Physical examination item combination generation method and related device

Abstract

The embodiment of the invention provides a physical examination item combination generation method and a related device. The physical examination item combination generation method comprises the following steps: analyzing according to user information to obtain concerned health information corresponding to the user information, and determining a recommended physical examination item identifier subset corresponding to the user information in combination with a standard physical examination item identifier set according to the concerned health information which can represent that the user information represents a potential health risk that a user needs to pay attention; as the physical examination items represented by the recommended physical examination item identification subsets accord with the concerned health field, the recommended mechanism item identification subsets corresponding to the physical examination mechanisms can be generated corresponding to the recommended physical examination item identification subsets by using the specified mapping relationship between the standard physical examination item identification set and the mechanism physical examination item identification sets of the multiple physical examination mechanisms; the physical examination items in the recommendation mechanism item identification subset form a physical examination item combination. According to the physical examination item combination generation method and the related device, the physical examination item combination adaptive to the actual health condition of the user can be generated.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a method for generating a combination of physical examination items and related devices. Background Art

[0002] With the development of computer technology, the combination of offline physical examination items and online health management platforms has become the mainstream way of health management. Online health management platforms are used to provide users with a variety of physical examination packages based on experience and market demand for users to choose from. After users select a physical examination package, they can go to an offline physical examination institution to complete the physical examination items specified in the physical examination package.

[0003] However, the physical examination packages provided to users are composed of a fixed combination of physical examination items, while the actual health conditions of different users vary greatly, and the fixed combination of physical examination items is difficult to adapt to the actual health conditions of users. Summary of the invention

[0004] In view of this, multiple embodiments of the present application are dedicated to providing a method for generating a physical examination item combination and a related device, which can generate a physical examination item combination that is suitable for the user's actual health condition.

[0005] One embodiment of the present application provides a method for generating a combination of physical examination items, comprising: obtaining health information of concern corresponding to the user information based on user information analysis; wherein the health information of concern indicates that the user information represents potential health risks that the user needs to pay attention to; based on the health information of concern and a standard physical examination item identification set, obtaining a recommended physical examination item identification subset corresponding to the user information; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern; utilizing a specified mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions, generating a recommended institution item identification subset of the corresponding physical examination institution corresponding to the recommended physical examination item identification subset; wherein the physical examination items represented in the recommended institution item identification subset constitute the physical examination item combination.

[0006] One embodiment of the present application provides a device for generating a combination of physical examination items, including: a health concern information generation module, used to obtain health concern information corresponding to the user information based on user information analysis; wherein the health concern information indicates that the user information represents potential health risks that the user needs to pay attention to; a recommended physical examination item identification subset determination module, used to obtain a recommended physical examination item identification subset corresponding to the user information based on the health concern information and a standard physical examination item identification set; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health concern field; a recommended institution item identification subset determination module, used to generate a recommended institution item identification subset of a corresponding physical examination institution corresponding to the recommended physical examination item identification subset by utilizing a specified mapping relationship between the standard physical examination item identification set and the institution physical examination item identifications of multiple physical examination institutions; wherein the physical examination items represented in the recommended institution item identification subset constitute the physical examination item combination.

[0007] One embodiment of the present application provides a computer device, which includes a memory and a processor, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the method for generating a combination of physical examination items as described above.

[0008] One embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by a processor, the method for generating a combination of physical examination items as described above can be implemented.

[0009] One embodiment of the present application provides a computer program product, which is used to implement the method for generating a combination of physical examination items as described above.

[0010] In multiple implementations provided in the present application, health information of concern corresponding to the user information is obtained based on the analysis of the user information. Since the health information of concern can indicate that the user information represents the potential health risks that the user needs to pay attention to, the recommended physical examination item identification subset corresponding to the user information can be determined based on this in combination with the standard physical examination item identification set. Since the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern, the specified mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions can be used to generate a recommended institutional item identification subset of the corresponding physical examination institution corresponding to the recommended physical examination item identification subset. The physical examination items in the recommended institutional item identification subset constitute a physical examination item combination. Based on the above method, a physical examination item combination that is compatible with the actual health condition of the user can be generated. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1A schematic diagram of the interaction between a device for generating a combination of physical examination items and a user terminal provided in one embodiment of the present application.

[0012] Figure 2 A schematic diagram of an application scenario of a method for generating a combination of physical examination items provided in one embodiment of the present application.

[0013] Figure 3 A flowchart of a method for generating a combination of physical examination items provided in one embodiment of the present application.

[0014] Figure 4 A schematic diagram of modules of a device for generating a combination of physical examination items provided in one embodiment of the present application.

[0015] Figure 5 A schematic diagram of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0017] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0018] In the related technology, users go to hospitals or medical examination centers to purchase medical examination packages on site, and then go to the corresponding departments to complete the various medical examination items in the medical examination packages. In order to avoid the problem of poor medical examination experience caused by too many people taking medical examinations on a single day, the related technology combines offline medical examination packages with online health management platforms, so that users can make reservations for medical examination packages on the online health management platform to disperse the medical examination population to different days, which can avoid problems such as tight medical examination resources caused by too many people taking medical examinations on a single day to a certain extent.

[0019] Generally speaking, the medical examination packages that users can book on online health management platforms are designed by relevant personnel or institutions based on market demand. The medical examination items included in these medical examination packages are fixed, but the actual health conditions of different users are different. For users, fixed combinations of medical examination items will have the following problems: based on the actual health conditions of users, one or more medical examination items in the medical examination package are items that users do not need to check, or the actual health conditions of users indicate that the medical examination items that need to be done are not included in any medical examination package.

[0020] It can be seen that there is a problem of poor matching between the fixed combination of physical examination items provided by the relevant technology and the actual health condition of the user. It can also be understood that the fixed combination of physical examination items provided by the relevant technology is not personalized enough.

[0021] Therefore, it is necessary to provide a method for generating a combination of physical examination items, and obtain the health information of concern corresponding to the user information based on the analysis of the user information. Since the health information of concern can indicate that the user information represents the potential health risks that the user needs to pay attention to, the recommended physical examination item identification subset corresponding to the user information can be determined based on this and combined with the standard physical examination item identification set. Since the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern, the specified mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions can be used to generate the recommended institutional item identification subset of the corresponding physical examination institution, and the physical examination items in the recommended institutional item identification subset constitute the physical examination item combination. Based on the above method, a physical examination item combination that is suitable for the actual health condition of the user can be generated.

[0022] See also Figure 1 In the multiple embodiments provided in the present application, the method for generating a combination of physical examination items can be applied to an electronic device with certain computing capabilities and network access capabilities. The electronic device can be a desktop computer, a laptop computer, a tablet computer, or a server. The electronic device includes a processor, a memory, a display module, and a network access module for network communication.

[0023] The processor in the electronic device can analyze the user information to obtain health information of concern corresponding to the user information; wherein the health information of concern indicates that the user information represents potential health risks that the user needs to pay attention to. The processor in the electronic device obtains a subset of recommended physical examination item identifiers corresponding to the user information based on the health information of concern and the standard physical examination item identifier set; wherein the recommended physical examination item identifier subset belongs to the standard identifier set, and the physical examination items represented by the recommended physical examination item identifier subset are consistent with the health field of concern.

[0024] The processor in the electronic device uses the specified mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions to generate a recommended institutional item identification subset for the corresponding physical examination institution corresponding to the recommended physical examination item identification subset; wherein the physical examination items represented in the recommended institutional item identification subset constitute the physical examination item combination.

[0025] The memory in the electronic device can store the recommended organization item identification subset and the intermediate results generated in the process of generating the recommended organization item identification subset.

[0026] The display module in the electronic device can display the corresponding data when a viewing operation on any data in the memory is detected.

[0027] Furthermore, the network access module in the electronic device can push the combination of physical examination items based on the subset of recommended institution item identifiers to the user terminal.

[0028] See also Figure 2 . One embodiment of the present application provides an example of an application scenario of a method for generating a combination of physical examination items. The method for generating a combination of physical examination items can be applied to a scenario in which a user consults and purchases a combination of physical examination items. The scenario includes a platform for recommending a combination of physical examination items to a user and a user terminal. The user terminal is a program running on a user device. The user terminal can provide an interactive interface for implementing a question-and-answer function and obtain user information input by the user in the interactive interface, and send text information to the platform for recommending a combination of physical examination items to the user. The platform is a background processing system for analyzing user information and returning the analysis results to the user terminal. The platform can call a large language model interface to implement an intelligent recommendation function, or the platform is integrated with a large language model that can perform intelligent recommendation of physical examination item combinations.

[0029] Specifically, the platform for recommending physical examination item combinations to users vectorizes the identifiers in the standard physical examination item identifier set X before applying the large language model to the physical examination item combination recommendation. The standard physical examination item identifier set X includes: standard physical examination item X1, standard physical examination item X2, standard physical examination item X3...

[0030] Among them, the standard physical examination item X1 includes the item code represented by 123, the item name represented by blood routine examination, and the item description represented by "blood routine examination is a basic examination used to evaluate the health status of the blood by analyzing the number and morphology of various cellular components in blood samples. Routine examination items include red blood cells, white blood cells, hemoglobin, platelets, etc. The indicators in routine examination items can help detect anemia, infection, blood diseases and other diseases."

[0031] Among them, the standard physical examination item X2 includes the item code represented by 456, the item name represented by urine routine test, and the item description represented by "Urinalysis test is to evaluate the health status of the urinary system and other systems by analyzing various components in urine, such as urine protein, urine sugar, urine specific gravity, etc. Urinalysis test can help to detect kidney disease, urinary tract infection, diabetes and other diseases at an early stage."

[0032] Among them, the standard physical examination item X3 includes the item code represented by 789, the item name represented by electrocardiogram, and "Electrocardiogram is a non-invasive examination method that records the electrical activity of the heart by placing electrodes on the surface of the skin. It can help doctors assess the health of the heart and detect various heart diseases such as arrhythmia, myocardial ischemia, cardiac hypertrophy, myocardial infarction, etc. Specifically, it can reflect the heart's rhythm, frequency and the functional state of the heart's electrical conduction system by depicting the heart's electrical waveform."

[0033] Then, a vector representation set X' of standard physical examination items can be obtained, and the vector representation set X' of standard physical examination items includes: a vector representation X1' corresponding to standard physical examination item 1, a vector representation X2' corresponding to standard physical examination item 2, and so on.

[0034] Furthermore, the platform for recommending physical examination item combinations to users vectorizes the identifiers corresponding to each physical examination institution, specifically, vectorizes the identifiers in the physical examination item identifier set A={……, routine blood test, routine urine test, …} of physical examination institution A to obtain the physical examination item vector representation set A' of physical examination institution A, and the physical examination item vector representation set A' includes: vector representation A1 corresponding to routine blood test, vector representation A2 corresponding to routine urine test, …. And, vectorizes the identifiers in the physical examination item identifier set B={……, electrocardiogram test, routine blood test, …} of physical examination institution B to obtain the physical examination item vector representation set B' of physical examination institution B, and the physical examination item vector representation set B' includes: vector representation B1 corresponding to electrocardiogram test, vector representation B2 corresponding to routine blood test, ….

[0035] Furthermore, a platform for recommending physical examination item combinations to users constructs a first prompt instruction (prompt) including a standard physical examination item vector representation set and an institutional physical examination item vector representation set, so as to instruct the large language model to perform vector matching on the standard physical examination item vector representation set X' with the institutional physical examination item vector representation set A' of the physical examination institution A and the institutional physical examination item vector representation set B' of the physical examination institution B, respectively, to obtain a specified mapping relationship 1={……, 123-routine blood test, 456-routine urine test, …} that can represent the standard physical examination item vector representation set X' and the institutional physical examination item vector representation set A', and a specified mapping relationship 2={……, 789-electrocardiogram test, 123-routine blood test, …} that can represent the standard physical examination item vector representation set X' and the institutional physical examination item vector representation set B'.

[0036] Furthermore, a platform for recommending a combination of physical examination items to users provides a human-computer dialogue function to users based on a large language model. The user end extracts user information (such as the problem of frequent waking up at night) in the human-computer dialogue interface and feeds it back to the platform. When the large language model analyzes that the user has a potential risk of kidney disease based on the user information, it can output health information of concern containing the potential risk of kidney disease. Furthermore, the large language model can also derive a recommended physical examination item identification subset = {123} corresponding to the user information based on the potential risk of kidney disease and the standard physical examination item identification set X, and use the specified mapping relationship 1 and the specified mapping relationship 2 to generate a recommended institution item identification subset = {..., routine urine examination, ...} corresponding to the recommended physical examination item identification subset = {123} for the corresponding physical examination institution B. The physical examination items represented in the recommended institution item identification subset constitute a physical examination item combination.

[0037] Furthermore, the platform for recommending a combination of physical examination items to users generates and outputs physical examination necessity information corresponding to each recommended physical examination item identifier in the subset of recommended institution item identifiers (for example, if you get up more frequently at night, a routine urine test can help assist in diagnosing problems with the urinary system, kidneys, metabolism, and endocrine system).

[0038] Furthermore, the platform for recommending physical examination item combinations to users generates physical examination item recommendation information based on user information, physical examination necessity information, and each recommended physical examination item in the recommended physical examination item identification subset using a large language model and a second prompt instruction, and pushes it to the user end, and the user end can browse the physical examination item recommendation information in the human-computer dialogue interface. And, the platform for recommending physical examination item combinations to users sends the recommendation information corresponding to the recommended institution item identification subset to the user end. When the user end detects confirmation information for the recommendation information, it can generate a corresponding electronic order and send the electronic order to the physical examination institution B to help the user complete the online appointment for a personalized physical examination item combination.

[0039] After that, the user goes offline to complete the physical examination items in the above physical examination item combination. Physical examination institution B can upload the corresponding test report to the generation device of the physical examination item combination. When the user terminal requests to query the test report, the generation device of the physical examination item combination can return the test report for the user to review on the user terminal.

[0040] In this application scenario, it is possible to accurately recommend a combination of physical examination items based on user information, and provide users with services such as online physical examination appointments and physical examination report inquiries.

[0041] See also Figure 3. An embodiment of the present application provides a method for generating a combination of physical examination items. The method for generating a combination of physical examination items can be applied to a device for generating a combination of physical examination items. The device for generating a combination of physical examination items can be an electronic device with certain computing capabilities and network access capabilities. Of course, the device for generating a combination of physical examination items can also refer to a software program running in an electronic device. In this embodiment, the method for generating a combination of physical examination items can include the following steps.

[0042] Step S110: deriving health information of concern corresponding to the user information based on the user information analysis; wherein the health information of concern indicates that the user information represents potential health risks that the user needs to pay attention to.

[0043] Step S120: Based on the health information of concern and the standard physical examination item identification set, a recommended physical examination item identification subset corresponding to the user information is obtained; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern.

[0044] Step S130: utilizing the specified mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions, generate a recommended institutional item identification subset for the corresponding physical examination institution corresponding to the recommended physical examination item identification subset; wherein the physical examination items represented in the recommended institutional item identification subset constitute the physical examination item combination.

[0045] In this embodiment, the device for generating the physical examination item combination can collect user information through a human-computer dialogue interface, or determine the user information through reports, medical records and other information uploaded by the user, wherein the user information may include but is not limited to: age, gender, medical history, demands, examination reports, and medical records.

[0046] For example, user information includes the following: gender - male, occupation - programmer, age - 40, height - 170CM, weight - 98KG, past medical history - fatty liver and gout, family medical history - diabetes, historical abnormal indicators - sinus arrhythmia and elevated alanine aminotransferase.

[0047] In this embodiment, the generation device of the combination of physical examination items can also obtain the health information of concern corresponding to the user information based on the analysis of the user information. The specific method is: using the large language model to determine the standard physical examination items that match the user information according to the matching degree between the information of each dimension in the user information and the standard physical examination items, and triggering the large language model according to the pre-set reference prompt instructions (such as, you are a health analyst, have the skills to assess the user's health status, and can point out the health areas that the user should focus on; Skill 1: Comprehensive analysis of health status; Skill 2: Identification of key health areas) and generate health information in accordance with the human-computer dialogue format (such as json) based on the matching standard physical examination items and send the health information to the user end, and the user end can display the health information in the human-computer dialogue interface for the user to browse. Among them, the large language model is based on a method (RAG) that combines information retrieval and generation models to determine the standard physical examination items that match the user information. Among them, the health information is used to prompt the user to pay attention to the potential health risks associated with the user information.

[0048] For example, health information to pay attention to includes: Field - Cardiovascular health; Reason - Age 40, Occupation as a programmer, may be sedentary, and has a record of sinus arrhythmia; Recommended monitoring indicators - heart rate, blood pressure, cholesterol level, blood sugar. Field - Liver function, Reason - There is a history of fatty liver, and the alanine aminotransferase (ALT) is high, indicating possible liver damage, recommended monitoring indicators - transaminase (ALT / AST), total bilirubin, liver B-ultrasound. Field - Metabolic health, Reason - Weight 98KG, BMI calculated as 33.6 (in the obese range), combined with family history of diabetes, there is a risk of metabolic syndrome, recommended monitoring indicators - fasting blood sugar, glycosylated hemoglobin (HbA1c), weight changes. Field - Joint health, Reason - Past history of gout, need to pay attention to uric acid level control to prevent recurrence, recommended monitoring indicators - uric acid level.

[0049] In this embodiment, the generation device of the physical examination item combination can also select standard physical examination items for assisting in detecting potential health risks from the standard physical examination item identification set based on the potential health risks contained in the health information of concern, so as to further obtain a recommended physical examination item identification subset. The recommended physical examination item identification subset includes the identification of the standard physical examination item, and the identification of the standard physical examination item can be a project code. The number of standard physical examination items included in the recommended physical examination item identification subset depends on the number of potential health risks. Among them, the standard physical examination item identification set is a set of identifications corresponding to multiple standard physical examination items stored by the generation device of the physical examination item combination. The standard physical examination items include specific project codes, project names, and project descriptions. In the same standard physical examination item, the project code, project name, and project description correspond to each other. The standard physical examination item is an examination or test used to diagnose a disease, assess health status, or monitor treatment effects. The identification corresponding to the standard physical examination item can be a project code.

[0050] In this embodiment, since different physical examination institutions may have different ways of expressing the same physical examination item, this application takes the standard physical examination item identification set as a benchmark to determine the designated mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions. Each designated mapping relationship can indicate the corresponding relationship between the physical examination item identification set of the corresponding institutional physical examination item identification set and the standard physical examination item identification set. The institutional physical examination item identification in the institutional physical examination item identification set is the item name. For example, the standard physical examination item identification set includes electrocardiogram (item code is 666), and the institutional physical examination item identification set includes electrocardiogram detection. The designated mapping relationships include: 666-electrocardiogram detection.

[0051] In this embodiment, when determining the recommended physical examination item identification subset, since the recommended physical examination item identification subset contains all standard physical examination items, it is possible to determine which institutional physical examination items the standard physical examination items in the recommended physical examination item identification subset correspond to in the institutional physical examination item identification set based on the specified mapping relationship. Based on this method, it can be determined that the recommended physical examination item identification subset corresponds to the recommended institutional item identification subset of each physical examination institution, and each recommended institutional item identification subset corresponds to the same combination of physical examination items but may correspond to different identifications (i.e., project names) for the same physical examination item. The recommended institutional item identification subset and the recommended physical examination item identification subset correspond to the same physical examination item, but the two have different representation methods for the same physical examination item. For example, it can also be understood that based on the above method, the names of the physical examination items that need to be recommended to the user in each physical examination institution can be determined.

[0052] For example, the recommended institution item identification subset corresponding to the medical examination institution A among the medical examination institutions includes: electrocardiogram items, liver ultrasound examination items, uric acid level detection, fasting blood sugar and glycosylated hemoglobin detection. The recommended institution item identification subset corresponding to the medical examination institution B among the medical examination institutions includes: electrocardiogram examination, liver ultrasound examination, uric acid level detection, fasting blood sugar and glycosylated hemoglobin detection.

[0053] It can be seen that the electrocardiogram, which is a standard physical examination item, is recorded as an electrocardiogram item in physical examination institution A and as an electrocardiogram examination in physical examination institution B. However, based on the previous steps, the electrocardiogram item has been associated with the electrocardiogram as a specified mapping relationship, and the electrocardiogram examination has been associated with the electrocardiogram as a specified mapping relationship. Therefore, when it is analyzed that the user needs to have an electrocardiogram, the physical examination items corresponding to the electrocardiogram in physical examination institutions A and B respectively can be identified and recommended to the user as recommended institution item identifiers.

[0054] In addition, since both physical examination institution A and physical examination institution B contain physical examination items that need to be recommended to users, this application recommends to users the recommended institution item identification subset corresponding to physical examination institution A and the recommended institution item identification subset corresponding to physical examination institution B, so that users can choose from physical examination institution A and physical examination institution B based on factors such as distance and preference.

[0055] The method for generating a combination of physical examination items provided in the implementation mode of the present application obtains health information of concern corresponding to the user information based on the analysis of the user information. Since the health information of concern can indicate that the user information represents the potential health risks that the user needs to pay attention to, the recommended physical examination item identification subset corresponding to the user information can be determined based on this in combination with the standard physical examination item identification set. Since the physical examination items represented by the recommended physical examination item identification subset are consistent with the field of health concern, the specified mapping relationship between the standard physical examination item identification set and the institution physical examination item identification sets of multiple physical examination institutions can be used to generate a recommended institution item identification subset of the corresponding physical examination institution corresponding to the recommended physical examination item identification subset. The physical examination items in the recommended institution item identification subset constitute a physical examination item combination. Based on the above method, a physical examination item combination that is compatible with the actual health condition of the user can be generated.

[0056] In some embodiments, the device for generating a combination of physical examination items can vectorize the physical examination items corresponding to the standard physical examination item identification set to obtain a standard physical examination item vector representation set; vectorize the institutional physical examination item identification set corresponding to the multiple physical examination institutions to obtain the institutional physical examination item vector representation set of the physical examination institutions; and vector match the standard physical examination item vector representation set with the institutional physical examination item vector representation sets of the multiple physical examination institutions respectively to obtain the specified mapping relationship.

[0057] In this embodiment, since the same physical examination item can be stored in different forms between different physical examination institutions in the related art, and there are also differentiated representations for what is essentially the same physical examination item between the standard physical examination item identification sets stored in the generation device of the physical examination item combination, however, the differentiated representations for the same physical examination item are likely to affect the recommendation efficiency of the physical examination item combination. In order to achieve more efficient recommendation of physical examination item combinations, the generation device of the physical examination item combination can vectorize the physical examination items corresponding to the standard physical examination item identification set to obtain a vector representation set of standard physical examination items.

[0058] In some embodiments, the model used to perform vectorization can be any of the following models: bag of words model (BoW), term frequency-inverse document frequency model (TF-IDF), word vector model (Word2Vec), global vector word representation model (GloVe), bidirectional encoder representation model (BERT), document vectorization model (Doc2Vec), transformer model (Transformer).

[0059] In this embodiment, vectorization refers to converting the physical examination items in the standard physical examination item identification set into standard physical examination item vector representations in numerical form based on a model used to perform vectorization, thereby obtaining the standard physical examination item vector representation corresponding to each physical examination item in the standard physical examination item identification set, and each standard physical examination item vector representation can constitute a standard physical examination item vector representation set.

[0060] In this embodiment, the physical examination items in the standard physical examination item identification set may include: item code, item name, and item description. Among them, the item code is a unique representation of the physical examination item, and the item code can be composed of one or more of numbers, characters, and symbols, such as JK0015. The item name is a textual representation of the physical examination item, such as electrocardiogram, electrocardiogram item, electrocardiogram item, and electrocardiogram examination. The item description is the detailed information of the physical examination item, and the item description includes but is not limited to: item details, applicable population, precautions, etc.

[0061] For example, there is one item in the standard physical examination item identification set, which is represented as follows: {Item code - JK0015; Item name - Uric acid level test; Item description - Uric acid level test is a blood test to assess the health of the liver. It is mainly used to detect whether the liver has damage, inflammation, dysfunction or disease, such as hepatitis, fatty liver, cirrhosis, etc. Common liver function indicators include transaminase (ALT, AST), total protein, albumin, total bilirubin, direct bilirubin, etc.}. Then, the project code - JK0015 is vectorized into [1,0,0,...,0], the project name - uric acid level test is vectorized into [0.25,-0.12,0.56,0.48,...,0.39], and the project description - uric acid level test is a blood test to assess the health of the liver. It is mainly used to detect whether the liver is damaged, inflamed, dysfunctional or has diseases such as hepatitis, fatty liver, cirrhosis, etc. Common liver function indicators include transaminase (ALT, AST), total protein, albumin, total bilirubin, direct bilirubin, etc. are vectorized into [0.15, 0.12, 0.10, 0.20, 0.11, 0.09,...,0.14]. Furthermore, the standard physical examination item vector representation corresponding to the above physical examination item can be obtained = ([1, 0, 0, ..., 0], [0.25, -0.12, 0.56, 0.48, ..., 0.39], [0.15, 0.12, 0.10, 0.20, 0.11, 0.09, ..., 0.14]), optionally, the standard physical examination item vector representation can also be [1, 0, 0, ..., 0], [0.25, -0.12, 0.56, 0.48, ..., 0.39], [0.15, 0.12, 0.10, 0.20, 0.11, 0.09, ..., 0.14] The fusion result. Based on the above method, each standard physical examination item in the standard physical examination item identification set can be vectorized to obtain a standard physical examination item vector representation set.

[0062] In this embodiment, in order to determine the mapping relationship between the standard physical examination item identification set and the physical examination item identification set of each institution to determine the physical examination item combination that meets the user's needs, the physical examination item combination generation device can vectorize the identification of the institutional physical examination item identification set corresponding to multiple physical examination institutions into an institutional physical examination item vector representation, thereby obtaining the institutional physical examination item vector representation of the identification set of each institutional physical examination item, that is, obtaining the institutional physical examination item vector representation set of each physical examination institution. Among them, the identification in the institutional physical examination item identification set is a unique representation of the corresponding institutional physical examination item, and the identification can be composed of one or more of numbers, characters, and symbols. The identification can be the project name of the institutional physical examination item (such as uric acid detection), or it can be a project code, project description, etc., which is not limited in this embodiment of the present application. In addition, vectorization refers to representing the identification as a vector, and the institutional physical examination item vector representation is a one-dimensional array that represents the institutional physical examination item.

[0063] In this embodiment, the device for generating the combination of physical examination items can perform vector matching on the vector representation sets of standard physical examination items with the vector representation sets of institutional physical examination items of multiple physical examination institutions, respectively, to obtain a specified mapping relationship. The specific implementation method is: perform vector similarity calculation on the vector representation sets of standard physical examination items with the vector representation sets of institutional physical examination items of multiple physical examination institutions, respectively, to obtain a specified mapping relationship corresponding to the vector representation sets of each institutional physical examination item. Among them, the specified mapping relationship includes the N standard physical examination items with the highest similarity corresponding to the vector representations of each institutional physical examination item in the corresponding institutional physical examination item vector representation set, and N is a positive integer. For example, the identifier corresponding to the institutional physical examination item vector representation is endoscope, and the N standard physical examination items with the highest similarity corresponding to the institutional physical examination item vector representation are colonoscopy and gastroscopy, respectively.

[0064] In this embodiment, the device for generating the physical examination item combination may store the specified mapping relationship in a local database to facilitate the local server to quickly call the specified mapping relationship.

[0065] In some embodiments, the device for generating a combination of physical examination items performs vector matching on the standard physical examination item vector representation set and the institutional physical examination item vector representation set of the multiple physical examination institutions respectively to obtain the specified mapping relationship, including: constructing a first prompt instruction including the standard physical examination item vector representation set and the institutional physical examination item vector representation set to instruct the large language model to output a specified mapping relationship representing the correspondence between the standard physical examination items and the institutional physical examination items based on the standard physical examination item vector representation set and the institutional physical examination item vector representation set.

[0066] In this embodiment, in order to improve the unified management of the institutional physical examination items of multiple physical examination institutions, the generation device of the physical examination item combination can construct a prompt instruction (prompt) including a set of standard physical examination item vector representations and a set of institutional physical examination item vector representations to instruct the large language model to output a specified mapping relationship representing the correspondence between the standard physical examination items and the institutional physical examination items based on the set of standard physical examination item vector representations and the set of institutional physical examination item vector representations. Based on the specified mapping relationship, it is convenient to uniformly manage the institutional physical examination items of multiple physical examination institutions. The specified mapping relationship includes a set of mapping relationships corresponding to multiple physical examination institutions respectively, and each mapping relationship included in the mapping relationship set is the relationship between the institutional physical examination items of the physical examination institution and the standard physical examination items. Among them, the prompt instruction refers to the input text that guides the large language model to generate specific content, which can help the large language model understand and respond to questions.

[0067] In some embodiments, a device for generating a combination of physical examination items can generate physical examination necessity information corresponding to each recommended physical examination item identifier in the subset of recommended physical examination item identifiers; wherein the physical examination necessity information represents the correlation between the corresponding recommended physical examination item identifier and the user information; trigger a large language model to generate physical examination item recommendation information based on the user information, the physical examination necessity information and each recommended physical examination item in the subset of recommended physical examination item identifiers using a second prompt instruction; wherein the second prompt instruction is used to indicate the generation format of the physical examination item recommendation information; and send the physical examination item recommendation information to the user end.

[0068] In this embodiment, in order to provide more diverse information as a basis for recommending physical examination item identification, the generation device of the physical examination item combination can trigger the large language model based on the second prompt instruction (such as, you are a medical examination assistant, you can recommend corresponding physical examination items based on the user's health information, and you have the following skills: health indicator assessment, inspection item recommendation), generate the physical examination necessity information corresponding to each recommended physical examination item identification in the recommended physical examination item identification subset, and each physical examination necessity information indicates the recommendation reason of the corresponding recommended physical examination item identification. Furthermore, based on the user information, the physical examination necessity information and each recommended physical examination item in the recommended physical examination item identification subset, the physical examination item recommendation information is generated, and the physical examination item recommendation information is sent to the user end in a specified format (such as json) for the user to browse. Among them, the second prompt instruction is used to indicate the generation format of the physical examination item recommendation information, and the generation format includes the fields that the physical examination item recommendation information should have, such as the recommended physical examination item identification, the physical examination necessity information, the health advice, etc.

[0069] For example, the recommended information for physical examination items includes: electrocardiogram - the user has a history of sinus arrhythmia, an abnormal indicator. The electrocardiogram is used to monitor the electrophysiological activity of the heart and evaluate whether the heart rhythm is normal, which is crucial for diagnosing heart rhythm problems; liver ultrasound - considering the past medical history of fatty liver and high alanine aminotransferase (ALT) in laboratory tests, liver ultrasound can evaluate liver fat deposition and structural changes, and monitor the progression of fatty liver; uric acid level test - the user has a history of gout, and uric acid level test is the key to monitoring gout control. Hyperuricemia is a risk factor for gout attacks - combined with dietary adjustments and drug treatment, regular testing is performed to maintain uric acid within the target range.

[0070] In some embodiments, the device for generating a combination of physical examination items can generate recommendation information based on the recommended institution item identifier subset, and send the recommendation information to the user end; when confirmation information for the recommendation information fed back by the user end is detected, a corresponding electronic order is generated for the physical examination institution corresponding to the confirmation information and the corresponding recommended institution item identifier subset; and the electronic order is sent to the corresponding physical examination institution.

[0071] In this embodiment, in order to improve the convenience of online appointment for physical examination items, the generation device of the physical examination item combination can generate recommendation information based on the subset of recommended institution item identifiers, and send the recommendation information to the user end. The recommendation information is used to suggest the user to make an appointment for the physical examination items of the institution corresponding to each recommended institution item identifier. When receiving the confirmation information fed back by the user end for the recommendation information, the corresponding electronic order can be automatically generated and automatically sent to the corresponding physical examination institution to complete the automated physical examination appointment. For the physical examination institution, the actual user needs can be understood based on the recommended institution item identifiers contained in the electronic order, so as to improve more diversified physical examination packages. For the user end, the automated appointment of personalized physical examination item combinations can be completed through simple operations, saving user operations.

[0072] In some embodiments, the device for generating the physical examination item combination can return the test report to the user terminal corresponding to the user identifier upon receiving the test report for the electronic order uploaded by the corresponding physical examination institution and upon detecting a query request for the electronic order from the user identifier corresponding to the user information.

[0073] In this embodiment, in order to provide users with one-stop services such as recommendation, order booking, and report query, the physical examination item combination generating device can return the test report to the user terminal corresponding to the user ID when receiving the test report for the electronic order uploaded by the corresponding physical examination institution and detecting the query request for the electronic order. The test report includes the test results of various items actually completed by the user offline. The test report may include but is not limited to: text, images, etc.

[0074] See also Figure 4 . One embodiment of the present application also provides a device for generating a combination of physical examination items. The device for generating a combination of physical examination items may include: a health information generation module, which is used to obtain health information of concern corresponding to the user information based on user information analysis; wherein the health information of concern indicates that the user information represents potential health risks that the user needs to pay attention to; a recommended physical examination item identification subset determination module, which is used to obtain a recommended physical examination item identification subset corresponding to the user information based on the health information of concern and the standard physical examination item identification set; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern; a recommended institution item identification subset determination module, which is used to generate a recommended institution item identification subset of the corresponding physical examination institution corresponding to the recommended physical examination item identification subset by using the specified mapping relationship between the standard physical examination item identification set and the institution physical examination item identifications of multiple physical examination institutions; wherein the physical examination items represented in the recommended institution item identification subset constitute the physical examination item combination.

[0075] In this embodiment, the specific functions and effects achieved by the device for generating a combination of physical examination items can be explained with reference to other embodiments of the present application and will not be described in detail here.

[0076] The embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor implements the method for generating a combination of physical examination items as described above.

[0077] The embodiment of the present application further provides a computer program product comprising instructions, and when the computer program product is executed by a processor, the method for generating a combination of physical examination items as described above is implemented.

[0078] See also Figure 5 The present embodiment may provide a computer device, the computer device comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, the instructions are executed by the one or more processors, so that the one or more processors implement the aforementioned method for generating a combination of physical examination items.

[0079] In some embodiments, the computer device may include a processor, a non-volatile storage medium, an internal memory, a communication interface, a display device, and an input device connected by a system bus. The non-volatile storage medium may store an operating system and related computer programs.

[0080] The user information or user account information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, etc.) involved in multiple implementation methods of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0081] It should be understood that the specific examples in this article are only intended to help those skilled in the art to better understand the embodiments of the present application, rather than to limit the scope of the present invention.

[0082] It can be understood that in the various implementations of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation methods of the present application.

[0083] It can be understood that the various embodiments described in this application can be implemented individually or in combination, and the embodiments of this application are not limited to this.

[0084] Unless otherwise stated, all technical and scientific terms used in the embodiments of the present application have the same meaning as those generally understood by those skilled in the art of the technical field of the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the scope of the present application. The term "and / or" used in the present application includes any and all combinations of one or more related listed items. The singular forms of "a kind of", "above" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0085] It can be understood that the processor of the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method implementation can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (DigitalSignal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiment of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0086] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasable PROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0087] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0092] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0093] The above is only a specific implementation of the present application, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating a combination of physical examination items, characterized in that: include: Obtaining health information of concern corresponding to the user information according to the user information analysis; wherein the health information of concern indicates that the user information represents a potential health risk that the user needs to pay attention to; Based on the health information of concern and the standard physical examination item identification set, a recommended physical examination item identification subset corresponding to the user information is obtained; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern; Utilizing the designated mapping relationship between the standard physical examination item identification set and the institutional physical examination item identification sets of multiple physical examination institutions, a recommended institutional item identification subset of the corresponding physical examination institution is generated corresponding to the recommended physical examination item identification subset; wherein the physical examination items represented in the recommended institutional item identification subset constitute the physical examination item combination.

2. The method according to claim 1, characterized in that The method further comprises: Vectorizing the physical examination items corresponding to the standard physical examination item identification set to obtain a vector representation set of the standard physical examination items; Vectorizing the identification of the physical examination items corresponding to the multiple physical examination institutions to obtain a vector representation set of the physical examination items of the physical examination institutions; Vector matching is performed on the standard physical examination item vector representation set and the institutional physical examination item vector representation sets of the multiple physical examination institutions respectively to obtain the specified mapping relationship.

3. The method according to claim 2, characterized in that The step of performing vector matching on the standard physical examination item vector representation set and the institutional physical examination item vector representation sets of the multiple physical examination institutions to obtain the specified mapping relationship includes: Construct a first prompt instruction including the standard physical examination item vector representation set and the institutional physical examination item vector representation set to instruct the large language model to output a specified mapping relationship representing the correspondence between the standard physical examination items and the institutional physical examination items based on the standard physical examination item vector representation set and the institutional physical examination item vector representation set.

4. The method according to claim 1, characterized in that: The method further comprises: Generate physical examination necessity information corresponding to each recommended physical examination item identifier in the recommended physical examination item identifier subset; wherein the physical examination necessity information represents the correlation between the corresponding recommended physical examination item identifier and the user information; The large language model is triggered to generate recommended physical examination item information using a second prompt instruction based on the user information, the physical examination necessity information and each recommended physical examination item in the recommended physical examination item identification subset; wherein the second prompt instruction is used to indicate a generation format of the recommended physical examination item information; The physical examination item recommendation information is sent to the user terminal.

5. The method according to claim 1, characterized in that The method further comprises: Generate recommendation information based on the recommended organization item identifier subset, and send the recommendation information to the user terminal; When confirmation information for the recommendation information fed back by the user terminal is detected, a corresponding electronic order is generated for the physical examination institution corresponding to the confirmation information and a corresponding subset of recommended institution item identifiers; The electronic order is sent to the corresponding medical examination institution.

6. The method according to claim 5, characterized in that The method further comprises: When the test report for the electronic order uploaded by the corresponding physical examination institution is received, and when the query request for the electronic order by the user identifier corresponding to the user information is detected, the test report is returned to the user terminal corresponding to the user identifier.

7. A device for generating a combination of physical examination items, characterized in that: include: A health concern information generation module, used to obtain health concern information corresponding to the user information according to the user information analysis; wherein the health concern information indicates that the user information represents a potential health risk that the user needs to pay attention to; A recommended physical examination item identification subset determination module, used to obtain a recommended physical examination item identification subset corresponding to the user information based on the health information of concern and the standard physical examination item identification set; wherein the recommended physical examination item identification subset belongs to the standard identification set, and the physical examination items represented by the recommended physical examination item identification subset are consistent with the health field of concern; A recommended institution item identification subset determination module is used to generate a recommended institution item identification subset of the corresponding physical examination institution corresponding to the recommended physical examination item identification subset by utilizing the specified mapping relationship between the standard physical examination item identification set and the institution physical examination item identifications of multiple physical examination institutions; wherein the physical examination items represented in the recommended institution item identification subset constitute the physical examination item combination.

8. A computer device, characterized in that: The computer device includes a memory and a processor, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the method for generating a combination of physical examination items according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by a processor, the method for generating a combination of physical examination items according to any one of claims 1 to 6 can be implemented.

10. A computer program product, characterized in that The computer program product is used to implement the method for generating a combination of physical examination items as described in any one of claims 1 to 6.

Images