Method and device for pushing physical examination information

Abstract

The invention discloses a method and device for pushing physical examination information, and relates to the technical field of intelligent medical treatment. A specific embodiment of the method comprises the steps of determining one or more second physical examination items to be pushed by utilizing a trained preset support vector machine model according to user feature data and a corresponding first physical examination item, and pushing physical examination pushing information containing the second physical examination items to a client; according to the embodiment of the invention, the second physical examination item to be recommended is determined in real time, so that the refinement degree of determining the pushed physical examination information is improved, and the individuation degree and flexibility of the pushed physical examination information are improved; and the user experience is improved to a great extent.

Description

Technical Field

[0001] The present invention relates to the field of smart medical technology, and in particular to a method and device for pushing physical examination information. Background Art

[0002] With the development and application of Internet technology and smart medical care, users can obtain various types of medical information through Internet applications. For example, users can obtain physical examination items, make appointments for physical examinations, etc. through Internet physical examination applications.

[0003] Currently, the physical examination items pushed to users through Internet physical examination applications are usually a small number of pre-set physical examination item sets, and the physical examination items contained in each physical examination item set are fixed content. It can be seen that the existing methods of pushing physical examination information have the problems of large management granularity, poor flexibility and low personalization of pushed information, which affects the user experience. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for pushing physical examination information, which can determine one or more second physical examination items to be pushed according to user feature data and the corresponding first physical examination items by using a trained preset support vector machine model, and push the physical examination push information containing the second physical examination items to the client; the embodiment of the present invention improves the refinement of determining the physical examination information to be pushed by determining the second physical examination items to be recommended in real time, and improves the personalization and flexibility of pushing the physical examination information; and improves the user experience to a great extent.

[0005] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, a method for pushing physical examination information is provided, characterized in that it includes: in response to the client's operation on the provided page, obtaining user feature data corresponding to the client and multiple first physical examination items corresponding to the user feature data; inputting the user feature data and the multiple first physical examination items into a trained preset support vector machine model, and determining one or more second physical examination items to be pushed according to the output of the preset support vector machine model; and pushing the physical examination push information containing one or more of the second physical examination items to the client.

[0006] Optionally, the method for pushing physical examination information further includes: iteratively performing the following operations until receiving information sent by the client indicating the end of the selection operation: receiving one or more new physical examination items selected by the client based on one or more of the second physical examination items included in the physical examination push information; inputting the new physical examination items into the trained preset support vector machine model, and determining in real time one or more new second physical examination items to be pushed that are associated with the new physical examination items based on the results output by the preset support vector machine model.

[0007] Optionally, after receiving information sent by the client indicating the end of the selection operation, the method for pushing physical examination information further includes: storing the multiple first physical examination items and newly added physical examination items selected by the client as a physical examination item set corresponding to the user feature data.

[0008] Optionally, the method for pushing physical examination information further includes: dividing the user feature data into multiple dimensions, and combining multiple dimensions, and for multiple dimension combinations, dividing the physical examination item set into physical examination item combinations corresponding to each dimension combination, and storing the dimension combinations and the physical examination item combinations accordingly.

[0009] Optionally, the method for pushing physical examination information further includes: in the event that multiple first physical examination items corresponding to the user characteristic data fail to be obtained, based on the user characteristic data, determining one or more target physical examination item combinations to be pushed for the client from a plurality of physical examination item combinations.

[0010] Optionally, the method for pushing physical examination information further includes: obtaining a plurality of stored historical physical examination samples, the historical physical examination samples including user feature data and a plurality of physical examination items corresponding to the user feature data; parsing each of the historical physical examination samples to obtain a plurality of physical examination factors, and setting a corresponding sample label for each physical examination factor; using the physical examination factors with sample labels as training physical examination data samples, and iteratively training the original support vector machine model to obtain the preset support vector machine model.

[0011] Optionally, the original support vector machine model includes a classification surface; the physical examination factors provided with sample labels are used as training physical examination data samples to iteratively train the original support vector machine model, including: using the training physical examination data samples to iteratively train the classification surface parameters contained in the classification surface, so as to determine the optimal parameters corresponding to the classification surface parameters through training, wherein the optimal parameters make the data samples classified by the classification surface to which they belong have the maximum classification interval.

[0012] Optionally, determining the optimal parameters corresponding to the classification surface parameters includes: obtaining a classification function corresponding to the classification surface; wherein the classification function is constructed based on the training physical examination data samples, the classification surface parameters, and the functional constraints between the training physical examination data samples and the classification surface parameters; converting the classification function into a quadratic programming model; using a sequential minimum optimization algorithm to perform a solution operation on the quadratic programming model; and determining, based on a result obtained from the solution operation, the optimal parameters corresponding to the classification surface parameters contained in the classification function that satisfies the functional constraints.

[0013] Optionally, the sequential minimum optimization algorithm is used to perform a solution operation on the quadratic programming model, including: for each model parameter among multiple model parameters in the quadratic programming model, executing: taking the model parameter as a target parameter to be solved, and while other model parameters among the multiple model parameters except the target parameter remain unchanged, performing an iterative solution operation on the target parameter until the optimal parameter corresponding to the target parameter is determined.

[0014] To achieve the above-mentioned purpose, according to a second aspect of an embodiment of the present invention, a device for pushing physical examination information is provided, characterized in that it includes: a data acquisition module, an information determination module and an information push module; wherein,

[0015] The data acquisition module is used to acquire user characteristic data corresponding to the client and a plurality of first physical examination items corresponding to the user characteristic data in response to the client's operation on the provided page;

[0016] The information determination module is used to input the user feature data and the plurality of the first physical examination items into a trained preset support vector machine model, and determine one or more second physical examination items to be pushed according to the output of the preset support vector machine model;

[0017] The push information module is used to push the physical examination push information containing one or more of the second physical examination items to the client.

[0018] Optionally, the device for pushing physical examination information is further used to iteratively perform the following operations until receiving information sent by the client indicating the end of the selection operation: receiving one or more new physical examination items selected by the client based on one or more of the second physical examination items included in the physical examination push information; inputting the new physical examination items into the trained preset support vector machine model, and determining in real time one or more new second physical examination items to be pushed that are associated with the new physical examination items based on the results output by the preset support vector machine model.

[0019] Optionally, the device for pushing physical examination information is used to, after receiving the information sent by the client indicating the end of the selection operation, further include: storing the multiple first physical examination items and newly added physical examination items selected by the client as a physical examination item set corresponding to the user characteristic data.

[0020] Optionally, the device for pushing physical examination information is also used to divide the user feature data into multiple dimensions and combine multiple dimensions. For multiple dimension combinations, the physical examination item set is divided into physical examination item combinations corresponding to each dimension combination, and the dimension combinations and the physical examination item combinations are stored accordingly.

[0021] Optionally, the device for pushing physical examination information is further used to determine one or more target physical examination item combinations to be pushed for the client from a plurality of physical examination item combinations based on the user characteristic data in the event that multiple first physical examination items corresponding to the user characteristic data fail to be obtained.

[0022] Optionally, the device for pushing physical examination information is further used to obtain multiple stored historical physical examination samples, the historical physical examination samples including user feature data and multiple physical examination items corresponding to the user feature data; analyze each of the historical physical examination samples to obtain multiple physical examination factors, and set a corresponding sample label for each physical examination factor; use the physical examination factors set with sample labels as training physical examination data samples, and iteratively train the original support vector machine model to obtain the preset support vector machine model.

[0023] Optionally, the original support vector machine model included in the device for pushing physical examination information includes a classification surface; the physical examination factors set with sample labels are used as training physical examination data samples, and the original support vector machine model is iteratively trained, including: using the training physical examination data samples to iteratively train the classification surface parameters contained in the classification surface, so as to determine the optimal parameters corresponding to the classification surface parameters through training, wherein the optimal parameters make the data samples classified by the classification surface to which it belongs have the maximum classification interval.

[0024] Optionally, the device for pushing physical examination information is used to determine the optimal parameters corresponding to the classification surface parameters, including: obtaining a classification function corresponding to the classification surface; wherein the classification function is constructed based on the training physical examination data samples, the classification surface parameters, and the functional constraints between the training physical examination data samples and the classification surface parameters; converting the classification function into a quadratic programming model; using a sequential minimum optimization algorithm to perform a solution operation on the quadratic programming model; and determining, based on the results of the solution operation, the optimal parameters corresponding to the classification surface parameters contained in the classification function that satisfy the functional constraints.

[0025] Optionally, the device for pushing physical examination information is used to use a sequential minimum optimization algorithm to perform a solution operation on the quadratic programming model, including: for each model parameter among multiple model parameters in the quadratic programming model, executing: taking the model parameter as a target parameter to be solved, and while other model parameters among the multiple model parameters except the target parameter remain unchanged, performing an iterative solution operation on the target parameter until the optimal parameter corresponding to the target parameter is determined.

[0026] To achieve the above-mentioned purpose, according to the third aspect of an embodiment of the present invention, there is provided an electronic device for pushing physical examination information, characterized in that it includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described in the above-mentioned method for pushing physical examination information.

[0027] To achieve the above-mentioned purpose, according to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, characterized in that when the program is executed by a processor, any method as described in the above-mentioned method for pushing physical examination information is implemented.

[0028] An embodiment of the above invention has the following advantages or beneficial effects: it can determine one or more second physical examination items to be pushed according to user feature data and the corresponding first physical examination items by using a trained preset support vector machine model, and push the physical examination push information containing the second physical examination items to the client; the embodiment of the present invention improves the degree of refinement in determining physical examination information by determining the second physical examination items to be recommended in real time, provides personalization and flexibility of the pushed physical examination information, and greatly improves the user experience.

[0029] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0031] Figure 1 It is a flowchart of a method for pushing physical examination information provided by an embodiment of the present invention;

[0032] Figure 2 is a schematic diagram of a process for pushing physical examination information provided by another embodiment of the present invention;

[0033] Figure 3 It is a schematic diagram of a flow chart of training a preset support vector machine model provided by an embodiment of the present invention;

[0034] Figure 4 It is a structural schematic diagram of a device for pushing physical examination information provided by an embodiment of the present invention;

[0035] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0036] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0038] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0039] In the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0040] After obtaining user characteristic data or physical examination information, we will de-identify the data through technical means. When it is necessary to display the information, we will desensitize your information by using methods including de-identification or anonymization to protect the security of your information.

[0041] In order to count the usage of our products / services, we will aggregate, analyze and use the technically processed user data and share the processed statistical information with third parties. We will use secure encryption technology and other methods to ensure that the recipient of the information cannot re-identify a specific individual.

[0042] The existing method of determining physical examination items for users often provides a set of fixed physical examination items (such as a physical examination package). The current method has the problem of low personalization and poor flexibility. For example, users cannot add physical examination items in real time, and cannot provide users with personalized physical examination item options according to user portraits.

[0043] In view of this, if Figure 1 As shown, an embodiment of the present invention provides a method for pushing physical examination information, which may include the following steps:

[0044] Step S101: in response to an operation of a client on a provided page, obtaining user characteristic data corresponding to the client and a plurality of first physical examination items corresponding to the user characteristic data.

[0045] Specifically, the user can operate the page providing the physical examination items through the client, such as browsing, refreshing, clicking, selecting and other gesture operations on the physical examination page; it can be understood that by obtaining the user information logged in to the client, the corresponding user identification can be parsed, so that the user characteristic data matching the user identification and the multiple first physical examination items corresponding to the user characteristic data can be found in the physical examination data source. Among them, the user characteristic data may include name, age, address, gender, and multiple historical data related to health provided by other users; the multiple first physical examination items corresponding to the user characteristic data may be physical examination items selected by the user. In an embodiment of the present invention, the physical examination items are element-level subdivision items. For example, for the blood routine category, it can be subdivided into N kinds (for example, 26 kinds, 30 kinds, etc.) of specific blood physical examination items, and each element-level physical examination item is a physical examination item described in the embodiment of the present invention. It can be seen that the embodiment of the present invention improves the refinement and personalization of the push physical examination information to a large extent through the selection and management of element-level physical examination items.

[0046] Further preferably, when acquiring the user characteristic data and the multiple first physical examination items corresponding to the user characteristic data, data matching can be performed through the MD5 signature algorithm, thereby improving the confidentiality of the user information and the matching efficiency. For example, for the following example data:

[0047] The MD5 value of {"age":24,"name":"User 1"} is

[0048] e8f13a8d567e29a5b7bc120640c44626

[0049] The MD5 value of {"age":25,"name":"User 2"} is

[0050] 1e2cdfb6601b80526d6fc4a30cae5a06

[0051] For user 1, the corresponding MD5 value can be used to search for one or more matching first physical examination items in the physical examination data source, where the physical examination data source can be stored in the cache, thereby further improving the data matching efficiency; the present invention does not limit the medium for storing the data source and the specific form and content of the data source.

[0052] Step S102: input the user feature data and the plurality of the first physical examination items into a trained preset support vector machine model, and determine one or more second physical examination items to be pushed according to the output of the preset support vector machine model.

[0053] Specifically, a trained preset support vector machine model is used to perform calculations based on the input user feature data and multiple first physical examination items, and multiple probability values ​​are output. One or more second physical examination items to be pushed are determined for the corresponding user through the numerical values ​​of the probability values. For example, physical examination items with larger probability values ​​or physical examination items with probability values ​​exceeding the set probability threshold can be determined as second physical examination items to be pushed.

[0054] In an embodiment of the present invention, the preset support vector machine model may be an SVM (Support Vector Machine, SVM for short) model. The trained preset support vector machine model may be used to calculate one or more newly added second physical examination items for the user based on the user portrait (user characteristic data) and the physical examination items (first physical examination items) that the user has selected. For example, based on user characteristic data such as the user's exposure to smoke, age, and the city where the user lives, in addition to the basic lung physical examination items, other refined physical examination items for the lungs (i.e., one or more second physical examination items to be pushed) are provided for the user to select.

[0055] It can be understood that the one or more second physical examination items to be pushed are element-level detailed items, and are newly added physical examination items different from the first physical examination items that the user has selected.

[0056] Further, preferably, after receiving the newly added physical examination items selected by the user from the second physical examination items via the client, continue to use the preset support vector machine model in real time to output results for the user based on the newly added physical examination items, that is, determine in real time one or more newly added second physical examination items to be pushed that are associated with the newly added physical examination items. Similarly, iteratively perform the above operations until receiving information sent by the client indicating the end of the selection operation; that is, iteratively perform the following operations until receiving information sent by the client indicating the end of the selection operation: receive one or more newly added physical examination items selected by the client based on one or more of the second physical examination items included in the physical examination push information; input the newly added physical examination items into the trained preset support vector machine model, and determine in real time one or more newly added second physical examination items to be pushed that are associated with the newly added physical examination items based on the results output by the preset support vector machine model.

[0057] It can be seen from this that the embodiments of the present invention can dynamically and in real time receive the newly added physical examination items selected by the user on the client from the second physical examination items to be recommended, and further perform the step of determining the physical examination items to be recommended in the next iteration cycle based on the newly added physical examination items, and perform multiple iterative calculations and determine the physical examination items to be recommended based on the newly added physical examination items selected by the user; the accuracy of the physical examination information pushed to the user is further improved, and the personalization and efficiency of determining the pushed physical examination information are improved.

[0058] Step S103: Pushing the physical examination push information including one or more of the second physical examination items to the client.

[0059] Specifically, after the preset support vector machine model determines one or more of the second physical examination items, physical examination push information containing one or more of the second physical examination items is pushed to the client, so that the client displays the physical examination push information containing one or more of the second physical examination items in multiple forms, so that the user can perform page operations on one or more of the second physical examination items, such as selecting newly added physical examination items, or directly ending the selection, or ending the selection after selecting newly added physical examination items multiple times, etc.

[0060] like Figure 2 As shown, an embodiment of the present invention provides a process for pushing physical examination information, which may include the following steps:

[0061] Step S201: input the user feature data and a plurality of the first physical examination items into a trained preset support vector machine model, and determine one or more second physical examination items to be pushed according to the output of the preset support vector machine model.

[0062] Step S202: Determine whether information for ending the selection operation is received, if so, execute step S205, otherwise execute step S203.

[0063] Step S203: receiving one or more newly added physical examination items selected by the client based on one or more second physical examination items included in the physical examination push information.

[0064] Step S204: input the newly added physical examination items into the trained preset support vector machine model, and determine in real time one or more newly added second physical examination items to be pushed that are associated with the newly added physical examination items according to the results output by the preset support vector machine model.

[0065] The description of step S201 to step S204 is: iteratively perform the following operations until receiving information sent by the client indicating the end of the selection operation: receiving one or more newly added physical examination items selected by the client based on one or more of the second physical examination items included in the physical examination push information; inputting the newly added physical examination items into the trained preset support vector machine model, and determining in real time one or more newly added second physical examination items to be pushed that are associated with the newly added physical examination items based on the results output by the preset support vector machine model.

[0066] Step S205: storing the plurality of first physical examination items and newly added physical examination items selected by the client as a physical examination item set corresponding to the user characteristic data.

[0067] Specifically, the first physical examination items and newly added physical examination items selected by each user through the client are stored together with the user characteristic data as a physical examination item set. It can be understood that the physical examination item sets corresponding to different users can be different, that is, the corresponding physical examination items are determined according to the user portrait. That is, after receiving the information sent by the client indicating the end of the selection operation, it further includes: storing the multiple first physical examination items and newly added physical examination items selected by the client as a physical examination item set corresponding to the user characteristic data.

[0068] Furthermore, based on multiple sets of physical examination items, multiple combinations of physical examination items are processed, that is, the user characteristic data is divided into multiple dimensions, and multiple dimensions are combined. For multiple dimension combinations, the physical examination item set is divided into physical examination item combinations corresponding to each combination of the dimensions, and the dimension combinations and the physical examination item combinations are stored accordingly. For example: for the user characteristics of age, address, gender, and multiple dimensions of multiple historical data related to health provided by other users are combined into multiple dimension combinations, such as combining the dimensions of gender, age, and address to determine multiple physical examination item combinations for the dimension combination, and the dimension combinations and the physical examination item combinations are stored accordingly; for another example, combining multiple dimensions such as gender, marital status, age, and age to determine multiple physical examination item combinations for the dimension combination, and the dimension combinations and the physical examination item combinations are stored accordingly; by constructing and storing the dimension combinations and the physical examination item combinations on the basis of personalization, matching dimension combinations and physical examination item combinations (i.e., target physical examination item combinations) can be provided for users who have not selected physical examination items (i.e., new users) ; Further, in the combination of physical examination items selected by the new user, the step of inputting the user characteristic data and multiple first physical examination items into a trained preset support vector machine model can be further performed for the new user, and determining one or more second physical examination items to be pushed according to the output of the preset support vector machine model, thereby further improving the user experience, that is, for the case where multiple first physical examination items corresponding to the user characteristic data fail to be obtained, wherein the case where the acquisition failure occurs, for example, when a new user is newly added to the client, or a new user who has not selected a physical examination item, and the corresponding first physical examination item is not found, then, based on the user characteristic data, one or more target physical examination item combinations to be pushed are determined for the client from the multiple physical examination item combinations.

[0069] like Figure 3 As shown, an embodiment of the present invention provides a method for training a preset support vector machine model, which may include the following steps:

[0070] Step S301: Acquire a plurality of stored historical physical examination samples, wherein the historical physical examination samples include user characteristic data and a plurality of physical examination items corresponding to the user characteristic data.

[0071] Specifically, the historical physical examination samples can be obtained from the stored physical examination item set corresponding to the user characteristic data, and each piece of data in the obtained physical examination item set within a set time range is used as a historical physical examination sample.

[0072] Step S302: Analyze each of the historical physical examination samples to obtain multiple physical examination factors, and set a corresponding sample label for each physical examination factor.

[0073] Specifically, each piece of data in the physical examination item set is used as a historical physical examination sample, and multiple physical examination factors in a piece of historical physical examination sample data are parsed. For example, the physical examination factors include age, gender, address, marital status, and selected physical examination item identifiers.

[0074] Furthermore, a corresponding sample label is set for each physical examination factor; for example, a sample data with a sample label is as follows:

[0075] {"age":22,"gender":1,"items":["770763509250","852245126658"..."7707763493890"],"marry":2}

[0076] When training the support vector machine model, a plurality of physical examination factors with sample labels are used as training samples.

[0077] Furthermore, for example, the training sample T is represented as:

[0078] T={(x1,y1),...,(x i ,y i )}∈(X·Y) l

[0079] Among them, (x i ,y i ) is the characteristic vector corresponding to the physical examination factor of the embodiment of the present invention, where x i Represents the input feature vector, xi belongs to X, y i Represents the output vector, y i Belongs to Y, i represents the sample identifier.

[0080] Step S303: using the physical examination factors with sample labels as training physical examination data samples, and iteratively training the original support vector machine model to obtain the preset support vector machine model.

[0081] Specifically, the original support vector machine model is iteratively trained using the physical examination data samples, and the trained original support vector machine model is used as the preset support vector machine model of the embodiment of the present invention.

[0082] The following describes the process of training a support vector machine (SVM) model:

[0083] The SVM model can project samples from the input space to the high-dimensional feature space through a nonlinear mapping function, and establish an optimal classification surface in the high-dimensional feature space. In order to make the classification surface have a high classification accuracy and a large classification interval, the SVM is transformed from a classification problem to an optimal solution problem. That is, the classification surface parameters contained in the classification surface are iteratively trained using the training physical examination data samples to determine the optimal parameters corresponding to the classification surface parameters through training, that is, to obtain the optimal classification surface. The data samples classified by the optimal classification surface have the maximum classification interval, so as to improve the classification accuracy of the preset support vector machine model output.

[0084] That is, the original support vector machine model includes a classification surface; the physical examination factors provided with sample labels are used as training physical examination data samples to iteratively train the original support vector machine model, including: using the training physical examination data samples to iteratively train the classification surface parameters contained in the classification surface, so as to determine the optimal parameters corresponding to the classification surface parameters through training, wherein the optimal parameters make the data samples classified by the classification surface to which they belong have the maximum classification interval.

[0085] Specifically, for example, the classification function corresponding to the classification surface of the SVM model is shown in formula (1):

[0086]

[0087] Among them, st represents function constraints, the classification surface parameters to be trained include "w", "b", etc., and the optimal parameters obtained as a result of the training are the optimal parameters of the classification surface parameters; that is, determining the optimal parameters corresponding to the classification surface parameters includes: obtaining the classification function corresponding to the classification surface; wherein the classification function is constructed based on the training physical examination data samples, the classification surface parameters, and the function constraints between the training physical examination data samples and the classification surface parameters.

[0088] Further, the partition function class is converted into a quadratic programming model. Specifically, the method of converting the partition function class into the quadratic programming model is:

[0089] First, construct the Lagrangian function corresponding to the classification function as shown in formula (2):

[0090]

[0091] Furthermore, by using strong duality transformation and taking partial derivatives of parameters w and b, we get formula (3):

[0092]

[0093]

[0094] Furthermore, combined with the classification function, we obtain the quadratic programming model shown in formula (4):

[0095]

[0096] Furthermore, a sequential minimum optimization algorithm is used to perform a solution operation on the quadratic programming model; and according to the result of the solution operation, the optimal parameters corresponding to the classification surface parameters contained in the classification function that satisfies the function constraint are determined. The sequential minimum optimization algorithm may be an SMO (Sequential Minimal Optimization) algorithm, and a sequential minimum optimization algorithm is used to perform a solution operation on the quadratic programming model shown in formula (4), and according to the solution result, the optimal parameters w, b, etc. corresponding to the classification surface parameters contained in the classification function that satisfies the function constraint are determined.

[0097] Specifically, when using the sequential minimum optimization algorithm to perform a solution operation on the quadratic programming model shown in formula (4), only one model parameter can be trained and optimized in each training cycle, and the other model parameters are first set to be fixed, that is, only the current parameter of the current cycle is determined, and the current parameter is the target parameter to be solved among the multiple model parameters in the quadratic programming model, and the optimization parameter value corresponding to the target parameter is obtained. The specific method can set the constraint relationship between the current parameter (i.e., the target parameter) and other model parameters, for example, the constraint relationship is shown in formula (5):

[0098] λ i y i +λ j y j =c λ i ≥0,λ j ≥0 (5)

[0099] in From this we can conclude That is, the expression of λi can be used to replace λj, so that the target problem is transformed into an optimization problem with only one constraint, in which the only constraint relationship is λi≥0. It can be understood that for an optimization problem with only one constraint, the partial derivative of the optimization target can be obtained on λi, and the derivative can be set to zero, so as to obtain the variable value λi, and then λj (i.e., the optimal parameter) can be obtained according to λi (i.e., the model parameter or the target parameter to be solved), that is, the optimal parameter corresponding to the target parameter is determined. Further, after multiple iterative training cycles until the model converges, the optimal parameter is obtained through SMO, that is, the sequential minimum optimization algorithm is used to perform a solution operation on the quadratic programming model, including: for each model parameter of the multiple model parameters in the quadratic programming model, the following is performed: taking the model parameter as the target parameter to be solved, and performing an iterative solution operation on the target parameter when the other model parameters except the target parameter among the multiple model parameters are unchanged, until the optimal parameter corresponding to the target parameter is determined. By using a quadratic programming model and training model parameters one by one (when training a certain parameter, other parameters except the parameter are fixed), the efficiency of training the SVM model is improved and computing resources are saved.

[0100] The description of step S301 to step S303 is: obtain multiple stored historical physical examination samples, the historical physical examination samples include user feature data and multiple physical examination items corresponding to the user feature data; analyze each of the historical physical examination samples to obtain multiple physical examination factors, and set a corresponding sample label for each physical examination factor; use the physical examination factors set with sample labels as training physical examination data samples, iteratively train the original support vector machine model, so as to obtain the preset support vector machine model.

[0101] like Figure 4 As shown, an embodiment of the present invention provides a device 400 for pushing physical examination information, including: a data acquisition module 401, an information determination module 402 and an information push module 403; wherein,

[0102] The data acquisition module 401 is used to acquire user characteristic data corresponding to the client and a plurality of first physical examination items corresponding to the user characteristic data in response to the client's operation on the provided page;

[0103] The information determination module 402 is used to input the user feature data and the plurality of the first physical examination items into a trained preset support vector machine model, and determine one or more second physical examination items to be pushed according to the output of the preset support vector machine model;

[0104] The push information module 403 is used to push the physical examination push information including one or more of the second physical examination items to the client.

[0105] An embodiment of the present invention also provides an electronic device for pushing physical examination information, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in any of the above embodiments.

[0106] An embodiment of the present invention further provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method provided in any of the above embodiments is implemented.

[0107] Figure 5 An exemplary system architecture 500 is shown to which the method for pushing physical examination information or the apparatus for pushing physical examination information according to the embodiments of the present invention can be applied.

[0108] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0109] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various client applications can be installed on terminal devices 501, 502, 503, such as e-commerce client applications, web browser applications, search applications, instant messaging tools, and email clients.

[0110] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting various client applications, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0111] The server 505 may be a server that provides various services, such as a background management server that provides support for the client application used by the user using the terminal devices 501, 502, and 503. The background management server may process the received client operation on the provided physical examination page, and push the generated physical examination push information containing one or more second physical examination items to the terminal device.

[0112] It should be noted that the method for pushing physical examination information provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the device for pushing physical examination information is generally set in the server 505 .

[0113] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0114] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0115] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0116] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0117] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0118] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The modules and / or units involved in the embodiments of the present invention may be implemented in software or hardware. The modules and / or units described may also be provided in a processor. For example, they may be described as follows: a processor includes a data acquisition module, an information determination module, and an information push module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the information push module may also be described as a "module for pushing physical examination push information containing one or more second physical examination items to a client."

[0121] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: in response to the client's operation on the provided page, obtaining user feature data corresponding to the client and multiple first physical examination items corresponding to the user feature data; inputting the user feature data and multiple first physical examination items into a trained preset support vector machine model, and determining one or more second physical examination items to be pushed according to the output of the preset support vector machine model; pushing physical examination push information containing one or more second physical examination items to the client.

[0122] The embodiments of the present invention can determine one or more second physical examination items to be pushed based on user feature data and the corresponding first physical examination items by using a trained preset support vector machine model, and push the physical examination push information containing the second physical examination items to the client; the embodiments of the present invention improve the refinement of pushing physical examination information by iteratively determining the newly added second physical examination items to be recommended in real time, and improve the personalization and flexibility of pushing physical examination information; and improve the user experience to a great extent.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for pushing physical examination information, characterized in that: include: In response to an operation of the client on the provided page, acquiring user characteristic data corresponding to the client and a plurality of first physical examination items corresponding to the user characteristic data; Inputting the user feature data and the plurality of the first physical examination items into a trained preset support vector machine model, and determining one or more second physical examination items to be pushed according to the output of the preset support vector machine model; Pushing the physical examination push information including one or more of the second physical examination items to the client.

2. The method according to claim 1, characterized in that Further including: Iteratively perform the following operations until receiving information sent by the client indicating the end of the selection operation: Receiving one or more newly added physical examination items selected by the client based on one or more second physical examination items included in the physical examination push information; The newly added physical examination items are input into the trained preset support vector machine model, and one or more newly added second physical examination items to be pushed that are associated with the newly added physical examination items are determined in real time according to the results output by the preset support vector machine model.

3. The method according to claim 2, characterized in that After receiving the information sent by the client indicating the end of the selection operation, the method further includes: The plurality of first physical examination items and newly added physical examination items selected by the client are stored as a physical examination item set corresponding to the user characteristic data.

4. The method according to claim 3, characterized in that Also includes: The user characteristic data is divided into multiple dimensions, and the multiple dimensions are combined. For multiple dimension combinations, the physical examination item set is divided into physical examination item combinations corresponding to each dimension combination, and the dimension combinations and the physical examination item combinations are stored correspondingly.

5. The method according to claim 4, characterized in that Further including: In case that the acquisition of multiple first physical examination items corresponding to the user characteristic data fails, Based on the user characteristic data, one or more target physical examination item combinations to be pushed are determined for the client from the multiple physical examination item combinations.

6. The method according to claim 1, characterized in that Further including: Acquire a plurality of stored historical physical examination samples, wherein the historical physical examination samples include user characteristic data and a plurality of physical examination items corresponding to the user characteristic data; Analyze each of the historical physical examination samples to obtain multiple physical examination factors, and set a corresponding sample label for each physical examination factor; The physical examination factors provided with sample labels are used as physical examination data samples for training, and the original support vector machine model is iteratively trained to obtain the preset support vector machine model.

7. The method according to claim 6, characterized in that The original support vector machine model includes a classification surface; The method of using the physical examination factors provided with sample labels as training physical examination data samples and iteratively training the original support vector machine model comprises: The classification surface parameters included in the classification surface are iteratively trained using the training physical examination data samples, so as to determine the optimal parameters corresponding to the classification surface parameters through training, wherein the optimal parameters enable the data samples classified by the classification surface to which they belong to have the maximum classification interval.

8. The method according to claim 7, characterized in that The determining of the optimal parameters corresponding to the classification surface parameters includes: Acquire a classification function corresponding to the classification surface; wherein the classification function is constructed based on the training physical examination data sample, the classification surface parameter, and a function constraint between the training physical examination data sample and the classification surface parameter; Converting the partition function class into a quadratic programming model; Using a sequential minimum optimization algorithm, performing a solution operation on the quadratic programming model; According to the result obtained by the solving operation, the optimal parameters corresponding to the classification surface parameters included in the classification function that meets the function constraint are determined.

9. The method according to claim 8, characterized in that The method of using a sequential minimum optimization algorithm to perform a solution operation on the quadratic programming model includes: For each of the plurality of model parameters in the quadratic programming model, executing: The model parameters are taken as the target parameters to be solved. When other model parameters except the target parameter among the plurality of model parameters remain unchanged, an iterative solution operation is performed on the target parameter until an optimal parameter corresponding to the target parameter is determined.

10. A device for pushing physical examination information, characterized in that: include: Acquisition module, information determination module and information push module; wherein, The data acquisition module is used to acquire user characteristic data corresponding to the client and a plurality of first physical examination items corresponding to the user characteristic data in response to the client's operation on the provided page; The information determination module is used to input the user feature data and the plurality of the first physical examination items into a trained preset support vector machine model, and determine one or more second physical examination items to be pushed according to the output of the preset support vector machine model; The push information module is used to push the physical examination push information containing one or more of the second physical examination items to the client.

11. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images