A data processing method and apparatus

Abstract

This application discloses a data processing method and apparatus. The method includes: acquiring a user's social attributes and / or vital signs; determining a user group composed of training users similar to the user's social attributes and / or vital signs; training a diagnostic model component using the group data of the user group; and obtaining a trained diagnostic model component, wherein the diagnostic model component is used to diagnose the user's health status. Using this application, a more accurate diagnostic result can be given for the user by leveraging the user group to which the user belongs.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data processing method and apparatus. Background Technology

[0002] With the development of internet technology, users often use the internet to diagnose their illnesses themselves after experiencing physical discomfort or receiving a medical examination report.

[0003] However, the same symptom may be caused by different diseases for different users. For example, when a user searches online based on "increased blood flow velocity in the left vertebral artery" from a physical examination report, they may get multiple diagnostic results such as "cerebral hypoxia and insufficient cerebral blood supply," "cerebral vasospasm," "cervical spondylosis and leg artery spasm," and "left vertebral artery plaque." Faced with so many diagnostic results, users cannot accurately determine the type of disease they have. It can be seen that the above diagnostic methods not only waste users' time and energy but also fail to provide accurate diagnostic results. Summary of the Invention

[0004] This application provides a data processing method and apparatus to at least solve the problems mentioned above.

[0005] This application also provides a data processing method, the method comprising: acquiring a user's social attributes and / or vital signs; determining a user group composed of training users similar to the user's social attributes and / or vital signs; training a diagnostic model component using the group data of the user group, and acquiring a trained diagnostic model component, wherein the diagnostic model component is used to diagnose the user's health status.

[0006] This application embodiment also provides a data processing method, which uses a medical diagnostic model trained by the above method to perform a medical diagnosis, including: inputting the social attributes and / or vital sign attributes into the trained medical diagnostic model to obtain the user's diagnostic information.

[0007] This application embodiment also provides a data processing method, the method receiving a medical service request input by a user, wherein the medical service request includes the user's medical diagnosis form; identifying the user's attribute information from the medical diagnosis form; and determining a user group composed of training users whose attribute information is similar to that of the user.

[0008] This application also provides a data processing method, the method including: obtaining a user's academic ability attributes and / or educational background attributes; determining a user group composed of training users whose academic ability attributes and / or educational background attributes are similar to those of the user; training a recommendation model component using the group data of the user group to obtain a trained recommendation model component, wherein the training recommendation model component is used to recommend training courses to the user.

[0009] This application embodiment also provides a data processing method, which utilizes a training recommendation model component trained by the above method, including inputting the academic ability attribute and / or educational background attribute into the trained training recommendation model component to obtain the user's training recommendation information.

[0010] This application also provides a data processing apparatus, including: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing the aforementioned method.

[0011] According to one aspect of the present invention, a computer-readable storage medium is provided for storing one or more programs, said one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the aforementioned method.

[0012] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0013] The data processing method according to an exemplary embodiment of this application can use a user's social attributes and / or vital signs to determine the user group to which the user belongs, and use the user group to determine the user's diagnostic information, making the diagnostic information more evidence-based and more accurate. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0015] Figure 1 This is a diagram illustrating a medical diagnostic system according to an exemplary embodiment of this application;

[0016] Figure 2 This is a flowchart illustrating the steps of a data processing method according to an exemplary embodiment of this application;

[0017] Figure 3 This is a block diagram illustrating a data processing method according to an exemplary embodiment of this application;

[0018] Figure 4 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0021] Figure 1 This is a diagram illustrating a medical diagnostic system according to an exemplary embodiment of this application.

[0022] like Figure 1 As shown, the medical diagnostic system includes an electronic device 110 with an application program installed and an application server 120 providing services for the application. The application program refers to an application with medical retrieval functions, such as a medical-related application or a search application. Furthermore, the application program can also provide services such as diagnosis, purchasing, and consultation.

[0023] In an implementation, the electronic device 110 may be an electronic device with a display unit, including but not limited to any of the following devices: personal computer (PC), mobile device (such as cellular phone, personal digital assistant (PDA), digital camera, portable game console, MP3 player, portable / personal multimedia player (PMP), handheld e-reader, tablet PC, portable laptop PC and GPS navigator), smart TV, etc.

[0024] When users experience physical discomfort or receive a medical diagnosis, they typically use the internet to self-diagnose their illness. Specifically, users can use electronic devices to run applications with medical search functions. They can then input their physical characteristics, such as headache, fever of 39 degrees Celsius, and sore throat. To improve accuracy, other attributes are usually input simultaneously, such as gender, age, and occupation. These applications can then use this combined attribute information for diagnosis.

[0025] Furthermore, users can perform searches using specific indicator data from their medical examination reports after completing various physical examinations. For example, a user can enter "hemoglobin is high" from their medical examination report. Going further, the above attribute information can be combined with the indicator data from the medical examination report for a search. For instance, a user can enter multiple search terms such as "39 ​​years old," "male," and "high hemoglobin" into a medical-related application and, after completing the input, send a medical service request to the application server 120.

[0026] After receiving the medical service request, application server 120 follows the instructions. Figure 2 The method shown determines the user's diagnostic information and sends the diagnostic information to the electronic device 110. The electronic device 110 receives and displays the diagnostic information. In addition, the application server 120 can also provide the user with a health plan based on the determined diagnostic information.

[0027] The following will refer to Figure 2 The data processing method according to exemplary embodiments of this application will be described in detail. In practice, the data processing method of exemplary embodiments of this application may be a method executed by an application server corresponding to each application, or it may be a method executed by an independent module coupled to the server. That is, the data processing device may be a module embedded in the application server or a module external to the application server, and this application does not set any limitations in this regard.

[0028] Figure 2 This is a flowchart illustrating the steps of a data processing method according to an exemplary embodiment of this application.

[0029] In step S210, the user's social attributes and / or vital signs are obtained. According to an exemplary embodiment of this application, the social attributes include information on the user's social identity and / or activities that affect the user's health. For example, the social attributes may be the user's occupation (e.g., construction worker, teacher, programmer, etc.), location (e.g., mountainous area, plain, plateau, etc.), or work and rest habits (including regular work and rest, frequently staying up late), exercise habits (e.g., no exercise, occasional exercise, frequent exercise), etc.

[0030] The vital signs attributes include information characterizing the user's physical condition. For example, the vital signs attributes may include the user's gender, age, height, weight, or information characterizing the user's various organs obtained through a physical examination. For example, information characterizing blood (such as hemoglobin, white blood cells, and red blood cells) can be determined through a complete blood count test, or information characterizing the liver (such as alanine aminotransferase (ALT) and aspartate aminotransferase (AST)) can be determined through liver function tests.

[0031] In implementation, users can use methods such as Figure 1The electronic device 110 displays instructions on its page for inputting the user's social attributes and / or vital signs. According to an exemplary embodiment of this application, a user can upload a medical information form according to the instructions. This medical information form may include the user's basic information (e.g., name, age, gender, and region), information about the doctor treating the user (e.g., doctor's name and level), department information, diagnosis time, drug attribute information (e.g., generic name, brand name, specifications, manufacturer, etc.), quantity of drugs purchased, and precautions for the drugs, such as daily dosage and administration time. It should be noted that the medical information form may use different templates depending on the hospital, and may even be handwritten by the doctor.

[0032] In addition, the medical information form also includes a physical examination report obtained after a health check of the user's body. The physical examination report may include examination data of different tissues of the user, such as a blood routine test report for blood, a liver function test report for liver function, and a lung function test report for lung function.

[0033] In addition, the social attributes and / or physical attributes may also be Figure 1 The historical information already stored in the application server 120 means that the application server 120 stores the user and user information (including social attributes and / or vital signs attributes), wherein the user information includes the medical record information or medical information form that the user has entered.

[0034] After the electronic device 110 acquires the aforementioned medical information form, it can recognize the text data on the form. For example, a user can use the image acquisition device (e.g., a camera) of the electronic device 110 to acquire an image of the medical diagnosis form and use image recognition methods to identify the text data in the image. For example, using OCR (Optical Character Recognition) technology, the text content in the image can be converted into editable text, and the user's social attributes and / or vital signs can be identified from it.

[0035] In step S220, a user group consisting of training users similar to the social attributes and / or physical attributes of the user is determined.

[0036] Specifically, the method assigns corresponding weight values ​​to the social attribute and the physical attribute according to preset rules. In implementation, the importance level of the social attribute and the physical attribute can be predetermined, and the weight value assigned can be determined based on the importance level. The importance level is usually proportional to the degree of influence of the attribute on health; that is, the greater the influence of the attribute on health, the greater the weight value assigned to it.

[0037] According to an exemplary embodiment of this application, in order to more accurately determine the user group to which the user belongs, a preset number of attributes can be selected from these social attributes and physical attributes. For example, ten attributes can be determined from these social attributes and physical attributes as classification criteria, and then weight values ​​can be assigned to these ten attributes according to their importance level.

[0038] Subsequently, the value range of these attributes can be determined. For attributes that are not quantified, discretization is performed. For example, after determining that a user's age is the classification criterion, the age can be divided into different age groups, and different age groups correspond to different values. For example, a 14-year-old boy can be classified into the age range of 10 to 20 years old and the corresponding value is 2.

[0039] After determining the rules for assigning values ​​to these social and / or physical attributes, training users similar to the target user can be selected from the training user set, and these users can be used to form a user group. Specifically, the social and physical attribute values ​​can be calculated for each training user in the training user set, and then the final value for that training user can be calculated using these social and physical attribute values ​​and their corresponding weights. In implementation, training users whose final values ​​exceed a predetermined threshold can be grouped into the same user group.

[0040] In step S230, the diagnostic model component is trained using the group data of the user group to obtain the trained diagnostic model component.

[0041] Specifically, attributes that influence the diagnostic information can be determined from the social attributes and the physical attributes as feature attributes. That is, the social attributes and the physical attributes can be used to better identify the user group, for example, identifying the user group as obese middle-aged male programmers, but these attributes are not suitable for diagnosing the user. Preferably, more attributes obtained from the physical attributes, especially the various indicators (i.e., attributes) obtained from the medical examination report, can be used as feature attributes.

[0042] Subsequently, the diagnostic model component can be trained using the feature attribute values ​​of the user group relative to the feature attribute and the corresponding disease information to obtain the trained diagnostic model component, wherein the diagnostic model component is used to diagnose the user's health status.

[0043] In implementation, the characteristic attribute value of each user group in the user group relative to the characteristic attribute can be determined first according to the value rules of the characteristic attribute.

[0044] For example, assuming the characteristic attributes include occupation, age, gender, body mass index (BMI), region, blood pressure, and blood sugar, then when the characteristic attribute includes the user's occupation, the occupation can be categorized as software developer, doctor, and tester; when the characteristic attribute is age, the age can be categorized as under 14 years old, 14 to 30 years old, and 30 to 50 years old; when the characteristic attribute is gender, the characteristic attribute can be categorized as male and female; when the characteristic attribute is BMI, the characteristic attribute can be categorized as underweight, normal, overweight, and obese; when the characteristic attribute is region, the characteristic attribute can be categorized as Beijing, Shanghai, Hubei, and Hunan; when the characteristic attribute is blood pressure, the characteristic attribute can be categorized as too high, normal, and too low; and when the characteristic attribute is blood sugar, the characteristic attribute can be categorized as too high, normal, and too low.

[0045] Based on the above value selection rules, the characteristic attribute values ​​of each user group in the user group relative to the above characteristic attributes can be determined respectively.

[0046] Subsequently, the diagnostic model component is constructed, which includes a decision tree model component. This decision tree model extracts a tree-like classification model from unordered training samples using an instance-based inductive learning method. Each non-leaf node in the tree structure records which feature was used for class determination, while each leaf node represents the final determined class. A classification path rule is formed from the root node to each leaf node.

[0047] In this application, the feature attribute values ​​and corresponding disease information can be used to train the decision tree model component until the root feature attribute and leaf feature attribute that serve as the root node and leaf node in the decision tree model are determined.

[0048] Specifically, using the feature attribute values ​​corresponding to each feature attribute and disease information, the information gain of the user group under each feature attribute is calculated. The information gain is used to measure the expected reduction in information entropy. The information entropy is an indicator used to measure the uncertainty of the message source. In other words, information entropy can be used to measure the degree of disorganization of the user group.

[0049] The feature attribute with the highest information gain is determined as the root feature attribute in the decision tree model. Subsequently, the range of values ​​for the root feature attribute can be used to classify the user group into at least one subset of users. For example, if user gender is determined as the root feature attribute, the user group can be classified into a subset of male users and a subset of female users.

[0050] For each user subset, the intermediate feature attributes (i.e., intermediate nodes) under the root feature attribute are determined by calculating the information gain of the user subset under all feature attributes except the root feature attribute. Each layer of intermediate feature attributes is regarded as the root feature attribute, and the direct lower layer intermediate feature attributes of each layer are determined in the above manner, until the user subset corresponding to the intermediate feature attribute of the last layer contains only a single feature attribute, then the intermediate feature attribute of that layer is regarded as a leaf feature attribute.

[0051] Furthermore, in practice, the user may belong to different user groups simultaneously. That is, the user group is determined according to different preset rules. For example, the same user may belong to both the group of older postpartum mothers and the group of middle-aged obese women. In this case, diagnostic model components can be trained according to different user groups to obtain the trained diagnostic model components.

[0052] Furthermore, according to exemplary embodiments of this application, the trained diagnostic model component can also be used to determine the user's diagnostic information.

[0053] Specifically, a user's social attributes and / or physical characteristics can be input into a trained medical diagnostic model to obtain the user's diagnostic information. Furthermore, attributes that influence the diagnostic information can be identified from the social attributes and / or physical characteristics as feature attributes, and then these feature attributes can be input into the trained medical diagnostic model to obtain the user's diagnostic information.

[0054] Optionally, after obtaining the user's diagnostic information in step S230, the method can recommend a health plan associated with the diagnostic information to the user. The health plan may include one or more combinations of dietary plans, sleep plans, exercise plans, and medication plans.

[0055] For example, if the diagnostic information indicates moderate to severe fatty liver, the health plan may include the user's diet plan (e.g., less oil, less salt, less sugar, and less liver intake), sleep plan (e.g., ensuring eight hours of sleep per day), exercise plan (e.g., half an hour of aerobic exercise per day), and medication plan (e.g., taking reduced glutathione).

[0056] In addition, the method can also determine the group disease information of the user group, wherein the group disease information includes the current disease information and / or the long-term susceptibility disease information of the user group, wherein the current disease information refers to the disease status that the user group currently generally has, and the long-term susceptibility disease information refers to the disease trend of the user group in the future.

[0057] For example, current health information for obese middle-aged male programmers might include cervical spondylosis, while their predisposition to liver diseases might include fatty liver, hair loss, and hyperglycemia. Thus, the method can provide the user with current health information and / or long-term predisposition to diseases within this group.

[0058] Furthermore, the method can also provide users with disease probabilities based on the proportion of each type of disease within the user group. For example, the method can graphically display the types of diseases in the user group and the probability of each disease type. Moreover, based on the disease information of the group, relevant health plans can be recommended to the user.

[0059] Furthermore, if the user belongs to different user groups and trains their respective diagnostic model components according to the different user groups and obtains the trained diagnostic model components, the user's feature attribute values ​​can be input into the trained diagnostic model components to determine at least one diagnostic information.

[0060] In summary, the data processing method according to the exemplary embodiments of this application can utilize a user's social attributes and / or physical characteristics to determine the user's user group, and use the user group to determine the user's diagnostic information, making the diagnostic information more evidence-based and accurate. Based on this, these attributes can be obtained from the user's uploaded medical information, making these attributes more representative of the user. Furthermore, by utilizing social attributes and / or physical characteristics to determine the user group, it is possible to find user groups similar to the user's situation. Furthermore, by assigning different weight values ​​to different attributes, it is possible to find user groups that better match the user's situation. Furthermore, by using the determined user group to train the diagnostic model component, the trained diagnostic model component can more accurately obtain the user's diagnostic information. Furthermore, based on the user's diagnostic information, health plans can be recommended to the user, improving the user experience. Furthermore, based on the user's stated user group, warnings can be issued regarding areas requiring attention, making the warnings more relevant to the user's situation and more persuasive. Furthermore, different user groups can be identified based on various user attributes, and diagnostic model components trained on different user groups can be used to obtain various diagnostic information, making the diagnostic information more accurate and with a wider coverage.

[0061] To more vividly illustrate exemplary embodiments of this application, reference will be made below. Figure 3 Further description. Figure 3 This is a block diagram illustrating a data processing method according to an exemplary embodiment of this application.

[0062] like Figure 3As shown, after receiving a medical information form, the user can run the relevant application running on the electronic device and use the image acquisition unit (e.g., camera) of the electronic device to take a picture and upload the medical information form.

[0063] Subsequently, the server corresponding to the relevant application can extract various attributes from the medical information form, including the user's social attributes and / or vital sign attributes. In practice, the server can also search the user's historical health records based on the user's identification information (e.g., the user's name, identification number, etc.) and extract the user's social attributes and / or vital sign attributes from the historical health records.

[0064] Subsequently, these social attributes and / or physical characteristics are used to determine the user group mentioned by the user. In implementation, different weight values ​​can be set for these social attributes and / or physical characteristics according to preset rules. For example, the weight value of gender can be set to the largest, and the weight value of attendance mode can be set to the smallest. Optionally, a predetermined number of attributes can also be selected from the extracted social attributes and / or physical characteristics.

[0065] Subsequently, diagnostic model components can be trained using user data from various user groups, such as... Figure 3 The diagnostic model component can be a decision tree model component, which has already been discussed in detail above and will not be repeated here. Finally, the selected feature attributes are input into the diagnostic model component to output the user's diagnostic information.

[0066] Furthermore, this application can also be applied to the field of education. Specifically, the method can obtain a user's academic ability attributes and / or educational background attributes, wherein the academic ability attributes include information about the user's learning ability, including the user's IQ, learning ability (e.g., concentration), hands-on ability, and knowledge level. The educational background attributes include information about the user's learning experience, including the user's educational background (e.g., winner of a provincial-level math Olympiad competition), current educational level (e.g., currently in the fourth grade of a primary school), etc.

[0067] As an example, the method can obtain the above information through an academic ability test form. Specifically, the method can receive an academic ability test form uploaded by a user; identify the text data on the academic ability test form; and obtain the educational background attribute and / or the academic ability attribute from the text data.

[0068] Then, the method can determine a user group composed of training users similar to the user's academic ability attribute and / or educational background attribute. Specifically, corresponding weight values ​​can be assigned to the academic ability attribute and / or the educational background attribute according to preset rules; by calculating the academic ability attribute value and / or the educational background attribute value and the corresponding weight value of each training user in the training user set, training users similar to the user are determined, and the user group composed of the training users is obtained. Finally, the group data of the user group is used to train the recommendation model component, and the trained training recommendation model component is obtained, wherein the training recommendation model component is used to recommend training courses to users.

[0069] Furthermore, the method can input the user's academic ability and / or educational background attributes into a trained training recommendation model component to obtain the user's training recommendation information. This training recommendation information includes educational and training courses suitable for the user.

[0070] Figure 4 A block diagram illustrating a data processing apparatus according to an exemplary embodiment of this application. (Refer to...) Figure 4 At the hardware level, the device includes a processor, an internal bus, and a computer-readable storage medium, wherein the computer-readable storage medium includes volatile memory and non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory and then executes it. Of course, in addition to software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0071] Specifically, the processor performs the following operations: acquiring the user's social attributes and / or vital signs; determining a user group consisting of training users similar to the user's social attributes and / or vital signs; training a diagnostic model component using the group data of the user group; and acquiring a trained diagnostic model component, wherein the diagnostic model component is used to diagnose the user's health status.

[0072] Optionally, the processor, in implementing the step of obtaining the user's social attributes and / or vital signs, includes: receiving a medical information form uploaded by the user; identifying the text data on the medical information form; and obtaining the social attributes and / or vital signs from the text data.

[0073] Optionally, the social attributes include information about the user's social identity and / or activities that affect the user's health; the vital signs attributes include information that characterizes the user's physical condition.

[0074] Optionally, the processor, in implementing the step of determining a user group composed of training users similar to the user's social attributes and / or physical attributes, includes: assigning corresponding weight values ​​to the social attributes and / or physical attributes according to preset rules; and determining training users similar to the user and obtaining the user group composed of the training users by calculating the social attribute values ​​and / or physical attribute values ​​and corresponding weight values ​​of each training user in the training user set.

[0075] Optionally, the processor, in implementing the step of training the diagnostic model component using the group data of the user group to obtain the trained diagnostic model component, includes: determining attributes that affect the diagnostic information from the social attributes and / or the physical signs attributes as feature attributes; using the feature attribute values ​​of the user group relative to the feature attributes and the corresponding disease information to train the diagnostic model component and obtain the trained diagnostic model component.

[0076] Optionally, the processor, in implementing the step of training the diagnostic model component using the feature attribute values ​​of the user group relative to the feature attribute and the corresponding disease information to obtain the trained diagnostic model component, includes: determining the feature attribute value of each user group in the user group relative to the feature attribute according to the value rules of the feature attribute; constructing the diagnostic model component, wherein the diagnostic model component includes a decision tree model component; and training the decision tree model component using the feature attribute values ​​and the corresponding disease information until the root feature attribute and leaf feature attribute serving as the root node and leaf node in the decision tree model are determined. The processor, in implementing the step of training the decision tree model component using the feature attribute values ​​and the corresponding disease information until the root feature attribute and leaf feature attribute serving as the root node and leaf node in the decision tree model are determined.

[0077] Optionally, the processor, in implementing the step of training the decision tree model component using the feature attribute values ​​and corresponding disease information until determining the root feature attribute and leaf feature attribute serving as the root node and leaf node in the decision tree model, includes: calculating the information gain of the user group under each feature attribute using the feature attribute value corresponding to each feature attribute and disease information; determining the feature attribute with the largest information gain as the root feature attribute in the decision tree model; classifying the user group into at least one user subset using the value range of the root feature attribute; for each user subset, determining the intermediate feature attribute under the root feature attribute by calculating the information gain of the user subset under other feature attributes besides the root feature attribute; treating each layer of intermediate feature attributes as the root feature attribute, determining the direct lower layer intermediate feature attribute of each layer of intermediate feature attributes in the above manner, until the user subset corresponding to the bottom leaf feature attribute includes only a single feature attribute.

[0078] Optionally, training the diagnostic model component using the user group's group data to obtain the trained diagnostic model component includes: classifying the user group into at least one subgroup according to a preset group classification method; and training the diagnostic model component using the subgroup data of the at least one subgroup to obtain the trained at least one diagnostic model component.

[0079] The processor according to an exemplary embodiment of this application can also perform medical diagnosis, including: inputting the social attributes and / or vital sign attributes into a trained medical diagnosis model to obtain the user's diagnosis information.

[0080] Optionally, the processor's step of inputting the social attributes and / or vital signs attributes into the trained medical diagnostic model to obtain the user's diagnostic information includes: determining attributes that affect the diagnostic information from the social attributes and / or vital signs attributes as feature attributes; inputting the feature attributes into the trained medical diagnostic model to obtain the user's diagnostic information.

[0081] The processor may also perform the following steps: recommending health plans associated with the diagnostic information to the user.

[0082] The processor may also perform the following steps: determining the group disease information of the user group, wherein the group disease information includes the current disease information and / or long-term susceptibility disease information of the user group; and recommending relevant health plans to the users based on the group disease information.

[0083] Furthermore, according to an exemplary embodiment of this application, the processor may perform the following steps: receiving a medical service request input by a user, wherein the medical service request includes the user's medical diagnosis form; identifying the user's attribute information from the medical diagnosis form; and determining a user group composed of training users whose attribute information is similar to that of the user.

[0084] Optionally, the processor may further perform the following step: determining the diagnostic information of the user based on the group disease information of the user group.

[0085] Optionally, the processor, in implementing the step of determining the user's diagnostic information based on the disease information of the user group, includes: training the diagnostic model component by means of the correspondence between the attribute information of the user group and the disease information of the group; and inputting the user's attribute information into the trained diagnostic model component to obtain the user's diagnostic information.

[0086] Furthermore, according to an exemplary embodiment of this application, the processor may also perform the following steps: obtaining the user's academic ability attributes and / or educational background attributes; determining a user group composed of training users similar to the user's academic ability attributes and / or educational background attributes; training a recommendation model component using the group data of the user group to obtain a trained training recommendation model component, wherein the training recommendation model component is used to recommend training courses to the user.

[0087] In addition, the academic ability attribute includes information about the user's learning ability; and the educational background attribute includes information about the user's learning experience.

[0088] Furthermore, the processor according to the exemplary embodiment of this application can perform training recommendations using the processor described above, including: inputting the academic ability attribute and / or educational background attribute into a trained training recommendation model component to obtain the user's training recommendation information.

[0089] In summary, the data processing apparatus according to the exemplary embodiments of this application can determine the user group to which the user belongs using the user's social attributes and / or physical characteristics, and use the user group to determine the user's diagnostic information, making the diagnostic information more evidence-based and accurate. Based on this, these attributes of the user can be obtained from the user's uploaded medical information, making these attributes more representative of the user. Furthermore, by using social attributes and / or physical characteristics to determine the user group to which the user belongs, it is possible to find user groups similar to the user's situation. Furthermore, by assigning different weight values ​​to different attributes, it is possible to find user groups that better match the user's situation. Furthermore, by using the determined user group to train the diagnostic model component, the trained diagnostic model component can more accurately obtain the user's diagnostic information. Furthermore, based on the user's diagnostic information, health plans can be recommended to the user, improving the user experience. Furthermore, based on the user's stated user group, warnings can be issued regarding areas requiring attention, making the warnings more relevant to the user's situation and more persuasive. Furthermore, different user groups can be identified based on various user attributes, and diagnostic model components trained on different user groups can be used to obtain various diagnostic information, making the diagnostic information more accurate and with a wider coverage.

[0090] It should be noted that the execution subject of each step of the method provided in Embodiment 1 can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 21 and 22 can be device 1, and the execution subject of step 23 can be device 2; or the execution subject of step 21 can be device 1, and the execution subject of steps 22 and 23 can be device 2; and so on.

[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0097] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0099] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data processing method, characterized in that, include: Obtain the user's social attributes and / or vital signs; Determine a user group consisting of training users similar to the social attributes and / or physical attributes of the user, wherein the user group includes multiple groups; The corresponding diagnostic model component is trained using the group data of the user group to obtain the trained diagnostic model component, wherein the diagnostic model component is used to diagnose the user's health status. Determining a user group consisting of training users similar to the user's social attributes and / or physical attributes includes: assigning corresponding weight values ​​to a preset number of attributes in the social attributes and / or physical attributes according to preset rules; calculating the social attribute value and / or physical attribute value and the corresponding weight value for each training user in the training user set through the weight value's value rules, the value range of the preset number of attributes, and the value range of the value range, thereby determining training users similar to the user and obtaining the user group consisting of the training users; The process of training a diagnostic model component using the user group's group data to obtain a trained diagnostic model component includes: determining attributes that influence diagnostic information from the social attributes and / or the physical characteristics attributes as feature attributes; determining the feature attribute values ​​of each user group relative to the feature attributes and the corresponding disease information of the user group using the value rules of the feature attributes, and training the diagnostic model component to obtain a trained diagnostic model component; and training the diagnostic model component using the feature attribute values ​​and the corresponding disease information to obtain a trained diagnostic model component, including: constructing the diagnostic model component, wherein the diagnostic model component includes a decision tree model component; and training the decision tree model component using the feature attribute values ​​and the corresponding disease information until the root feature attribute and leaf feature attribute, which serve as the root node and leaf node in the decision tree model, are determined.

2. The method as described in claim 1, characterized in that, Obtaining a user's social and / or vital signs attributes includes: Receive medical information forms uploaded by users; Identify the text data on the medical information form; The social attributes and / or physical attributes are obtained from the text data.

3. The method as described in claim 1, characterized in that, The social attributes include information about the user's social identity and / or activities that affect the user's health; and the physical attributes include information that characterizes the user's physical condition.

4. The method as described in claim 1, characterized in that, The decision tree model components are trained using the feature attribute values ​​and corresponding disease information until the root feature attributes and leaf feature attributes serving as the root and leaf nodes in the decision tree model are determined, including: Using the feature attribute values ​​and disease information corresponding to each feature attribute, the information gain of the user group under each feature attribute is calculated; The feature attribute with the largest information gain is determined as the root feature attribute in the decision tree model; Using the value range of the root feature attribute, the user group is classified into at least one user subset; For each user subset, the intermediate feature attribute under the root feature attribute is determined by calculating the information gain of the user subset under the feature attributes other than the root feature attribute. Each intermediate feature attribute is treated as the root feature attribute. The direct lower intermediate feature attributes of each intermediate feature attribute are determined in the manner described above, until the user subset corresponding to the leaf feature attribute at the bottom layer contains only a single feature attribute.

5. The method as described in claim 1, characterized in that, The diagnostic model component obtained by training using the group data of the user group includes: According to a preset group classification method, the user group is classified into at least one subgroup; The diagnostic model component is trained using subgroup data from the at least one subgroup to obtain at least one trained diagnostic model component.

6. A method for performing medical diagnosis using the method of claim 1, characterized in that, include: Display instruction information to the user so that the user can input the social attributes and / or vital signs into the trained medical diagnostic model according to the instruction information, and obtain the user's diagnostic information; Display the user's diagnostic information.

7. The method as described in claim 6, characterized in that, The process of inputting the social attributes and / or vital signs into the trained medical diagnostic model to obtain the user's diagnostic information includes: The attributes that influence the diagnostic information are determined from the social attributes and / or the physical characteristics attributes as feature attributes; The feature attributes are input into the trained medical diagnostic model to obtain the user's diagnostic information.

8. The method as described in claim 6, characterized in that, Also includes: Recommend health plans associated with the diagnostic information to the user.

9. The method as described in claim 6, characterized in that, Also includes: Determine the group disease information of the user group, wherein the group disease information includes the current disease information and / or the long-term susceptibility disease information of the user group; Based on the group's disease information, relevant health plans are recommended to the user.

10. A data processing method, characterized in that, include: Receive a medical service request input by a user, wherein the medical service request includes the user's medical diagnosis report; Identify the user's attribute information from the medical diagnosis report; Determining a user group consisting of training users whose attribute information is similar to that of the user, wherein the total number of users includes multiple users, wherein determining the user group consisting of training users whose attribute information is similar to that of the user includes: assigning corresponding weight values ​​to a preset number of attributes in the attribute information according to a preset rule; calculating the attribute information value and corresponding weight value of each training user in the training user set through the value rules of the weight values, the value range of the preset number of attributes, and the value range of the value range, thereby determining the training users similar to the user and obtaining the user group consisting of the training users; The method further includes: training a corresponding diagnostic model component using the group data of the user group to obtain a trained diagnostic model component, wherein training the diagnostic model component using the group data of the user group to obtain a trained diagnostic model component includes: determining attributes that affect diagnostic information from the attribute information as feature attributes; determining the feature attribute value of each user group relative to the feature attribute and the disease information corresponding to the user group using the value rules of the feature attribute, and training the diagnostic model component to obtain a trained diagnostic model component; training the diagnostic model component using the feature attribute value and the corresponding disease information to obtain a trained diagnostic model component includes: constructing the diagnostic model component, wherein the diagnostic model component includes a decision tree model component; training the decision tree model component using the feature attribute value and the corresponding disease information until the root feature attribute and leaf feature attribute, which serve as the root node and leaf node in the decision tree model, are determined.

11. The method as described in claim 10, characterized in that, Also includes: Based on the group disease information of the user group, the diagnostic information of the user is determined.

12. The method as described in claim 11, characterized in that, Determining the user's diagnostic information based on the disease information of the user group includes: The diagnostic model components are trained by establishing a correspondence between the attribute information of the user group and the group's disease information. The user's attribute information is input into the trained diagnostic model component to obtain the user's diagnostic information.

13. A data processing method, characterized in that, include: Obtain the user's academic ability and / or educational background attributes; Identify a user group consisting of training users whose academic ability and / or educational background attributes are similar to those of the user, wherein the user group includes multiple groups; The training recommendation model component is trained using the group data of the user group to obtain the trained training recommendation model component, wherein the training recommendation model component is used to recommend training courses to users; Determining a user group consisting of training users similar to the user's academic ability and / or educational background attributes includes: assigning corresponding weight values ​​to a preset number of attributes in the academic ability and / or educational background attributes according to preset rules; calculating the academic ability and / or educational background attribute values ​​and corresponding weight values ​​for each training user in the training user set through the weight value rules, the value range of the preset number of attributes, and the value range of the value range, thereby determining training users similar to the user and obtaining the user group consisting of the training users; The process of training a training recommendation model component using the user group's group data to obtain a trained training recommendation model component includes: determining attributes that influence training recommendations from the academic ability and / or educational background attributes as feature attributes; determining the feature attribute values ​​of each user group relative to the feature attributes and the corresponding training recommendation information of the user group using the value rules of the feature attributes, and training the training recommendation model component to obtain a trained training recommendation model component; and further training the training recommendation model component using the feature attribute values ​​and the corresponding training recommendation information to obtain a trained training recommendation model component, including: constructing the training recommendation model component, wherein the training recommendation model component includes a decision tree model component; and training the decision tree model component using the feature attribute values ​​and the corresponding training recommendation information until the root feature attribute and leaf feature attribute, which serve as the root node and leaf node in the decision tree model, are determined.

14. The method as described in claim 13, characterized in that, The academic ability attribute includes information about the user's learning ability; and the educational background attribute includes information about the user's learning experience.

15. A method for performing training recommendations using the method of claim 13, characterized in that, include: The academic ability attribute and / or educational background attribute are input into the trained training recommendation model component to obtain the user's training recommendation information.

16. A data processing apparatus, comprising: One or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods according to claims 1-15.

17. A computer-readable storage medium storing one or more programs, said one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods according to claims 1-15.

Images