Vaccine recommendation method, device and equipment and storage medium

Abstract

The invention relates to the technical field of data analysis, can be applied to the field of medical health, and provides a vaccine recommendation method and device, equipment and a storage medium. According to the method, the matching degree of a target user and candidate vaccines is determined by obtaining validity scores corresponding to the candidate vaccines, adverse reaction probabilities corresponding to the candidate vaccines, risk probability values of target infectious disease infection of the target user and disease severity, and the target infectious disease is detected according to the matching degree of the target user and various candidate vaccines. When the method is applied to the field of medical health, the accuracy of vaccination can be improved, and the vaccination safety of the user can be guaranteed.

Description

Recommended methods, devices, equipment and storage media for vaccines Technical Field

[0001] This application relates to the technical field of data analysis, and can be used in the medical and health field, particularly to a vaccine recommendation method, apparatus, device, and storage medium. Background Technology

[0002] Vaccination, as a crucial means of preventing infectious diseases, is widely used globally to safeguard public health. With the accelerating arrival of the digital healthcare era, artificial intelligence technology is permeating the medical and health field and gradually empowering the vaccination sector. Current medical platforms typically generate standardized vaccination schedules for users based on national immunization program guidelines. While this meets the general public's vaccination needs, the accuracy of vaccination is relatively low, making it difficult to guarantee vaccine safety for users. Therefore, improving vaccination accuracy to ensure user safety has become a critical issue that urgently needs to be addressed. Summary of the Invention

[0003] The main purpose of this application is to provide a vaccine recommendation method, apparatus, device, and storage medium that can be applied in the medical and health field, aiming to improve the accuracy of vaccination and thus ensure the safety of users' vaccination.

[0004] In a first aspect, this application provides a vaccine recommendation method, comprising: obtaining a vaccination query request, the vaccination query request including personal information of a target user to be vaccinated; extracting a feature vector of the target user's personal information from the vaccination query request; querying a preset knowledge graph based on the feature vector corresponding to the target user for candidate vaccines matching the target user, the effectiveness score of the candidate vaccines, and the probability of adverse reactions corresponding to the candidate vaccines; obtaining an infectious disease risk map, the infectious disease risk map recording the probability values ​​of infection with a target infectious disease corresponding to multiple administrative regions, the target infectious disease including infectious diseases that can be prevented by vaccination with the candidate vaccines; determining the probability value of the target user's infection with the target infectious disease and the severity of the disease after the target user is infected with the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user; determining the degree of matching between the target user and the candidate vaccines based on the effectiveness score of the candidate vaccines, the probability of adverse reactions corresponding to the candidate vaccines, the probability value of the target user's infection with the target infectious disease, and the severity of the disease; and generating a vaccination recommendation for the target user based on the degree of matching between the target user and multiple candidate vaccines.

[0005] Secondly, this application also provides a vaccine recommendation device, comprising: a first acquisition module for acquiring a vaccination query request, the vaccination query request including personal information of a target user to be vaccinated; an information extraction module for extracting feature vectors of the target user's personal information from the vaccination query request; a data query module for querying, based on the feature vectors corresponding to the target user, candidate vaccines matching the target user, the effectiveness scores of the candidate vaccines, and the adverse reaction probabilities of the candidate vaccines in a preset knowledge graph; and a second acquisition module for acquiring an infectious disease risk map, the infectious disease risk map recording the risk probability values ​​of infection with target infectious diseases corresponding to multiple administrative regions. The target infectious disease includes infectious diseases that can be prevented by vaccination with the candidate vaccine; a first data determination module is used to determine the risk probability value of the target user contracting the target infectious disease and the severity of the disease after the target user is infected with the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user; a second data determination module is used to determine the matching degree between the target user and the candidate vaccine based on the effectiveness score corresponding to the candidate vaccine, the adverse reaction probability corresponding to the candidate vaccine, the risk probability value of the target user contracting the target infectious disease, and the severity of the disease; a data generation module is used to generate vaccination recommendations for the target user based on the matching degree between the target user and multiple candidate vaccines.

[0006] Thirdly, this application also provides a computer device, the computer device including a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the steps of the vaccine recommendation method as described above.

[0007] Fourthly, this application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the vaccine recommendation method as described above.

[0008] This application provides a vaccine recommendation method, apparatus, device, and storage medium. The method involves obtaining a vaccination query request, first extracting a feature vector of the target user's personal information from the query request, then querying a pre-defined knowledge graph based on the target user's feature vector to obtain candidate vaccines matching the target user, their corresponding efficacy scores, and their corresponding adverse reaction probabilities. Subsequently, by combining an infectious disease risk map with the target user's feature vector, the risk probability of the target user contracting a target infectious disease and the severity of the disease after infection are further determined. Based on the candidate vaccine's efficacy score, adverse reaction probability, risk probability, and severity, the matching degree between the target user and the candidate vaccine is calculated. Finally, a suitable vaccination recommendation is generated based on the matching degree. This method avoids the problems of traditional vaccine recommendation methods that focus only on protective benefits while neglecting vaccination safety or vice versa. By transforming the expected benefits and potential risks of vaccination from qualitative judgment to quantitative calculation, the vaccine recommendation results are more accurate, ensuring the user's vaccination safety. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 is a flowchart illustrating the steps of a vaccine recommendation method provided in an embodiment of this application; Figure 2 is a flowchart illustrating a sub-step of the vaccine recommendation method in Figure 1; Figure 3 is a scene diagram illustrating an infectious disease risk map provided in an embodiment of this application; Figure 4 is a flowchart illustrating another sub-step of the vaccine recommendation method in Figure 1; Figure 5 is a flowchart illustrating another sub-step of the vaccine recommendation method in Figure 1; Figure 6 is a scene diagram illustrating the vaccine recommendation method in Figure 1; Figure 7 is a schematic block diagram illustrating a vaccine recommendation device provided in an embodiment of this application; Figure 8 is a schematic block diagram illustrating a computer device provided in an embodiment of this application.

[0011] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0013] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0014] This application provides a vaccine recommendation method, apparatus, device, and storage medium. The vaccine recommendation method can be applied to a terminal device or a server. The terminal device can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device. The server can be a single server or a server cluster composed of multiple servers. The following explanation uses the application of the vaccine recommendation method to a server as an example.

[0015] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0016] Please refer to Figure 1, which is a schematic flowchart of a vaccine recommendation method provided in an embodiment of this application.

[0017] As shown in Figure 1, the recommended method for this vaccine includes steps S101 to S107.

[0018] Step S101: Obtain a vaccination query request, which includes the personal information of the target user to be vaccinated.

[0019] The target users for vaccination refer to those who actively initiate vaccination inquiry requests and have a need for vaccination. When users are unsure which vaccine they should receive or the optimal time for vaccination, they initiate a vaccination inquiry request on their terminal device to seek vaccination recommendations tailored to their health condition and actual needs. The vaccination inquiry request includes the target user's personal information. This personal information may include at least two of the following: basic demographic information, clinical health records, genetic and biomarker data, past vaccination history and reaction records, and user behavior data. Basic demographic information may include the target user's age, gender, body mass index (BMI), etc.; clinical health records may include the target user's chronic disease history (such as diabetes, cardiovascular disease, etc.) and medication use (such as immunosuppressants), etc.; past vaccination history and reaction records may include the types of vaccines previously administered, the number of doses, the date of administration, and adverse reactions (such as fever level), etc.; user behavior data may include data affecting immunity, such as sleep quality, exercise frequency, smoking and drinking habits, etc.

[0020] For example, a target user enters the query text "Hello, I am 68 years old, have a 5-year history of hypertension, and have no vaccine allergies. I would like to consult which vaccine is suitable for me and what precautions I should take when getting vaccinated?" on the online service platform of the hospital's official website. The query text is semantically cleaned to remove redundant data, resulting in the semantically cleaned query text "I am 68 years old, have a 5-year history of hypertension, have no history of vaccine allergies, and would like to consult which vaccine is suitable for me and what precautions to take when getting vaccinated." The semantically cleaned query text is then processed through algorithms such as entity recognition and intent classification to obtain the vaccine vaccination query request, specifically as follows: Vaccine vaccination query request {health characteristics: {age: 68 years old, underlying medical history: hypertension (5 years), vaccine allergy history: none}, core request: matching suitable vaccine + obtaining vaccination precautions}, which facilitates subsequent feature extraction of the vaccine vaccination query request.

[0021] Step S102: Extract the feature vector of the target user's personal information from the vaccination query request.

[0022] After processing by algorithms such as entity recognition, intent classification, and vector encoding, the vaccine inquiry request extracts structured information representing the core meaning of the question. Based on this structured information, a feature vector of the target user's personal information is generated. The feature vector of the target user's personal information can cover entities (such as age, basic medical history, and vaccine allergy history), intent (such as consulting about suitable vaccines), context (such as duration of medical history), constraints (such as no history of vaccine allergy), and semantic vectors (numerical vectors that quantify semantics).

[0023] It's important to note that by extracting feature vectors from target users' personal information in vaccination inquiry requests, scattered personal information can be transformed into structured feature vectors, laying the foundation for generating subsequent vaccination recommendations. These feature vectors not only reflect the target user's current health status but can also be used to predict trends in their health status through time series modeling. For example, they can predict the trend of the target user's immunity over the next 6-12 months. Time series modeling refers to a data analysis method that collects historical time series data of the target user's immunity-related indicators, analyzes their patterns over time, and then extrapolates the future trend of immunity. Based on this prediction, targeted recommendations for vaccination timing can be made, further improving the accuracy of vaccine recommendations.

[0024] For example, a target user seeking vaccination inputs on a terminal device: "Hello, I am 68 years old this year, have a 5-year history of hypertension, and have no allergies to any vaccines. I would like to consult which vaccine is suitable for me and what precautions I should take when getting vaccinated?" After processing by entity recognition and intent classification algorithms, the extracted structured information is as follows: (Entity: Age (68 years old), Basic medical history (hypertension, 5 years), Vaccine allergy history (none), Intent: Consultation on suitable vaccines and vaccination precautions, Context: 5-year history of hypertension, no history of vaccine allergy, Constraint: no history of vaccine allergy). Based on the above structured information, a feature vector is constructed in combination with preset dimension rules, and a quantized semantic vector is generated as follows: Structured feature vector: {Entity: [68 years old, hypertension (5 years), no history of vaccine allergy], Intent: Consultation on suitable vaccines and vaccination precautions, Context: 5-year history of hypertension + no history of allergies, Constraint: no contraindications to vaccination, Semantic vector: [0.15, -0.22, 0.30, -0.05, 0.28, ...]}. The semantic vector values ​​are generated by a vector encoding algorithm and are used to quantify the semantic features of the text.

[0025] Step S103: Based on the feature vector corresponding to the target user, query the preset knowledge graph for candidate vaccines that match the target user, the effectiveness score of the candidate vaccine, and the probability of adverse reactions of the candidate vaccine.

[0026] The pre-defined knowledge graph is a structured knowledge network centered on "entity-relationship-attribute," which can logically link scattered information related to vaccination. By collecting multi-source data such as clinical guidelines, drug instructions, clinical diagnosis and treatment data, and expert experience data, entity recognition algorithms (such as the BERT model) are used to extract core entities such as user health from the collected text data. Relation extraction algorithms are used to mine the logical relationships between entities, and the data is organized according to the "entity-relationship-attribute" triple format to construct the pre-defined knowledge graph.

[0027] Therefore, based on the feature vector corresponding to the target user, candidate vaccines matching the target user, their corresponding efficacy scores, and the probability of adverse reactions can be quickly retrieved from a pre-defined knowledge graph. It should be noted that candidate vaccines matching the target user refer to vaccine categories selected based on the target user's feature vector that are compatible with the target user's health condition and have no contraindications; the efficacy score of a candidate vaccine can be used to assess the protective effect the target user can obtain after receiving the candidate vaccine; and the probability of adverse reactions refers to the likelihood of the target user experiencing adverse reactions such as fever, local redness and swelling, or allergies after receiving the candidate vaccine.

[0028] It should be noted that by querying and retrieving candidate vaccines that match the target user from the preset knowledge graph, vaccines that the target user cannot receive can be quickly eliminated, ensuring the target user's vaccination safety from the source. Furthermore, the efficacy score and the probability of adverse reactions corresponding to the candidate vaccines quantify the protective benefits and vaccination risks after the target user receives the vaccine, avoiding the recommendation misconception of "only focusing on the vaccine effect while ignoring individual risks".

[0029] For example, the feature vector corresponding to the target user is input into a preset knowledge graph. Based on the retrieval rules in the preset knowledge graph (if the user has a history of vaccine allergy or acute infection, all vaccines are excluded; if the user has a history of serious adverse reactions to vaccines, the same vaccine is excluded), the system matches the 23-valent pneumococcal polysaccharide vaccine suitable for elderly people with hypertension and the influenza vaccine suitable for autumn and winter. Then, the entity attributes of the two vaccines are read, and the effectiveness score and adverse reaction probability of the 23-valent pneumococcal polysaccharide vaccine are output as 85% and 0.3%, respectively, and the effectiveness score and adverse reaction probability of the influenza vaccine are 78% and 0.2%, respectively.

[0030] Step 104: Obtain the infectious disease risk map. The infectious disease risk map records the risk probability values ​​of infection with target infectious diseases corresponding to multiple administrative regions. Target infectious diseases include infectious diseases that can be prevented by vaccination with candidate vaccines.

[0031] Among them, the infectious disease risk map can be an early warning map that records the level of infectious disease infection risk in each administrative region, with each administrative region having a corresponding risk probability value.

[0032] The risk probability value for infection with the target infectious disease corresponding to an administrative region can refer to the likelihood of a population within that administrative region contracting the target infectious disease within a specific time period. Target infectious diseases can include at least one of several types of infectious diseases, such as influenza, dengue fever, hand-foot-and-mouth disease, and HPV infection. Candidate vaccines can include vaccines that can prevent the corresponding infectious disease. For example, if the candidate vaccine is an "HPV vaccine," then the infectious disease that the candidate vaccine can prevent is "HPV infection."

[0033] It should be noted that, to ensure data timeliness, the infectious disease risk map can be updated every 24 hours, and the peak periods of the target infectious disease's prevalence can be predicted based on this map. If the vaccination query request includes the target user's planned travel destination, the risk probability value corresponding to the planned travel destination can also be obtained from the infectious disease risk map. This risk probability value can then be used to dynamically adjust vaccination priorities, improving the accuracy of vaccination and ensuring the user's vaccination safety.

[0034] Step 105: Based on the infectious disease risk map and the feature vector corresponding to the target user, determine the risk probability value of the target user being infected with the target infectious disease, as well as the severity of the disease after the target user is infected with the target infectious disease.

[0035] The risk probability value of a target user contracting a target infectious disease can be determined by combining the target user's corresponding feature vector (reflecting the target user's current health status) with the risk probability value of the target infectious disease in the administrative region where the user is located (reflecting the likelihood of the target user contracting the target infectious disease in their administrative region). In other words, the risk probability value of a target user contracting a target infectious disease is a quantitative representation of the comprehensive likelihood of their infection after comprehensively considering the target user's own health status (internal factor) and the epidemic risk level of the area where they are located or plan to travel (external factor), intuitively reflecting the degree of infection risk of an individual in a specific scenario.

[0036] The severity of a target user's illness after being infected with a target infectious disease can be a quantitative level of the severity of the illness after being infected with a target infectious disease, determined by combining the target user's corresponding feature vector (reflecting the target user's current health status) with the risk probability value of the target user being infected with the target infectious disease.

[0037] It should be noted that by using infectious disease risk maps and feature vectors corresponding to target users, the risk probability value of target users contracting the target infectious disease, as well as the severity of the disease after the target users are infected with the target infectious disease, can be determined. This can effectively avoid the technical defects of traditional vaccine recommendation methods that rely solely on external environmental factors and ignore individual differences among users, thereby improving the accuracy of vaccine recommendations and further ensuring the vaccination safety of target users.

[0038] In one embodiment, as shown in FIG2, determining the risk probability value of the target user being infected with the target infectious disease and the severity of the disease after the target user is infected with the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user includes steps S1051 to S1054, wherein: step S1051, determining the target administrative region where the target user is located, and determining the risk probability value of the target user being infected with the target infectious disease in the target administrative region from the infectious disease risk map.

[0039] Step S1052: Based on the feature vector corresponding to the target user, query the initial disease severity and the initial risk probability value of the target user after being infected with the target infectious disease in the preset knowledge graph.

[0040] The initial severity of a target user's infection with a target infectious disease can refer to the initial quantitative reference value of the severity of the target user's illness if infected with the target infectious disease, based solely on the target user's corresponding feature vector (reflecting their current health status) and queried from a preset knowledge graph (containing authoritative treatment guidelines, clinical case data, etc.), without considering external environmental risk factors.

[0041] The initial risk probability value of a target user being infected with a target infectious disease can refer to the quantitative value of the probability of a target user being infected with a target infectious disease, which is initially determined based solely on the feature vector corresponding to the target user (reflecting its current health status) and after matching infection risk data of similar populations in a preset knowledge graph, without considering external environmental risk factors.

[0042] Step S1053: Correct the initial risk probability value of the target user contracting the target infectious disease based on the risk probability value of the target user contracting the target infectious disease in the target administrative region, and obtain the risk probability value of the target user contracting the target infectious disease.

[0043] It should be noted that the risk probability value of a target user contracting the target infectious disease reflects the target user's actual risk of infection. This risk is determined not only by the user's own health condition but also by the prevalence of infectious diseases in the administrative region where the user resides. For example, an elderly person with poor health has a much higher probability of infection in an outbreak area than in a low-prevalence area. Therefore, correcting the initial risk probability value of a target user's infection with the risk probability value of infection in the target administrative region corresponding to the target user allows the assessment results to more closely reflect the user's actual exposure environment, avoiding misjudgments, improving the accuracy of vaccination, and ensuring the safety of users' vaccinations.

[0044] Step S1054: Correct the initial disease severity of the target user after infection with the target infectious disease based on the risk probability value of the target user being infected with the target infectious disease, and obtain the disease severity of the target user after infection with the target infectious disease.

[0045] It should be noted that the initial severity of illness after a target user is infected with the target infectious disease is determined solely from a pre-defined knowledge graph based on the user's own characteristics (such as age and underlying diseases), resulting in a static assessment detached from the actual infection scenario. However, by adjusting this initial severity of illness using the risk probability value of the target user contracting the target infectious disease, the influence of the external environment on the user can be further incorporated, making the assessment results more closely reflect reality. This improves the accuracy of vaccine recommendations and ensures the safety of vaccination for users.

[0046] For example, as shown in Figure 3, which is an infectious disease risk map, this map uses color depth to distinguish the probability of risk (the darker the color, the higher the probability). As shown, areas 801, 802, 803, and 804 are the administrative regions included in this map. The probability values ​​of infection with the target infectious disease in areas 801, 802, 803, and 804 are 65%, 50%, 85%, and 30%, respectively. Among them, area 801 is the target administrative region where the target user is located, and the probability value of infection with the target infectious disease in area 801 (the target administrative region corresponding to the target user) is 65%. The feature vector corresponding to the target user is: {Age: 68 years old, Underlying diseases: Hypertension + COPD, Immune status: Low (history of respiratory infection in the past 3 months), Occupation: Home-based elderly care}. Based on the feature vector corresponding to the target user, a query in the preset knowledge graph shows that the initial disease severity of the target user after infection with the target infectious disease is 22%, and the initial probability value of infection with the target infectious disease is 35%. Based on the risk probability value of infection with the target infectious disease in Zone 801 (the target administrative region corresponding to the target user), the initial risk probability value of the target user contracting the target infectious disease is adjusted, resulting in a risk probability value of 45.5%. Based on the risk probability value of infection with the target infectious disease, the initial disease severity after the target user contracts the target infectious disease is adjusted, resulting in a disease severity value of 28.6%.

[0047] Step S106: Based on the efficacy score of the candidate vaccine, the probability of adverse reactions of the candidate vaccine, the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease, determine the degree of matching between the target user and the candidate vaccine.

[0048] It should be noted that by using four types of data—the efficacy score of the candidate vaccine, the probability of adverse reactions to the candidate vaccine, the risk probability of the target user contracting the target infectious disease, and the severity of the disease—to determine the degree of matching between the target user and the candidate vaccine, it is possible to quantitatively assess whether the benefits of receiving a certain vaccine outweigh the risks, thus avoiding the one-sidedness of traditional vaccine recommendations that "only focus on the vaccine's effectiveness while ignoring the user's tolerability, and only emphasize adverse reactions while underestimating the user's risk of infection."

[0049] In one embodiment, as shown in Figure 4, determining the matching degree between the target user and the candidate vaccine based on the effectiveness score of the candidate vaccine, the probability of adverse reactions of the candidate vaccine, the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease includes steps S1061 to S1062, wherein: step S1061, based on the effectiveness score of the candidate vaccine, the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease, obtains the protective benefit of the candidate vaccine for the target user.

[0050] In one embodiment, the product of the risk probability value of the target user contracting the target infectious disease and the severity of the disease is calculated as the target product value; the product of the effectiveness score of the candidate vaccine and the target product value is calculated as the protective benefit of the candidate vaccine for the target user.

[0051] Among them, the protective benefit of the candidate vaccine for the target user reflects the health benefits (such as reduced risk of infection) that the target user can obtain by receiving the candidate vaccine.

[0052] It's important to note that the product of the risk probability of a target user contracting a target infectious disease and the severity of the disease essentially quantifies the upper limit of health loss for that user from not getting vaccinated. For example, elderly people with a high risk probability of contracting a target infectious disease and a high degree of disease severity will have a larger target product, meaning that not getting vaccinated poses a significant health risk. Therefore, deriving the protective benefit of a candidate vaccine for the target user based on its efficacy score, the target user's risk probability of contracting the target infectious disease, and the severity of the disease avoids the pitfall of "using group risk to substitute for individual risk," fully considers the differences in protective benefits obtained by different users after vaccination, improves the accuracy of vaccine recommendations, and ensures the safety of users' vaccination.

[0053] Step S1062: Based on the protective efficacy of the candidate vaccine for the target user and the probability of adverse reactions corresponding to the candidate vaccine, determine the degree of matching between the target user and the candidate vaccine.

[0054] In one embodiment, the ratio of the protective benefit of the candidate vaccine to the probability of adverse reactions corresponding to the candidate vaccine is used as the degree of matching between the target user and the candidate vaccine.

[0055] The degree of matching between the target user and the candidate vaccine reflects the cost-effectiveness of the candidate vaccine and is used to assess whether the candidate vaccine can effectively cover the infection risk faced by the target user. For example, if the target user has a high probability of contracting the target infectious disease, or if the target user does contract the target infectious disease and the severity of the disease is high, the protective benefit produced by the candidate vaccine can specifically offset this risk.

[0056] It should be noted that using the ratio of the protective benefit of a candidate vaccine to the probability of adverse reactions corresponding to the candidate vaccine as the degree of matching between the target user and the candidate vaccine avoids both the problem of focusing only on protective benefits while ignoring vaccination safety and the drawback of focusing only on vaccination safety while neglecting protective benefits. By transforming the benefit-risk trade-off from a qualitative judgment to a quantitative calculation, the vaccine recommendation results are more accurate, effectively ensuring the vaccination safety of users.

[0057] Step S107: Generate vaccination recommendations for the target user based on the matching degree between the target user and multiple candidate vaccines.

[0058] The vaccination recommendations may include at least two of the following: vaccination time, vaccination location, vaccination dosage, precautions for vaccination, and the recommendation level of the vaccination (e.g., level A indicates that vaccination is strongly recommended).

[0059] In one embodiment, as shown in FIG5, generating a vaccination recommendation for the target user based on the matching degree between the target user and the candidate vaccine includes steps S1071 to S1072, wherein: step S1071, the matching degree between the target user and multiple candidate vaccines is sorted in descending order to obtain the candidate vaccine with the highest matching degree with the target user, and the candidate vaccine with the highest matching degree with the target user is selected as the target vaccine to be administered to the target user.

[0060] It should be noted that by sorting the matching degree between the target user and multiple candidate vaccines in descending order, the candidate vaccine with the highest matching degree with the target user is obtained. The candidate vaccine with the highest matching degree with the target user is selected as the target vaccine for the target user to be vaccinated. This can effectively reduce the ineffective investment of high-quality vaccine resources in low-benefit groups, while ensuring the priority access of high-risk groups to suitable vaccines, improving the accuracy of vaccination, and ensuring the safety of users' vaccination.

[0061] Step S1072: Query the vaccination recommendation corresponding to the target vaccine in the vaccination recommendation query table, and use the vaccination recommendation corresponding to the target vaccine as the vaccination recommendation for the target user. The vaccination recommendation query table records multiple vaccines and their corresponding vaccination recommendations.

[0062] The vaccination recommendation lookup table is pre-formulated based on authoritative clinical guidelines, vaccine instructions, and disease control regulations. It records vaccination recommendations for various vaccines (such as dosage, vaccination interval, and absolute contraindications), avoiding the bias in recommendations caused by experience-based judgment.

[0063] It should be noted that by looking up the vaccination recommendation corresponding to the target vaccine in the vaccination recommendation query table, and using the vaccination recommendation corresponding to the target vaccine as the vaccination recommendation for the target user, operational errors such as incorrect vaccination, missed vaccination, and incorrect vaccine dosage can be avoided, thereby improving the accuracy of vaccination.

[0064] For example, as shown in Table 1, which is a vaccine administration recommendation lookup table, if the target vaccine for a user is known to be the "recombinant shingles vaccine," the vaccine administration recommendation for the "recombinant shingles vaccine" can be retrieved from the lookup table. This recommendation includes the vaccination time, location, dosage, and contraindications for the "recombinant shingles vaccine." This vaccine administration recommendation lookup table provides a basis for querying vaccine administration recommendations, enabling rapid matching between the "target vaccine" and the "administration recommendation." This not only reduces the computational complexity of the algorithm but also facilitates the user's understanding of the vaccination process and precautions.

[0065]

[0066] In one embodiment, after generating vaccination recommendations for the target user, the method further includes: sending the vaccination recommendations for the target user to a client, and receiving the vaccination recommendation evaluation results returned by the client.

[0067] It should be noted that sending vaccination recommendations to the target users and receiving the evaluation results of the vaccination recommendations returned by the client can further mitigate vaccination risks and ensure the safety of users' vaccinations.

[0068] For example, the vaccination recommendation for the target user is: "Vaccine name: 23-valent pneumococcal polysaccharide vaccine; vaccination time: recommended to be completed within 1 month; vaccination location: vaccination clinic of XX Street Community Health Service Center; dosage: single dose of 0.5ml, intramuscular injection in the deltoid muscle of the upper arm; contraindications: those allergic to vaccine components, patients in the acute phase of infection." This vaccination recommendation for the target user is sent to the client used by medical staff, and the client returns the vaccination recommendation assessment result, which is: "Based on the user's recent surgical history, the current physical condition is not suitable for immediate vaccination, and it is recommended to receive the vaccine 3 weeks later."

[0069] It should be noted that after a target user receives the target vaccine, they can upload antibody test results or adverse reaction feedback information through the client. Based on this, the vaccine recommendation method can be further optimized, the accuracy of vaccine recommendations can be improved, and the safety of users' vaccination can be ensured.

[0070] Figure 6 illustrates a scenario of the vaccine recommendation method provided in the above embodiment. Figure 6 includes a server 200 and a terminal device 201, which communicate via a wireless network signal. The terminal device 201 sends a vaccination query request to the server 200. The server 200 receives the vaccination query request, extracts the feature vector of the target user's personal information from the request, and then queries a preset knowledge graph based on the feature vector corresponding to the target user to obtain candidate vaccines matching the target user, the effectiveness score of the candidate vaccines, and the probability of adverse reactions corresponding to the candidate vaccines. Subsequently, combining the infectious disease risk map with the feature vector corresponding to the target user, the server further determines the risk probability value of the target user contracting the target infectious disease and the severity of the disease after the target user contracts the target infectious disease. Based on the effectiveness score of the candidate vaccine, the probability of adverse reactions corresponding to the candidate vaccine, the risk probability value of the target user contracting the target infectious disease, and the severity of the disease, the matching degree between the target user and the candidate vaccine is calculated. Finally, based on the matching degree between the target user and the candidate vaccine, a suitable vaccination recommendation is generated for the target user, and the server 200 sends this vaccination recommendation to the terminal device 201.

[0071] The vaccine recommendation method provided in the above embodiments obtains the effectiveness score of the candidate vaccine, the probability of adverse reactions of the candidate vaccine, the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease. Based on these data, it obtains the matching degree between the target user and the candidate vaccine, and finally generates a suitable vaccination recommendation for the target user based on the matching degree between the target user and the candidate vaccine. This transforms the expected benefits and potential risks of vaccination from qualitative judgment to quantitative calculation, making the vaccine recommendation results more accurate and ensuring the vaccination safety of users.

[0072] Please refer to Figure 7, which is a schematic block diagram of a vaccine recommendation device provided in an embodiment of this application.

[0073] As shown in Figure 7, the vaccine recommendation device 600 includes: a first acquisition module 601, an information extraction module 602, a data query module 603, a second acquisition module 604, a first data determination module 605, a second data determination module 606, and a data generation module 607.

[0074] The first acquisition module 601 is used to acquire a vaccine vaccination query request, which includes the personal information of the target user to be vaccinated.

[0075] The information extraction module 602 is used to extract the feature vector of the target user's personal information from the vaccination query request.

[0076] The data query module 603 is used to query, based on the feature vector corresponding to the target user, candidate vaccines that match the target user, the effectiveness score of the candidate vaccine, and the probability of adverse reactions of the candidate vaccine in a preset knowledge graph.

[0077] The second acquisition module 604 is used to acquire an infectious disease risk map, which records the risk probability values ​​of infection with target infectious diseases corresponding to multiple administrative regions, including infectious diseases that can be prevented by vaccination with the candidate vaccine.

[0078] The first data determination module 605 is used to determine the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease after the target user is infected with the target infectious disease, based on the infectious disease risk map and the feature vector corresponding to the target user.

[0079] The second data determination module 606 is used to determine the matching degree between the target user and the candidate vaccine based on the effectiveness score corresponding to the candidate vaccine, the probability of adverse reactions corresponding to the candidate vaccine, the risk probability value of the target user being infected with the target infectious disease, and the severity of the disease.

[0080] The data generation module 607 is used to generate vaccination recommendations for the target user based on the degree of matching between the target user and multiple candidate vaccines.

[0081] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the above-described apparatus and its modules and units can be referred to the corresponding processes in the aforementioned vaccine recommended method embodiments, and will not be repeated here.

[0082] The apparatus provided in the above embodiments can be implemented as a computer program that can run on the computer device shown in FIG8.

[0083] Please refer to Figure 8, which is a schematic block diagram of the structure of a computer device provided in an embodiment of this application.

[0084] As shown in Figure 8, the computer device includes a processor, a memory, and a network interface connected via a system bus. The memory may include a storage medium and internal memory. The storage medium may be non-volatile or volatile.

[0085] The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any recommended vaccine method.

[0086] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0087] Internal memory provides an environment for the execution of computer programs stored in storage media. When these computer programs are executed by a processor, the processor can execute any recommended vaccine method.

[0088] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that the structure shown in Figure 8 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0089] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0090] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: obtaining a vaccination query request, the vaccination query request including personal information of a target user to be vaccinated; extracting a feature vector of the target user's personal information from the vaccination query request; querying a preset knowledge graph based on the feature vector corresponding to the target user for candidate vaccines matching the target user, the effectiveness score of the candidate vaccines, and the probability of adverse reactions corresponding to the candidate vaccines; obtaining an infectious disease risk map, the infectious disease risk map recording the probability values ​​of infection with a target infectious disease corresponding to multiple administrative regions, the target infectious disease including infectious diseases that can be prevented by vaccination with the candidate vaccines; determining the probability value of the target user's infection with the target infectious disease and the severity of the disease after the target user is infected with the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user; determining the matching degree between the target user and the candidate vaccines based on the effectiveness score of the candidate vaccines, the probability of adverse reactions corresponding to the candidate vaccines, the probability value of the target user's infection with the target infectious disease, and the severity of the disease; and generating a vaccination recommendation for the target user based on the matching degree between the target user and multiple candidate vaccines.

[0091] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the computer equipment described above can be referred to the corresponding process in the aforementioned vaccine recommendation method embodiments, and will not be repeated here.

[0092] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0093] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can refer to various embodiments of the vaccine recommendation method of this application.

[0094] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0095] Furthermore, the computer's usable storage medium may primarily include a stored program area and a stored data area. The stored program area may store the operating system, applications required for at least one function, etc.; the stored data area may store data created based on the use of blockchain nodes, etc. The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. A blockchain is essentially a decentralized database, a chain of data blocks linked using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain may include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0096] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0097] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0098] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recommending vaccines, characterized in that, include: Obtain a vaccination query request, which includes the personal information of the target user to be vaccinated; The following steps are performed: First, extract feature vectors of the target user's personal information from the vaccination query request. Second, query a preset knowledge graph for candidate vaccines matching the target user, their corresponding efficacy scores, and their corresponding adverse reaction probabilities. Third, obtain an infectious disease risk map, which records the risk probability values ​​of infection with a target infectious disease corresponding to multiple administrative regions, including infectious diseases preventable by the candidate vaccine. Fourth, determine the risk probability value of the target user contracting the target infectious disease and the severity of the disease after infection based on the infectious disease risk map and the target user's feature vector. Fifth, determine the matching degree between the target user and the candidate vaccine based on the efficacy score, the adverse reaction probability, the risk probability value, and the severity of the disease. Vaccination recommendations are generated for the target user based on the degree of matching between the target user and multiple candidate vaccines.

2. The vaccine recommendation method as described in claim 1, characterized in that, The step of determining the matching degree between the target user and the candidate vaccine based on the efficacy score of the candidate vaccine, the probability of adverse reactions of the candidate vaccine, the risk probability value of the target user contracting the target infectious disease, and the severity of the disease includes: obtaining the protective efficacy of the candidate vaccine for the target user based on the efficacy score of the candidate vaccine, the probability value of the target user contracting the target infectious disease, and the severity of the disease; and determining the matching degree between the target user and the candidate vaccine based on the protective efficacy of the candidate vaccine for the target user and the probability of adverse reactions of the candidate vaccine.

3. The vaccine recommendation method as described in claim 1, characterized in that, The step of determining the matching degree between the target user and the candidate vaccine based on the efficacy score corresponding to the candidate vaccine, the probability of adverse reactions corresponding to the candidate vaccine, the risk probability value of the target user contracting the target infectious disease, and the severity of the disease includes: calculating the product of the risk probability value of the target user contracting the target infectious disease and the severity of the disease as a target product value; calculating the product of the efficacy score corresponding to the candidate vaccine and the target product value as the protective benefit of the candidate vaccine for the target user; and calculating the division between the protective benefit of the candidate vaccine for the target user and the probability of adverse reactions corresponding to the candidate vaccine as the matching degree between the target user and the candidate vaccine.

4. The vaccine recommendation method as described in claim 1, characterized in that, The step of generating a vaccination recommendation for the target user based on the matching degree between the target user and multiple candidate vaccines includes: sorting the matching degree between the target user and multiple candidate vaccines in descending order, obtaining the candidate vaccine with the highest matching degree with the target user, and selecting the candidate vaccine with the highest matching degree with the target user as the target vaccine to be administered to the target user; The vaccine recommendation query table retrieves the vaccine recommendation corresponding to the target vaccine, and uses the vaccine recommendation corresponding to the target vaccine as the vaccine recommendation for the target user. The vaccine recommendation query table records multiple vaccines and their corresponding vaccine recommendations.

5. The vaccine recommendation method according to any one of claims 1-4, characterized in that, The step of determining the risk probability value of a target user contracting the target infectious disease and the severity of the disease after the target user contracts the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user includes: determining the target administrative region where the target user is located; determining the risk probability value of the target user contracting the target infectious disease in the target administrative region from the infectious disease risk map; querying the initial severity of the disease after the target user contracts the target infectious disease and the initial risk probability value of the target user contracting the target infectious disease in a preset knowledge graph based on the feature vector corresponding to the target user; correcting the initial risk probability value of the target user contracting the target infectious disease based on the risk probability value of the target user contracting the target infectious disease in the target administrative region to obtain the risk probability value of the target user contracting the target infectious disease; and correcting the initial severity of the disease after the target user contracts the target infectious disease based on the risk probability value of the target user contracting the target infectious disease to obtain the severity of the disease after the target user contracts the target infectious disease.

6. The vaccine recommendation method according to any one of claims 1-4, characterized in that, The target user's personal information includes at least two of the following: basic demographic information, clinical health records, genetic and biomarker data, past vaccination history and reaction records, and user behavior data.

7. The vaccine recommendation method as described in claim 1, characterized in that, The vaccination recommendations include at least two of the following: vaccination time, vaccination location, vaccination dosage, precautions for vaccination, and the recommendation level of the vaccination recommendations.

8. A vaccine recommendation device, characterized in that, The device includes: a first acquisition module for acquiring a vaccination query request, the vaccination query request including personal information of a target user to be vaccinated; an information extraction module for extracting feature vectors of the target user's personal information from the vaccination query request; a data query module for querying, based on the feature vectors corresponding to the target user, candidate vaccines matching the target user, the effectiveness scores of the candidate vaccines, and the adverse reaction probabilities of the candidate vaccines in a preset knowledge graph; and a second acquisition module for acquiring an infectious disease risk map, the infectious disease risk map recording the risk probability values ​​of infection with target infectious diseases corresponding to multiple administrative regions, the target infectious diseases including vaccination. The candidate vaccine can prevent infectious diseases; a first data determination module is used to determine the risk probability value of the target user contracting the target infectious disease and the severity of the disease after the target user is infected with the target infectious disease based on the infectious disease risk map and the feature vector corresponding to the target user; a second data determination module is used to determine the matching degree between the target user and the candidate vaccine based on the effectiveness score corresponding to the candidate vaccine, the adverse reaction probability corresponding to the candidate vaccine, the risk probability value of the target user contracting the target infectious disease, and the severity of the disease; a data generation module is used to generate vaccination recommendations for the target user based on the matching degree between the target user and multiple candidate vaccines.

9. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the vaccine recommendation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the vaccine recommendation method as described in any one of claims 1 to 7.

Images