pregnancy history, previous pregnancy information, previous delivery information, and pregnancy complications, respectively. The information corresponding to the medical labels can generally be obtained directly from the preprocessed data. This application uses a two-level label as an example for illustrative purposes. Those skilled in the art will understand that the label levels can be set according to the actual situation, and this application does not impose any restrictions on this.

[0094] In an exemplary embodiment of this application, after establishing a two-level tagging system, tags in each level of the tagging system can be defined based on the tagging system. For example, basic information, composition information, and tag attributes can be configured. Figure 3 As shown, taking the specific medical tag B0302 surgical information as an example, the basic information and tag attributes configured for the tag can include: category, cardinality, gender restriction, age restriction, data type, validity rules, validity period, expiration handling, acquisition method, and search conditions. The composition information and tag attributes configured for the tag can include: node name, node meaning, data type, field length, encoding table, deduplication criteria, search conditions, and operations. Among these, data types can include simple tags and composite tags. Simple tags contain only one field, while composite tags can contain multiple fields.

[0095] According to the exemplary implementation of this application, by establishing a multi-level tagging system and defining the tags in each level of the multi-level tagging system, the relationship between tags and data, and the relationship between tags, can be better displayed, which is beneficial to the management and maintenance of tags.

[0096] In an exemplary embodiment of this application, the data processing module 2300 can be used to configure corresponding data processing rules based on a multi-level tag system, and to process preprocessed data based on the data processing rules to obtain target tags and corresponding target data. First, the data processing module 2300 can directly extract data from the preprocessed data to obtain a first target tag and first target data. Obtaining the first target tag and first target data may include: filtering tags in the multi-level tag system to obtain a first target tag, wherein the first target tag is a directly extracted tag; configuring a first data extraction rule based on the first target tag; and extracting data from the preprocessed data based on the first data extraction rule to obtain the first target data.

[0097] For example, direct extraction can directly extract relevant information from various business tables or only require simple data transformation to obtain the corresponding information. Therefore, the tags in the multi-level tag system can be filtered first, and tags that can be directly extracted can be selected as the first target tags. Then, the first data extraction rules can be configured based on the first target tags. The process of configuring the first data extraction rules is as follows: Select business table → Set extraction conditions (i.e., certain fields in the business table meet the extraction conditions, such as equal to, not equal to, greater than, or less than a certain value, before extraction can be performed) → Select mapping fields (select the mapping fields corresponding to the first target tags in the business tables) → Set data transformation method. Then, the preprocessed data is extracted based on the first data extraction rules to obtain the first target data. For example, surgical information in the business tables of the preprocessed data can be extracted using the first data extraction rules to obtain the corresponding first target data, such as surgical name, surgical date, surgical institution name, etc.

[0098] According to the exemplary implementation of this application, preprocessed data is directly extracted based on the first target label to obtain the corresponding first target data. Through simple data transformation and mapping, there is no need for developers to write scripts to extract data, which can reduce the difficulty of obtaining residents' medical profile labels to a certain extent.

[0099] In an exemplary embodiment of this application, the priority of the first target label can also be established based on the label establishment module 2200. For example, a first target label of the resident identification category, such as a name or ID card number, can be set as the first priority. During data extraction, data corresponding to the first target label with the first priority should be extracted first, and so on. By setting the priority of the first target label, the extraction progress of the first target data can be optimized, and the accuracy of the association between the first target data and the first target label can be improved.

[0100] In an exemplary embodiment of this application, the first target data can be further processed based on the data processing module 2300 to obtain a second target label and second target data. Obtaining the second target label and second target data may include: analyzing and processing the first target data to generate the second target data; and selecting a second target label associated with the second target data.

[0101] For example, by analyzing the first target data, the transformation method of the first target data can be determined. This transformation method can include basic data transformation methods and special data transformation methods, allowing the first target data to be transformed to obtain the second target data. Further, a second target tag associated with the second target data is selected in the tagging system. For instance, the first target data can be used to determine whether a resident has undergone surgery based on their surgical information (surgery name, surgery date, surgical institution name, etc.), thus obtaining the second target data, i.e., whether the resident has undergone surgery. Then, the corresponding surgical history is associated with the second target data in the tagging system. Figure 2 The second target data can be filtered based on the configuration information of the second target label. For example, the second target data can be filtered based on the time range specified by the second target label.

[0102] According to the exemplary implementation of this application, by analyzing and processing the first target data to obtain the second target data and associating it with the second target label, the first target data can be further simplified, which is beneficial to simplifying the subsequent data analysis process and can improve the efficiency of generating medical profile labels to a certain extent.

[0103] In an exemplary embodiment of this application, since residents' medical data is updated rapidly, it is necessary to obtain the latest medical data of residents to predict their medical profile labels in order to generate more accurate medical profile labels. Therefore, after obtaining the first target data, the second target data, the first target label, and the second target label, the initial medical data of residents can be further detected based on the data processing module 2300. Detecting the initial medical data of residents may include: obtaining time information from the target data; selecting the latest data acquisition time from the time information and comparing the latest data acquisition time with a preset time; detecting whether updated initial medical data exists in response to the latest data acquisition time being earlier than the preset time; and obtaining the target label corresponding to the updated initial medical data in response to the existence of updated initial medical data.

[0104] For example, time information is acquired from the first target data and / or the second target data. The first target data and / or the second target data may contain multiple time information items. The latest data acquisition time is selected from these multiple time information items, and then compared with a preset time. The preset time can be set to 00:00 every day. If the latest data acquisition time is earlier than the preset time, an incremental data processing procedure can be performed, i.e., detecting whether there is an update to the initial medical data. If there is an update to the initial medical data, the first target label and / or the second target label corresponding to the updated initial medical data are acquired. The acquisition of the first target label and / or the second target label corresponding to the updated initial medical data has been described in detail above and will not be elaborated further here.

[0105] According to an exemplary implementation of this application, the system detects whether updated initial medical data exists based on a preset time interval. If updated initial medical data exists, the target tag corresponding to the updated initial medical data is obtained. By detecting the initial medical data through a preset time interval, the updated initial medical data only needs to be processed based on the original data processing rules. This improves the flexibility of tag management while ensuring that the target tag is obtained based on the latest medical data.

[0106] In an exemplary embodiment of this application, the validity period of the target label can also be configured based on the label creation module 2200, and the validity period of the target label can be detected. If the validity period is greater than the validity period threshold, the corresponding target label is marked as an expired label. For example, different labels can be set with different validity periods. For instance, one label may have a validity period of one year. If it is detected that the validity period of the generated label exceeds one year, this label is set as an expired label. By setting the validity period of the label, the accuracy of the generated medical profile label can be improved to a certain extent.

[0107] In an exemplary embodiment of this application, the medical profile tag generation module 2400 can be used to set an evaluation model and generate medical profile tags for residents based on the evaluation model and evaluation information, wherein the evaluation information includes target tags and target data. Generating medical profile tags may include: obtaining parameter information corresponding to the evaluation model and obtaining corresponding evaluation information based on the parameter information; setting an evaluation period and generating medical profile tags for residents based on the evaluation model and evaluation information.

[0108] For example, a corresponding assessment model can be selected from the system's predefined assessment models, and the corresponding parameter information can be obtained. The requirements for the parameter information are analyzed to obtain the corresponding assessment information, which may include a first target label, a second target label, first target data, and second target data. This will be illustrated using a cardiovascular disease risk assessment model as an example. Figure 8 As shown, the parameters of the cardiovascular disease risk assessment model include date of birth, systolic blood pressure, body mass index (BMI), total cholesterol, smoking status, and diabetes markers. Based on the data type requirements in the parameter information, a first or second target label is determined, and the corresponding first or second target data is obtained. Taking BMI as an example, it requires the resident's height and weight, calculated using the BMI formula. The first target label includes the resident's height and weight, obtaining the corresponding first target data. After analyzing and processing the first target data, the corresponding second target data (i.e., the resident's BMI index) can be obtained and associated with the corresponding second target label (BMI). Taking date of birth as an example, the resident's first target label (date of birth) can be directly associated, and the corresponding first target data (Year, Month, Day) can be obtained. Then, an assessment period is set, and the assessment information is filtered based on the assessment period to obtain the assessment information within that period. For example, if the assessment period for the cardiovascular disease risk assessment model is one year, then the assessment information for the resident within the past year will be filtered.

[0109] In an exemplary embodiment of this application, the saturation of the assessment information can be further determined based on the medical profile tag generation module 2400. Determining the saturation of the assessment information may include: identifying necessary information in the parameter information and detecting the assessment information based on the necessary information; determining the data saturation of the assessment information in response to the assessment information containing all necessary information, and comparing the data saturation of the assessment information with the data saturation threshold of the assessment model; and generating a medical profile tag corresponding to the resident in response to the data saturation of the assessment information being greater than or equal to the data saturation threshold.

[0110] For example, firstly, the necessary information in the parameter information is determined. This necessary information is indispensable for generating medical profile labels, such as the resident's identity information. Based on this necessary information, the evaluation information is checked. If the evaluation information does not contain all the necessary information, a prompt or marker can be generated, pausing the generation of the resident's medical profile label. If the evaluation information contains all the necessary information, the data saturation of the evaluation information can be further determined and compared with the data saturation threshold of the evaluation model. Since not all target data corresponding to the target label can be obtained when acquiring resident information, it is necessary to determine the data saturation of the evaluation information to ensure more accurate medical profile labels. For example, the data saturation threshold is 70%. When the data saturation of the evaluation information reaches 70%, the resident's medical profile label can be further generated. For example, a cardiovascular disease risk assessment model generates a resident's medical profile label by comprehensively analyzing the evaluation information. The resident's medical profile label can include various output formats; for example, the resident's medical profile label is the resident's risk level for cardiovascular disease.

[0111] According to the exemplary implementation of this application, by setting necessary information in the parameter information and detecting the evaluation information based on the necessary information, the evaluation information can be initially detected. If any necessary information is missing, no medical profile label for the resident will be generated, which can improve the accuracy and efficiency of generating the resident's medical profile label to a certain extent. Furthermore, after determining that the evaluation information contains all necessary information, further detecting the data saturation of the evaluation information can further ensure the accuracy of generating the resident's medical profile label.

[0112] This application also provides an electronic device and a computer-readable storage medium. Figure 11 This is a schematic diagram of the structure of an electronic device 3000 adapted to implement embodiments of the present disclosure, according to an embodiment of the present disclosure.

[0113] The following is for reference. Figure 11 The diagram illustrates a structural schematic of an electronic device 3000 suitable for implementing embodiments of the present disclosure. Terminal devices in embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 11 The terminal device / server shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0114] like Figure 11As shown, the electronic device 3000 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 3100, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 3200 or a program loaded from a storage device 3800 into a random access memory (RAM) 3300. The RAM 3300 also stores various programs and data required for the operation of the electronic device 3000. The processing unit 3100, the ROM 3200, and the RAM 3300 are interconnected via a bus 3400. An input / output (I / O) interface 3500 is also connected to the bus 3400.

[0115] Typically, the following devices can be connected to the I / O interface 3500: input devices 3600 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 3700 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 3800 including, for example, magnetic tapes, hard disks, etc.; and communication devices 3900. The communication device 3900 allows the electronic device 3000 to communicate wirelessly or wiredly with other devices to exchange data. Although... Figure 11 An electronic device 3000 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 11 Each box shown can represent a device or multiple devices as needed.

[0116] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 3900, or installed from a storage device 3800, or installed from a ROM 3200. When the computer program is executed by a processing device 3100, it performs the functions defined in the methods of embodiments of this disclosure.

[0117] It should be noted that the computer-readable medium described in the embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the embodiments of this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the embodiments of this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0118] The aforementioned computer-readable medium may be included in the aforementioned electronic device or may exist independently without being assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, enable the electronic device to: acquire residents' initial medical data and preprocess the initial medical data to obtain preprocessed data; establish a multi-level tagging system and define tags in each level of the tagging system; configure corresponding data processing rules based on the multi-level tagging system and process the preprocessed data based on the data processing rules to obtain target tags and corresponding target data; and set an evaluation model and generate residents' medical profile tags based on the evaluation model and evaluation information, wherein the evaluation information includes target tags and target data.

[0119] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0121] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating medical profile tags, characterized in that, The method includes: Acquire residents' initial medical data and preprocess the initial medical data to obtain preprocessed data; Establish a multi-level tagging system and define the tags in each level of the tagging system; Based on the multi-level tagging system, corresponding data processing rules are configured, and the preprocessed data is processed according to the data processing rules to obtain target tags and corresponding target data; and An assessment model is set up, and medical profile tags for residents are generated based on the assessment model and assessment information, wherein the assessment information includes the target tags and the target data; Obtain the parameter information corresponding to the evaluation model, first determine the necessary information in the parameter information, and detect the evaluation information based on the necessary information; when the evaluation information contains all the necessary information, determine the data saturation of the evaluation information, and compare the data saturation with the data saturation threshold of the evaluation model; when the data saturation of the evaluation information is greater than or equal to the threshold, generate the medical profile label corresponding to the resident. Configure an expiration period for the target label and check the expiration period. If the expiration period is greater than the expiration period threshold, mark the corresponding target label as an expired label.

2. The method for generating medical profile tags according to claim 1, characterized in that, Based on the multi-level tagging system, corresponding data processing rules are configured, and the preprocessed data is processed according to the data processing rules to obtain target tags and corresponding target data, including: The tags in the multi-level tag system are filtered to obtain a first target tag, wherein the first target tag is a directly extracted tag; Configure a first data extraction rule based on the first target label; and The preprocessed data is extracted based on the first data extraction rule to obtain the first target data.

3. The method for generating medical profile tags according to claim 2, characterized in that, Based on the multi-level tagging system, corresponding data processing rules are configured, and the preprocessed data is processed based on the data processing rules to obtain target tags and corresponding target data, which also includes: The first target data is analyzed and processed to generate the second target data; and Select a second target label associated with the second target data.

4. The method for generating medical profile tags according to claim 3, characterized in that, Set up an assessment model, and generate medical profile tags for residents based on the assessment model and assessment information, including: Obtain the parameter information corresponding to the evaluation model, and obtain the corresponding evaluation information based on the parameter information; Set an assessment cycle and generate the resident's medical profile label based on the assessment model and the assessment information.

5. The method for generating medical profile tags according to claim 2, characterized in that, After filtering the tags in the multi-level tagging system to obtain the first target tag, the process also includes: Set the priority of the first target label.

6. The method for generating medical profile tags according to claim 4, characterized in that, Before generating the resident's medical profile label based on the assessment model and the assessment information, the method further includes: Obtain the time information from the target data; Select the latest data acquisition time from the time information and compare the latest data acquisition time with a preset time; In response to the latest data acquisition time being earlier than the preset time, it is detected whether there is an update to the initial medical data; In response to the existence of the updated initial medical data, the target label corresponding to the updated initial medical data is obtained.

7. A device for generating medical portrait tags, characterized in that, The device includes: The preprocessing module is used to acquire residents' initial medical data and preprocess the initial medical data to obtain preprocessed data; The tag creation module is used to create a multi-level tag system and define the tags in each level of the tag system; A data processing module is used to configure corresponding data processing rules based on the multi-level tagging system, and to process the preprocessed data based on the data processing rules to obtain target tags and corresponding target data; and A medical profile tag generation module is used to set up an assessment model and generate medical profile tags for residents based on the assessment model and assessment information, wherein the assessment information includes the target tag and the target data; Obtain the parameter information corresponding to the evaluation model, first determine the necessary information in the parameter information, and detect the evaluation information based on the necessary information; when the evaluation information contains all the necessary information, determine the data saturation of the evaluation information, and compare the data saturation with the data saturation threshold of the evaluation model; when the data saturation of the evaluation information is greater than or equal to the threshold, generate the medical profile label corresponding to the resident. Configure an expiration period for the target label and check the expiration period. If the expiration period is greater than the expiration period threshold, mark the corresponding target label as an expired label.

8. An electronic device, characterized in that, include: A processor, adapted to execute computer programs; as well as A computer-readable storage medium storing a computer program that, when executed by the processor, implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the method as described in any one of claims 1 to 6.

Images