Age prediction method, device, server and storage medium based on prediction model

Abstract

The present invention discloses an age prediction method, device, server and storage medium based on a prediction model. The method comprises: receiving an age prediction request sent by a terminal, the age prediction request carrying first data, the first data including basic information of an object to be detected, and also including one or more information of disease information, exercise information and living habit information of the object to be detected, the basic information including actual age; obtaining second data corresponding to an input item of an age prediction model from the first data; inputting the second data into the age prediction model for processing to obtain a predicted age of the object to be detected; obtaining an age difference between the predicted age and the actual age, and determining health status information of the object to be detected based on the age difference; and sending the predicted age, actual age and health status information to the terminal. The present invention can improve the efficiency of age prediction, and can quickly determine the health status of the object to be detected according to the predicted age.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an age prediction method, device, server and storage medium based on a prediction model. Background Art

[0002] In recent years, with the development of society, although people's living standards have been improved, the probability of people getting sick has also increased, so people are paying more and more attention to their own health problems. Among them, whether the body is healthy can be determined by the age of the organism. At present, when estimating the age of an organism, the subject to be tested needs to go to the hospital for relevant tests to obtain the diagnosis value, and then estimate the age of the organism based on the obtained diagnosis value. However, it takes too long and is very troublesome to obtain the diagnosis value, which results in too long time and low efficiency in age estimation. Summary of the invention

[0003] The embodiments of the present invention provide an age prediction method, device, server and storage medium based on a prediction model, which can improve the efficiency of age prediction and quickly determine the health status of a subject to be detected according to the predicted age.

[0004] In a first aspect, an embodiment of the present invention provides an age prediction method based on a prediction model, comprising:

[0005] receiving an age prediction request sent by a terminal, the age prediction request carrying first data, the first data including basic information of a subject to be detected, the first data also including one or more of disease information, exercise information, and life habit information of the subject to be detected, the basic information including actual age;

[0006] Acquire second data corresponding to an input item of an age prediction model from the first data;

[0007] Inputting the second data into the age prediction model for processing to obtain the predicted age of the subject to be detected;

[0008] Obtaining an age difference between the predicted age and the actual age, and determining health status information of the subject to be detected based on the age difference;

[0009] The predicted age, the actual age and the health status information are sent to the terminal.

[0010] Optionally, the predicted age is determined based on a total age risk value obtained by adding the age risk value corresponding to each item of the second data and the actual age, and the age risk value is calculated based on a basic score and weight corresponding to each item of data.

[0011] Optionally, the basic information further includes location information of the object to be detected, and the method further includes:

[0012] Detecting whether the age difference is greater than or equal to an age difference threshold;

[0013] When the age difference is greater than or equal to the age difference threshold, determining at least one recommended physical examination hospital according to the location information, and the distance between the at least one recommended physical examination hospital and the subject to be detected is within a preset distance range;

[0014] Obtaining hospital information of the at least one recommended physical examination hospital, wherein the hospital information includes information on specialized treatment items, hospital name, address, telephone number, and distance from the subject to be examined;

[0015] The hospital information of the at least one recommended physical examination hospital is sent to the terminal, so that the terminal outputs the hospital information after receiving the hospital information.

[0016] Optionally, the method further includes:

[0017] receiving a path request sent by the terminal, the path request carrying an identifier of a target physical examination hospital, the target physical examination hospital being determined according to a selection instruction input by a user for hospital information of the at least one recommended physical examination hospital;

[0018] Obtaining path information from the geographical location indicated by the location information to the geographical location corresponding to the target physical examination hospital, wherein the path indicated by the path information includes one or more of a path with the shortest distance, a path with the shortest time consumption, and a path avoiding congestion;

[0019] The path information is sent to the terminal, so that the terminal outputs the path information after receiving the path information.

[0020] Optionally, the basic information further includes regional information, and the acquiring, from the first data, second data corresponding to an input item of the age prediction model includes:

[0021] Determining a target age prediction model from a plurality of preset age prediction models according to the regional information;

[0022] Acquire second data corresponding to an input item of the target age prediction model from the first data;

[0023] The step of inputting the second data into the age prediction model for processing to obtain the predicted age of the subject to be detected includes:

[0024] The second data is input into the target age prediction model for processing to obtain the predicted age of the object to be detected.

[0025] Optionally, before receiving the age prediction request sent by the terminal, the method further includes:

[0026] Acquire historical sample data and historical predicted age, wherein the historical sample data includes basic information of the subject to be detected, and the basic information includes regional information;

[0027] Classifying the historical sample data according to the regional information to obtain a plurality of classification categories, wherein the objects to be detected corresponding to the historical sample data under each category are all in the same region;

[0028] Based on the historical sample data and the historical predicted age under each of the multiple classification categories, an age prediction model for the region corresponding to each category is trained respectively.

[0029] Optionally, before receiving the age prediction request sent by the terminal, the method further includes:

[0030] Receiving a data request for a target interface sent by the terminal;

[0031] In response to the data request, target data of the target interface is sent to the terminal, so that the terminal outputs the target interface according to the target data, wherein the target interface includes a plurality of dialog boxes and a plurality of options, and the plurality of dialog boxes and the plurality of options are used for a user to input information of the object to be detected;

[0032] The receiving terminal sends an age prediction request, including:

[0033] An age prediction request generated according to the information of the object to be detected input by the user in response to the multiple dialog boxes and multiple options is received and sent by the terminal.

[0034] In a second aspect, an embodiment of the present invention provides an age prediction device based on a prediction model, wherein the age prediction device includes a unit for executing the method of the first aspect.

[0035] In a third aspect, an embodiment of the present invention provides a server, comprising a processor, a communication interface and a memory, wherein the processor, the communication interface and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect above.

[0036] In a fourth aspect, an embodiment of the present invention provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method of the first aspect.

[0037] In an embodiment of the present invention, after receiving an age prediction request sent by a terminal, second data is first obtained from the first data carried in the age prediction request, and the second data is input into an age prediction model for processing to obtain a predicted age, and then the health status information of the object to be detected is determined based on the age difference between the predicted age and the actual age in the first data, so that the predicted age can be quickly obtained through the age prediction model, the efficiency of age prediction is improved, and the health status of the object to be detected can be quickly determined based on the predicted age. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0039] Figure 1 is a flow chart of an age prediction method provided by the first embodiment of the present invention;

[0040] Figure 2 is a flow chart of an age prediction method provided by the second embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of the structure of an age prediction device provided by an embodiment of the present invention;

[0042] Figure 4 It is a structural diagram of a server provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0044] The embodiment of the present invention discloses an age prediction method, device, server and storage medium based on a prediction model, which are used to quickly obtain a predicted age through an age prediction model to improve the efficiency of age prediction, and to quickly determine the health status of a subject to be detected according to the predicted age. The following are detailed descriptions.

[0045] The technical solution in the embodiment of the present invention can be applied to a server, which can be a server corresponding to an online insurance platform or other cloud servers in the Internet. The terminal in the embodiment of the present invention can be a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a computer, a personal laptop, a tablet computer, a mobile Internet device (Mobile Internet Devices, MID) and a personal digital assistant, etc.

[0046] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of an age prediction method based on a prediction model provided by the first embodiment of the present invention. Specifically, Figure 1 As shown, the age prediction method may include the following steps:

[0047] S101. A server receives an age prediction request sent by a terminal, where the age prediction request carries first data.

[0048] In an embodiment of the present invention, the first data carried by the age prediction request includes basic information of the object to be detected, and the basic information includes the actual age, gender, height, weight, occupation information, regional information and location information of the object to be detected. The regional information includes the name of the permanent city of the object to be detected, the location information is used to indicate the current geographical location of the object to be detected, and the occupation information includes the occupation name and occupation category of the object to be detected. The first data also includes one or more information of the disease information, exercise information and living habit information of the object to be detected. The disease information includes past medical history, existing disease information and family medical history, etc.; the exercise information includes exercise name, exercise frequency and exercise duration, etc.; the living habit information includes eating habit information, sleeping habit information (such as sleeping time, whether to stay up late, frequency of staying up late, etc.) and whether to smoke and drink. After the terminal receives the above information of the object to be detected input by the user, it generates the first data according to the above information, and generates the age prediction request according to the first data. The terminal sends the age prediction request to the server, and after receiving the age prediction request sent by the terminal, the server parses the age prediction request to obtain the first data. The user may be the object to be detected or an insurance personnel.

[0049] In one embodiment, before the server receives the age prediction request sent by the terminal, it receives the data request generated by the operation of the target interface sent by the terminal, and obtains the target data about the target interface in response to the data request, and sends the target data to the terminal. After receiving the target data sent by the server, the terminal outputs the target interface according to the target data. Wherein, the target interface includes multiple dialog boxes and multiple options, and the multiple dialog boxes and multiple options are used for users to input information about the object to be detected. For example, the target interface includes multiple dialog boxes for users to fill in the name, height, weight, date of birth and city of residence of the object to be detected; the target interface also includes multiple options for users to select the gender, occupation, past medical history, existing disease and family medical history of the object to be detected. The terminal receives the information of the object to be detected input by the user for the multiple dialog boxes and multiple options, and generates the first data according to the input information of the object to be detected. Further, the terminal generates an age prediction request according to the first data, and sends the age prediction request to the server. After receiving the age prediction request sent by the terminal, the server parses the age prediction request to obtain the first data.

[0050] S102: The server obtains second data corresponding to an input item of an age prediction model from the first data.

[0051] In an embodiment of the present invention, the age prediction model is pre-built and pre-stored in the server. The age prediction model is trained by the server based on the historical predicted age and the historical target data obtained from the historical sample data. The server first obtains the historical predicted age and the historical sample data, and obtains the historical target data from the historical sample data; then the historical target data is used as the input of the age prediction model, and the historical predicted age is used as the output of the age prediction model to train the age prediction model. After the server obtains the first data, the age prediction model is called, and the second data corresponding to the input item of the age prediction model is obtained from the first data.

[0052] Among them, on the one hand, the second data can be part of the first data, that is to say, the second data is part of the first data that the age prediction model needs to use when predicting age. For example, the first data includes basic information, disease information and living habits information of the object to be detected; the basic information includes name, ID number, actual age, gender, height, weight, occupation name and regional information. Since disease information, living habits information and actual age, gender, height, weight, occupation name and regional information in the basic information are all useful parameters in the age prediction process, and all correspond to the input items of the age prediction model; the second data obtained by the server from the first data according to the input items of the age prediction model includes the disease information, living habits information and actual age, gender, height, weight, occupation name and regional information in the basic information. However, the name, ID number and other information in the basic information are useless parameters in the age prediction process, and the age prediction model has no input items corresponding to the above information, so the name, ID number and other information in the basic information are discarded. On the other hand, the second data is generated by converting the representation form of the first data, or converting the first data from the current representation form into another representation form to obtain the second data. The representation form of the second data is consistent with the representation form of the data of the input item of the age prediction model.

[0053] S103: The server inputs the second data into the age prediction model for processing to obtain the predicted age of the object to be detected.

[0054] In the embodiment of the present invention, after the server obtains the second data from the first data, the server uses the second data as the input of the age prediction model, and obtains the predicted age of the object to be detected after being processed by the age prediction model. The predicted age is determined based on the total age risk value obtained by adding the age risk value corresponding to each item of data in the second data and the actual age, and the age risk value is calculated based on the basic score and weight corresponding to each item of data.

[0055] In one embodiment, the age prediction model multiplies the basic score corresponding to the third data by the weight corresponding to the third data to obtain the age risk value corresponding to the third data. The third data can be any one of the second data, or it can be any one of the second data that will cause the biological age of the object to be detected to increase. Further, the age prediction model adds the age risk values ​​corresponding to each of the third data to obtain the total age risk value of the object to be detected; then the risk age of the object to be detected is determined according to the total age risk value, and the risk age is the total age of the biological age of the object to be detected caused by each of the third data. Further, the age prediction model obtains the actual age of the object to be detected, and adds the risk age to the actual age to obtain the predicted age of the object to be detected. Among them, each third data corresponds to the same basic score (for example, 1), but different third data correspond to different weights. The predicted age is usually higher than the actual age of the object to be detected, and the predicted age is used to indicate the predicted biological age of the object to be detected. The larger the predicted age of the object to be detected, the larger the biological age of the object to be detected.

[0056] For example, suppose that the name of the occupation of the object to be detected in the first data is engineering architect, the past medical history includes diabetes, and the family medical history includes cardiovascular disease. Assume that the weight corresponding to the third data corresponding to the occupation of engineering architect is 7, because the occupation of engineering architect may suffer from digestive tract diseases, respiratory diseases and other diseases, so the weight is higher; the weight corresponding to the third data corresponding to the past medical history of diabetes is 4; the weight corresponding to the third data corresponding to the family medical history of cardiovascular disease is 3.7; and assume that the basic score of each third data is 1. Then the age prediction model can calculate the age risk value corresponding to the third data of the engineering architect as 7, the age risk value corresponding to the third data of the past medical history of diabetes is 4; the age risk value corresponding to the third data of the family medical history of cardiovascular disease is 3.7; and the total age risk value of the object to be detected can be added to 14.7. Then the age prediction model converts the total age risk value of the object to be detected into the risk age of the object to be detected. The total age risk value is 14.7, and the corresponding risk age can be 14.7 years old. Among them, the total age risk value can also be multiplied by a coefficient according to the age range to which the actual age of the object to be detected belongs to obtain the risk age of the object to be detected. Further, assuming that the actual age of the object to be detected in the first data is 38 years old, the age prediction model adds the risk age to the actual age to obtain a predicted age of 52.7 years old for the object to be detected.

[0057] It should be noted that if the third data is any one of the second data, the weight corresponding to the data in the third data that will not cause the biological age of the object to be detected to increase is 0. For example, if the actual age of the object to be detected is in the first age interval, and the actual age of the object to be detected in the first age interval will not cause the biological age of the object to be detected to increase, then the weight corresponding to the third data of the actual age of the object to be detected can be 0. On the contrary, if the actual age of the object to be detected is in the second age interval, and the actual age of the object to be detected in the second age interval will cause the biological age of the object to be detected to increase, then the weight corresponding to the third data of the actual age of the object to be detected is not 0, for example, it can be 1.2, etc. In another embodiment, each of the third data corresponds to an identical weight (e.g., 1 or 1.2, etc.), but different third data correspond to different basic scores. The method for determining the predicted age of the object to be detected in this way can refer to the above description, and will not be repeated here.

[0058] S104: The server obtains an age difference between the predicted age and the actual age of the subject to be detected, and determines health status information of the subject to be detected based on the age difference.

[0059] In an embodiment of the present invention, after the server obtains the predicted age of the object to be detected through the age prediction model, the server subtracts the age value indicated by the actual age from the age value indicated by the predicted age to obtain the age difference. Further, the server detects whether the age difference is less than or equal to the first age difference threshold. When the age difference is less than or equal to the first age difference threshold, the health status of the object to be detected is determined to be the first health level, and the first health level is used as the health status information of the object to be detected. When the age difference is greater than the first age difference threshold, the server detects whether the age difference is less than or equal to the second age difference threshold; when the age difference is less than or equal to the second age difference threshold, the server determines that the health status of the object to be detected is the second health level, and the second health level is used as the health status information of the object to be detected. When the age difference is greater than the second age difference threshold, the server determines that the health status of the object to be detected is the third health level, and the third health level is used as the health status information of the object to be detected. Wherein, the first age difference threshold is less than the second age difference threshold. The health status indicated by the health level is a first health level, a second health level and a third health level from good to bad, the first health level may be excellent, the second health level may be good, and the third health level may be poor. It should be noted that the embodiment of the present invention does not limit the classification of health levels.

[0060] S105. The server sends the predicted age, the actual age and the health status information to the terminal.

[0061] In the embodiment of the present invention, after the terminal determines the predicted age and health status information of the object to be detected, the predicted age, the actual age and the health status information are sent to the terminal. After receiving the predicted age, the actual age and the health status information sent by the server, the terminal outputs the predicted age, the actual age and the health status information so that the user and the object to be detected can understand the health status of the object to be detected and the biological age of the object to be detected.

[0062] In an embodiment of the present invention, after receiving an age prediction request sent by a terminal, second data is first obtained from the first data carried in the age prediction request, and the second data is input into an age prediction model for processing to obtain a predicted age, and then the health status information of the object to be detected is determined based on the age difference between the predicted age and the actual age in the first data, so that the predicted age can be quickly obtained through the age prediction model, the efficiency of age prediction is improved, and the health status of the object to be detected can be quickly determined based on the predicted age.

[0063] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of another age prediction method based on a prediction model provided by an embodiment of the present invention. Specifically, Figure 2 As shown, the age prediction method may include the following steps:

[0064] S201. A server receives an age prediction request sent by a terminal, where the age prediction request carries first data.

[0065] For details, please refer to the above description of step S201. Figure 1 The relevant description in the illustrated embodiment will not be repeated here.

[0066] S202: The server obtains second data corresponding to an input item of an age prediction model from the first data.

[0067] In an embodiment of the present invention, the basic information in the first data includes the geographical information of the object to be detected, and the geographical information includes the name of the permanent city of the object to be detected, etc. After the server obtains the first data carried by the age prediction request, it determines the target age prediction model from multiple age prediction models preset by the server according to the geographical information. For example, assuming that the city name indicated by the geographical information is Beijing, the server obtains the age prediction model corresponding to the city name Beijing from the preset multiple age prediction models, and uses the age prediction model corresponding to the city name Beijing as the target age prediction model. Furthermore, the server obtains the second data corresponding to the input item of the target age prediction model from the first data. The specific implementation method can be referred to the previous description and will not be repeated here.

[0068] In one embodiment, the multiple age prediction models are pre-built and pre-stored in the server. Before the server receives the age prediction request sent by the terminal, it first obtains historical sample data and historical predicted age, and extracts the regional information of the object to be detected from the historical sample data; then the acquired historical sample data is classified according to the regional information to obtain multiple classification categories, and the objects to be detected corresponding to the historical sample data under each category are in the same region. Assuming that the city names indicated by the regional information are Beijing and Shenzhen, the server classifies the historical sample data corresponding to the city name Beijing into the same category, and the historical sample data corresponding to the city name Shenzhen into another category. Further, the server uses the historical sample data under the target category as the input of the age prediction model, and the target category is any one of the multiple categories obtained by classification; and the historical predicted age corresponding to the historical sample data under the target category is used as the output of the age prediction model, and the age prediction model of the region corresponding to the target category is trained. In other words, each region corresponds to an age prediction model, and different regions correspond to different age prediction models. By adopting the above method, different age prediction models can be trained for different regions, and the trained age prediction models are more in line with the actual conditions of different regions.

[0069] In one embodiment, the basic information in the first data includes the geographical information and occupational information of the object to be detected. The geographical information includes the name of the permanent city of the object to be detected, and the occupational information includes the occupational name and occupational category of the object to be detected. After the server obtains the first data carried by the age prediction request, it determines the target age prediction model from multiple age prediction models preset by the server according to the geographical information and occupational information. For example, assuming that the city name indicated by the geographical information is Beijing, and the occupational category indicated by the occupational information is mining engineer; the server obtains the age prediction model corresponding to the city name Beijing and the occupational category mining engineer from the preset multiple age prediction models, and uses the age prediction model corresponding to the city name Beijing and the occupational category mining engineer as the target age prediction model. Further, the server obtains the second data corresponding to the input item of the target age prediction model from the first data. The specific implementation method can be referred to the previous description, which will not be repeated here.

[0070] In one embodiment, the multiple age prediction models are pre-built and pre-stored in the server. Before the server receives the age prediction request sent by the terminal, it first obtains historical sample data and historical predicted age, and extracts the geographical information and occupational information of the object to be detected from the historical sample data; then the acquired historical sample data is classified according to the geographical information and occupational information to obtain multiple classification categories, and the objects to be detected corresponding to the historical sample data under each category are in the same region and the same occupational category. Further, the server trains the age prediction model of the region and occupational category corresponding to each category according to the historical sample data and historical predicted age under each category in the multiple classification categories. Using the above method, different age prediction models can be trained for objects to be detected in different regions and different occupational categories, and the trained age prediction model is more in line with the actual situation of each industry in each region.

[0071] S203: The server inputs the second data into the age prediction model for processing to obtain the predicted age of the object to be detected.

[0072] In the embodiment of the present invention, the server inputs the second data into the target age prediction model for processing to obtain the predicted age of the object to be detected. The specific implementation method can be referred to the above description and will not be repeated here.

[0073] S204. The server obtains the age difference between the predicted age and the actual age of the object to be detected, determines the health status information of the object to be detected based on the age difference, and sends the predicted age, the actual age and the health status information to the terminal.

[0074] For details, please refer to the above description of step S204. Figure 1 The relevant description in the illustrated embodiment will not be repeated here.

[0075] S205: The server detects whether the age difference is greater than or equal to an age difference threshold.

[0076] In an embodiment of the present invention, the server subtracts the age value indicated by the actual age from the age value indicated by the predicted age to obtain an age difference; and detects whether the age difference is greater than or equal to an age difference threshold. The age difference threshold is, for example, 5 years old or 10 years old. When the age difference is greater than or equal to the age difference threshold, the server executes steps S206 to S209. When the age difference is less than the age difference threshold, the process ends. It should be noted that step S204 may be executed before step S205 or after step S205, and the embodiment of the present invention does not limit this.

[0077] S206. When the age difference is greater than or equal to the age difference threshold, the server determines at least one recommended physical examination hospital according to the location information of the object to be detected, and obtains hospital information of the at least one recommended physical examination hospital.

[0078] In an embodiment of the present invention, the basic information in the first data includes the location information of the object to be detected, and the location information is used to indicate the current geographical location of the object to be detected. The geographical location can be the longitude and latitude of the object to be detected in the geographical coordinate system. The server obtains the location information of multiple hospitals from the network data, and then calculates the geographical location indicated by the location information of the object to be detected, and the distance between the geographical location indicated by the location information of each hospital obtained; and determines the hospital within a preset distance range from the object to be detected as a recommended physical examination hospital, and the recommended physical examination hospital is at least one. Furthermore, the server obtains the hospital information of the at least one recommended physical examination hospital from the network data, and the hospital information includes a brief introduction of the hospital, information on treatment projects it specializes in, the name, address, telephone number of the hospital, and the distance between the hospital and the object to be detected, etc.

[0079] In one embodiment, the location information of the terminal can be used as the location information of the object to be detected, and the location information of the terminal can be obtained by the server. The server can obtain the Internet Protocol Address (IP address) of the terminal, and then obtain the geographical location of the IP address from the IP geographical location database, and use the geographical location of the IP address as the geographical location of the terminal. In addition, the server can also obtain the geographical location of the terminal through the Global Positioning System (GPS) device configured by the terminal. It should be noted that the server can also obtain the location information of the terminal in other ways, which is not limited in the embodiments of the present invention.

[0080] S207. The server sends the hospital information of the at least one recommended physical examination hospital to the terminal, so that the terminal outputs the hospital information after receiving the hospital information.

[0081] S208. The server receives the path request sent by the terminal, where the path request carries an identifier of a target physical examination hospital.

[0082] In an embodiment of the present invention, after receiving the hospital information of at least one recommended physical examination hospital sent by the server, the terminal outputs the hospital information of the at least one recommended physical examination hospital, so that the subject to be tested manually determines the target physical examination hospital to go to for examination based on the hospital information of the at least one recommended physical examination hospital. Furthermore, the terminal receives a selection instruction input by the user for the hospital information of the at least one recommended physical examination hospital, and determines the target physical examination hospital from the at least one recommended physical examination hospital based on the selection instruction. The terminal sends a path request to the server, and the path request carries an identifier of the target physical examination hospital, which may be the name or address of the target physical examination hospital, etc. After receiving the path request sent by the terminal, the server obtains the identifier of the target physical examination hospital carried by the path request.

[0083] S209. The server obtains path information from the geographical location indicated by the location information to the geographical location corresponding to the target physical examination hospital, and sends the path information to the terminal so that the terminal outputs the path information after receiving the path information.

[0084] In an embodiment of the present invention, the server obtains the geographical location of the target physical examination hospital, and obtains the path information from the geographical location of the terminal to the geographical location of the target physical examination hospital from the network data, and the path indicated by the path information includes one or more of the shortest distance path, the shortest time path, and the path avoiding congestion. Further, the server sends the path information to the terminal, and the terminal outputs the path information after receiving the path information to provide path prompts to the object to be detected, or to provide path navigation for the object to be detected. It should be noted that the server can send the predicted age, the actual age, the health status information and the path information to the terminal together.

[0085] In one embodiment, the server analyzes the first data or the second data to predict the medical examination result of the subject to be detected, and the medical examination result includes the name of the disease that the subject to be detected may suffer from, and the probability of each disease that the subject to be detected may suffer from. The server determines the target recommended hospital from the at least one recommended medical examination hospital based on the information of the treatment items that the at least one recommended medical examination hospital is good at and the medical examination result. For example, assuming that the medical examination result indicates that the probability that the subject to be detected suffers from a respiratory disease is greater than 70%, and if the information of the treatment items that the recommended medical examination hospital is good at treating is a respiratory disease, the server determines the recommended medical examination hospital as the target recommended hospital.

[0086] Further, the server sends the hospital information of the target recommended hospital to the terminal, and the terminal outputs the hospital information of the target recommended hospital after receiving the hospital information of the target recommended hospital, so that the object to be detected can determine whether to go to the target recommended hospital for examination according to the hospital information of the target recommended hospital. After receiving the confirmation instruction input by the user for the hospital information of the target recommended hospital, a path request about the target recommended hospital is sent to the server. The server receives the path request about the target recommended hospital, and obtains the path information from the geographical location of the terminal to the geographical location of the target recommended hospital from the network data, and the path indicated by the path information includes one or more of the shortest distance path, the shortest time-consuming path, and the path to avoid congestion. Further, the server sends the path information to the terminal, and the terminal outputs the path information after receiving the path information to provide a path prompt to the object to be detected. By adopting the above method, not only can a physical examination hospital be recommended nearby, but also a physical examination hospital can be reasonably recommended based on the predicted condition examination results of the object to be detected, which is conducive to the object to be detected to get better treatment after diagnosis. It should be noted that the condition examination results of the object to be detected can also be predicted by the age prediction model.

[0087] In an embodiment of the present invention, after receiving an age prediction request sent by a terminal, firstly, second data is obtained from the first data carried in the age prediction request, and the second data is input into an age prediction model for processing to obtain a predicted age, and then the health status information of the object to be detected is determined based on the age difference between the predicted age and the actual age in the first data, so that the predicted age can be quickly obtained through the age prediction model, the efficiency of age prediction can be improved, and the health status of the object to be detected can be quickly determined based on the predicted age. Furthermore, at least one examination hospital is recommended to the object to be detected based on the location information of the object to be detected, and when a path request sent by the terminal is received, path information from the location of the terminal to the location of the target physical examination hospital is sent to the terminal, so that not only hospital recommendations can be made, but also path navigation can be performed for the user.

[0088] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an age prediction device based on a prediction model provided by an embodiment of the present invention. The age prediction device of the embodiment of the present invention includes a unit for executing the above-mentioned age prediction method. Specifically, the age prediction device 300 of the embodiment of the present invention may include: a transceiver unit 301, an acquisition unit 302 and a processing unit 303. Among them:

[0089] The transceiver unit 301 is configured to receive an age prediction request sent by a terminal, wherein the age prediction request carries first data, wherein the first data includes basic information of a subject to be detected, and the first data also includes one or more of disease information, exercise information, and life habit information of the subject to be detected, wherein the basic information includes actual age;

[0090] An acquisition unit 302 is used to acquire second data corresponding to an input item of an age prediction model from the first data;

[0091] A processing unit 303 is used to input the second data into the age prediction model for processing to obtain the predicted age of the object to be detected;

[0092] The processing unit 303 is further configured to obtain an age difference between the predicted age and the actual age, and determine health status information of the subject to be detected based on the age difference;

[0093] The transceiver unit 301 is further configured to send the predicted age, the actual age and the health status information to the terminal.

[0094] In one embodiment, the predicted age is determined based on a total age risk value obtained by adding the age risk value corresponding to each item of the second data and the actual age, and the age risk value is calculated based on a basic score and weight corresponding to each item of data.

[0095] In one embodiment, the basic information further includes the location information of the object to be detected, and the processing unit 303 is further configured to detect whether the age difference is greater than or equal to an age difference threshold;

[0096] The processing unit 303 is further configured to determine at least one recommended physical examination hospital according to the location information when the age difference is greater than or equal to the age difference threshold, and the distance between the at least one recommended physical examination hospital and the subject to be detected is within a preset distance range;

[0097] The acquisition unit 302 is further configured to acquire hospital information of the at least one recommended physical examination hospital, wherein the hospital information includes information on treatment items, hospital name, address, telephone number, and distance from the subject to be detected;

[0098] The transceiver unit 301 is further configured to send the hospital information of the at least one recommended physical examination hospital to the terminal, so that the terminal outputs the hospital information after receiving the hospital information.

[0099] In one embodiment, the transceiver unit 301 is further configured to receive a path request sent by the terminal, the path request carrying an identifier of a target physical examination hospital, and the target physical examination hospital is determined according to a selection instruction input by a user for hospital information of the at least one recommended physical examination hospital;

[0100] The acquisition unit 302 is further configured to acquire path information from the geographical location indicated by the location information to the geographical location corresponding to the target physical examination hospital, wherein the path indicated by the path information includes one or more of a path with the shortest distance, a path with the shortest time consumption, and a path avoiding congestion;

[0101] The transceiver unit 301 is further configured to send the path information to the terminal, so that the terminal outputs the path information after receiving the path information.

[0102] In one implementation, the basic information further includes regional information, and the acquiring unit 302 is specifically configured to:

[0103] Determining a target age prediction model from a plurality of preset age prediction models according to the regional information;

[0104] Acquire second data corresponding to an input item of the target age prediction model from the first data;

[0105] The processing unit 303 is specifically configured to input the second data into the target age prediction model for processing to obtain the predicted age of the object to be detected.

[0106] In one embodiment, the acquisition unit 302 is further used to acquire historical sample data and historical predicted age, wherein the historical sample data includes basic information of the object to be detected, and the basic information includes regional information;

[0107] The processing unit 303 is further configured to:

[0108] Classifying the historical sample data according to the regional information to obtain a plurality of classification categories, wherein the objects to be detected corresponding to the historical sample data under each category are all in the same region;

[0109] Based on the historical sample data and the historical predicted age under each of the multiple classification categories, an age prediction model for the region corresponding to each category is trained respectively.

[0110] In one implementation, the transceiver unit 301 is further configured to:

[0111] Receiving a data request for a target interface sent by the terminal;

[0112] In response to the data request, target data of the target interface is sent to the terminal, so that the terminal outputs the target interface according to the target data, wherein the target interface includes a plurality of dialog boxes and a plurality of options, and the plurality of dialog boxes and the plurality of options are used for a user to input information of the object to be detected;

[0113] The transceiver unit 301 is specifically configured to receive an age prediction request sent by the terminal and generated according to the information of the object to be detected input by the user in response to the multiple dialog boxes and multiple options.

[0114] Specifically, the age prediction device can achieve the above-mentioned Figure 1 or Figure 2 Part or all of the steps in the age prediction method in the illustrated embodiment. It should be understood that the embodiment of the present invention is an apparatus embodiment corresponding to the method embodiment, and the description of the method embodiment is also applicable to the embodiment of the present invention.

[0115] In an embodiment of the present invention, after receiving an age prediction request sent by a terminal, second data is first obtained from the first data carried in the age prediction request, and the second data is input into an age prediction model for processing to obtain a predicted age, and then the health status information of the object to be detected is determined based on the age difference between the predicted age and the actual age in the first data, so that the predicted age can be quickly obtained through the age prediction model, the efficiency of age prediction is improved, and the health status of the object to be detected can be quickly determined based on the predicted age.

[0116] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a server provided by an embodiment of the present invention. The server is used to execute the above method. Figure 4 As shown, the server 400 in this embodiment may include: one or more processors 401 and a memory 402. Optionally, the server may also include one or more communication interfaces 403. The processor 401, the communication interface 403 and the memory 402 may be connected via a bus 404, or may be connected in other ways. Figure 4 The bus mode is used as an example.

[0117] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0118] The communication interface 403 can be used for the interaction of sending and receiving information or signaling, as well as the reception and transmission of signals. The communication interface 403 may include a receiver and a transmitter for communicating with other devices. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and a storage program required for at least one function (such as a text storage function, a location storage function, etc.); the data storage area may store data created according to the use of the server (such as image data, text data), etc., and may include application storage programs, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0119] The memory 402 is also used to store program instructions. The processor 401 can call the program instructions stored in the memory 402 to implement the age prediction method shown in the embodiment of the present invention.

[0120] Among them, the processor 401 can be used to call the program instructions to perform the following steps: receive an age prediction request sent by the terminal through the communication interface 403, the age prediction request carries first data, the first data includes basic information of the object to be detected, the first data also includes one or more of the disease information, exercise information and living habit information of the object to be detected, and the basic information includes the actual age; obtain second data corresponding to the input item of the age prediction model from the first data; input the second data into the age prediction model for processing to obtain the predicted age of the object to be detected; obtain the age difference between the predicted age and the actual age, and determine the health status information of the object to be detected based on the age difference; send the predicted age, the actual age and the health status information to the terminal through the communication interface 403.

[0121] In one embodiment, the predicted age is determined based on a total age risk value obtained by adding the age risk value corresponding to each item of the second data and the actual age, and the age risk value is calculated based on a basic score and weight corresponding to each item of data.

[0122] In one embodiment, the basic information also includes the location information of the object to be detected, and the processor 401 can also call the program instructions to perform the following steps: detect whether the age difference is greater than or equal to the age difference threshold; when the age difference is greater than or equal to the age difference threshold, determine at least one recommended physical examination hospital according to the location information, and the distance between the at least one recommended physical examination hospital and the object to be detected is within a preset distance range; obtain the hospital information of the at least one recommended physical examination hospital, and the hospital information includes the treatment project information, hospital name, address, telephone number and distance from the object to be detected; send the hospital information of the at least one recommended physical examination hospital to the terminal through the communication interface 403, so that the terminal outputs the hospital information after receiving the hospital information.

[0123] In one embodiment, the processor 401 may also call the program instructions to perform the following steps: receiving a path request sent by the terminal through the communication interface 403, the path request carrying an identifier of a target physical examination hospital, and the target physical examination hospital is determined based on a selection instruction input by a user for hospital information of at least one recommended physical examination hospital; obtaining path information from the geographical location indicated by the location information to the geographical location corresponding to the target physical examination hospital, the path indicated by the path information including one or more of a path with the shortest distance, a path with the shortest time consumption, and a path avoiding congestion; sending the path information to the terminal through the communication interface 403, so that the terminal outputs the path information after receiving the path information.

[0124] In one embodiment, the basic information also includes regional information. When the processor 401 calls the program instruction to execute the step of obtaining the second data corresponding to the input item of the age prediction model from the first data, the processor 401 specifically performs the following steps: determining a target age prediction model from a plurality of preset age prediction models according to the regional information; and obtaining the second data corresponding to the input item of the target age prediction model from the first data. When the processor 401 calls the program instruction to execute the step of inputting the second data into the age prediction model for processing to obtain the predicted age of the object to be detected, the processor 401 specifically performs the following steps: inputting the second data into the target age prediction model for processing to obtain the predicted age of the object to be detected.

[0125] In one embodiment, the processor 401 may also call the program instructions to perform the following steps: obtain historical sample data and historical predicted age, the historical sample data including basic information of the object to be detected, and the basic information including geographical information; classify the historical sample data according to the geographical information to obtain multiple classification categories, and the objects to be detected corresponding to the historical sample data under each category are all in the same region; based on the historical sample data and the historical predicted age under each category of the multiple classification categories, respectively train an age prediction model for the region corresponding to each category.

[0126] In one embodiment, the processor 401 may also call the program instructions to perform the following steps: receiving a data request for a target interface sent by the terminal through the communication interface 403; sending target data of the target interface to the terminal in response to the data request, so that the terminal outputs the target interface according to the target data, and the target interface includes multiple dialog boxes and multiple options, and the multiple dialog boxes and multiple options are used for the user to input information about the object to be detected. When the processor 401 calls the program instructions to execute the age prediction request sent by the receiving terminal, it specifically performs the following steps: receiving an age prediction request generated by the terminal based on the information of the object to be detected input by the user in response to the multiple dialog boxes and multiple options.

[0127] In a specific implementation, the processor 401 described in the embodiment of the present invention may execute the above Figure 1 or Figure 2 The implementation described in the method embodiment shown in the figure can also be used to implement the embodiment of the present invention. Figure 3 The implementation of each unit described is not described here in detail.

[0128] In an embodiment of the present invention, after receiving an age prediction request sent by a terminal, second data is first obtained from the first data carried in the age prediction request, and the second data is input into an age prediction model for processing to obtain a predicted age, and then the health status information of the object to be detected is determined based on the age difference between the predicted age and the actual age in the first data, so that the predicted age can be quickly obtained through the age prediction model, the efficiency of age prediction is improved, and the health status of the object to be detected can be quickly determined based on the predicted age.

[0129] The embodiment of the present invention further provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, Figure 1 or Figure 2 Part or all of the steps in the age prediction method described in the corresponding embodiment can also implement the present invention. Figure 3 The function of the age prediction device in the embodiment shown can also realize the present invention Figure 4 The functions of the server in the illustrated embodiment are not described in detail here.

[0130] The embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute part or all of the steps in the above method.

[0131] The storage medium may be an internal storage unit of the age prediction device or server described in the above embodiments, such as a hard disk or memory of the age prediction device or server. The storage medium may also be an external storage device of the age prediction device or server, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc., provided on the age prediction device or server.

[0132] In this application, the term "and / or" is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0133] In various embodiments of the present application, the sequence numbers of the above processes do 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 embodiments of the present invention.

[0134] The above descriptions are only partial implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention.

Claims

1. An age prediction method based on a prediction model, characterized in that: The method comprises: receiving an age prediction request sent by a terminal, the age prediction request carrying first data, the first data including basic information of a subject to be detected, the first data also including one or more of disease information, exercise information, and life habit information of the subject to be detected, the basic information including actual age; Acquire second data corresponding to an input item of an age prediction model from the first data; The second data is input into the age prediction model for processing to obtain the predicted age of the object to be detected; the predicted age is determined based on the total age risk value obtained by adding the age risk value corresponding to each item of data in the second data and the actual age, and the age risk value is calculated based on the basic score and weight corresponding to each item of data; the processing includes: multiplying the basic score corresponding to the third data by the weight corresponding to the third data to obtain the age risk value corresponding to the third data, and the third data is the data in the second data; adding the age risk values ​​corresponding to each item of the third data respectively to obtain the total age risk value of the object to be detected; determining the risk age of the object to be detected based on the total age risk value, and the risk age is used to indicate the total age of the biological body of the object to be detected caused by each item of the third data; obtaining the actual age of the object to be detected, and adding the risk age to the actual age to obtain the predicted age of the object to be detected; Obtaining an age difference between the predicted age and the actual age, and determining health status information of the subject to be detected based on the age difference; the health status information includes a health level; Sending the predicted age, the actual age and the health status information to the terminal; Detecting whether the age difference is greater than or equal to an age difference threshold; If the age difference is greater than or equal to the age difference threshold, determining at least one recommended physical examination hospital according to the location information of the subject to be detected, and the distance between the at least one recommended physical examination hospital and the subject to be detected is within a preset distance range; The hospital information of the at least one recommended physical examination hospital is obtained, and the hospital information of the at least one recommended physical examination hospital is sent to the terminal, so that the terminal outputs the hospital information after receiving the hospital information.

2. The method according to claim 1, characterized in that The hospital information includes information on treatment items, hospital name, address, telephone number, and distance from the subject to be detected.

3. The method according to claim 1, characterized in that The method further comprises: receiving a path request sent by the terminal, the path request carrying an identifier of a target physical examination hospital, the target physical examination hospital being determined according to a selection instruction input by a user for hospital information of the at least one recommended physical examination hospital; Obtaining path information from the geographical location indicated by the location information to the geographical location corresponding to the target physical examination hospital, wherein the path indicated by the path information includes one or more of a path with the shortest distance, a path with the shortest time consumption, and a path avoiding congestion; The path information is sent to the terminal, so that the terminal outputs the path information after receiving the path information.

4. The method according to claim 1, characterized in that The basic information also includes regional information, and the acquiring of second data corresponding to an input item of the age prediction model from the first data includes: Determining a target age prediction model from a plurality of preset age prediction models according to the regional information; Acquire second data corresponding to an input item of the target age prediction model from the first data; The step of inputting the second data into the age prediction model for processing to obtain the predicted age of the subject to be detected includes: The second data is input into the target age prediction model for processing to obtain the predicted age of the object to be detected.

5. The method according to claim 4, characterized in that Before the receiving terminal sends an age prediction request, the method further includes: Acquire historical sample data and historical predicted age, wherein the historical sample data includes basic information of the subject to be detected, and the basic information includes regional information; Classifying the historical sample data according to the regional information to obtain a plurality of classification categories, wherein the objects to be detected corresponding to the historical sample data under each category are all in the same region; Based on the historical sample data and the historical predicted age under each of the multiple classification categories, an age prediction model for the region corresponding to each category is trained respectively.

6. The method according to claim 1, characterized in that Before the receiving terminal sends an age prediction request, the method further includes: Receiving a data request for a target interface sent by the terminal; In response to the data request, target data of the target interface is sent to the terminal, so that the terminal outputs the target interface according to the target data, wherein the target interface includes a plurality of dialog boxes and a plurality of options, and the plurality of dialog boxes and the plurality of options are used for a user to input information of the object to be detected; The receiving terminal sends an age prediction request, including: An age prediction request generated according to the information of the object to be detected input by the user in response to the multiple dialog boxes and multiple options is received and sent by the terminal.

7. An age prediction device based on a prediction model, characterized in that: The method comprises means for performing the method as claimed in any one of claims 1 to 6.

8. A server, characterized in that: It comprises a processor, a communication interface and a memory, wherein the processor, the communication interface and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method as claimed in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images