User portrait construction method, system and related device

By extracting and integrating the user's basic portrait data and medical evaluation data from multimodal data, and building user portraits, the inaccuracy of portraits caused by uneven quality of users' medical data is solved, and the accuracy and comprehensiveness of user portraits are improved. .

CN118942604AInactive Publication Date: 2024-11-12ANHUI IFLYHEALTH CO LTD

Patent Information

Application Number
CN202410849753.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The uneven quality of user medical data has led to inaccurate construction of user portraits, making it difficult to provide comprehensive access and management of health information for medical service providers and users.

Method used

By obtaining medical portrait systems of multiple basic categories, matching basic portrait data is extracted from multimodal data related to users, and based on user basic portrait data and medical evaluation data, users' user portraits under the medical portrait system are built based on user basic portrait data and medical evaluation data. , improve the comprehensiveness and accuracy of the portrait.

Benefits of technology

By integrating the user's basic portrait data and medical evaluation data, the accuracy of user portraits is significantly improved, ensuring the matching degree of user portraits with users and the comprehensiveness of health information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942604A_ABST
    Figure CN118942604A_ABST
Patent Text Reader

Abstract

The invention discloses a user portrait construction method and system and a related device, and the method comprises the steps: obtaining a medical portrait system comprising a plurality of basic categories, and extracting basic portrait data matched with each basic category from multi-modal data related to a user; and based on each type of basic portrait data of the user in the medical portrait system, determining medical evaluation data of the user, and constructing a user portrait of the user in the medical portrait system by using all the basic portrait data and the medical evaluation data of the user. According to the scheme, the accuracy of user portrait construction can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a user portrait construction method, system and related devices. Background Art

[0002] With the rapid development of artificial intelligence technology in the medical field, user portraits in medical care play a vital role in personalized medical interactions. However, due to the uneven quality of users' medical data, the constructed user portraits are inaccurate, which is not convenient for providing comprehensive health information access and management for medical service providers and users. In view of this, how to improve the accuracy of user portrait construction has become an urgent problem to be solved. Summary of the invention

[0003] The main technical problem solved by the present application is to provide a user portrait construction method, system and related devices, which can improve the accuracy of user portrait construction.

[0004] In order to solve the above technical problems, the first aspect of the present application provides a user portrait construction method, which includes: obtaining a medical portrait system including multiple basic categories, extracting basic portrait data matching each of the basic categories from multimodal data related to the user; based on each of the basic portrait data of the user under the medical portrait system, determining the medical assessment data of the user, and using all of the basic portrait data and the medical assessment data of the user to construct a user portrait of the user under the medical portrait system.

[0005] In order to solve the above-mentioned technical problems, the second aspect of the present application provides a user portrait construction system, which includes: an acquisition module, used to acquire a medical portrait system including multiple basic categories, and extract basic portrait data matching each of the basic categories from the multimodal data related to the user; a construction module, used to determine the medical assessment data of the user based on each of the basic portrait data of the user under the medical portrait system, and use all of the basic portrait data and the medical assessment data of the user to construct a user portrait of the user under the medical portrait system.

[0006] To solve the above technical problems, the third aspect of the present application provides an electronic device, comprising: a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the method described in the first aspect above.

[0007] In order to solve the above technical problems, the fourth aspect of the present application provides a computer-readable storage medium on which program instructions are stored. When the program instructions are executed by a processor, the method described in the first aspect is implemented.

[0008] The above scheme obtains a medical portrait system including multiple basic categories, extracts basic portrait data matching each basic category from multimodal data related to the user, and improves the comprehensiveness of the basic portrait data of the user by extracting basic portrait data matching multiple basic categories. Based on each basic portrait data of the user under the medical portrait system, the corresponding medical assessment data of the user is determined, and the user portrait of the user under the medical portrait system is constructed by using all the basic portrait data and medical assessment data of the user. By integrating and processing all the basic portrait data and medical assessment data of the user together, the accuracy of user portrait construction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0010] Figure 1 It is a flowchart of an implementation method of the user portrait construction method of the present application;

[0011] Figure 2 This is a schematic diagram of the structure of an implementation method of the medical imaging system of the present application;

[0012] Figure 3 yes Figure 1 A flowchart of an implementation method corresponding to part of step S101 in FIG.

[0013] Figure 4 yes Figure 1 A schematic diagram of a flow chart of an implementation method corresponding to step S102;

[0014] Figure 5 This is a structural diagram of an implementation method of a user portrait construction system of the present application;

[0015] Figure 6 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0016] Figure 7 It is a structural schematic diagram of an implementation method of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0019] The user portrait construction method proposed in this application is implemented by a smart terminal, which can be a smart device that at least integrates the corresponding portrait construction function and interactive function, or can also be an application on a smart device. The smart device can be a mobile phone, a tablet computer, or a personal computer.

[0020] See also Figure 1 and Figure 2 , Figure 1 This is a flowchart of an implementation method of the user portrait construction method of the present application. Figure 2 This is a schematic diagram of the structure of an implementation method of the medical image system of the present application, the method comprising:

[0021] S101: Acquire a medical portrait system including multiple basic categories, and extract basic portrait data matching each basic category from multimodal data related to the user.

[0022] Specifically, a medical portrait system including multiple basic categories is obtained, wherein the basic categories include at least the user's basic information, health history, examination report, symptoms and signs, medication data, and living habits. The basic information includes the user's height, age, weight, etc., the health history includes the user's historical diseases, the examination report includes the user's report sheet and medical record, the symptoms and signs include the user's fever, pain, abnormal heart rate and blood pressure, etc., the medication data includes the user's medication history, and the living habits include the user's exercise and diet, etc. Basic portrait data matching each basic category is extracted from the multimodal data related to the user, and the basic portrait data matching multiple basic categories is extracted to improve the comprehensiveness of the basic portrait data of the user.

[0023] In one application mode, a dialogue is conducted with the user, and multimodal data related to the user is collected during the dialogue.

[0024] In one application scenario, by conducting multiple rounds of conversations with the user, multimodal data related to the user is obtained based on the text entered, pictures uploaded, and voice sent by the user during the conversation.

[0025] In another application mode, multimodal data related to the user is obtained from the inspection report actively uploaded by the user.

[0026] In one application scenario, the report sheets and medical records actively uploaded by the user are obtained, and texts and images are extracted from the report sheets and medical records to obtain multimodal data related to the user.

[0027] In yet another application, multimodal data related to the user is obtained from data synchronously uploaded by a connected medical device.

[0028] In one application scenario, after the user measures the medical data through the connected medical device, the medical device will automatically synchronize and upload the medical data to the smart device, extract text, images and / or videos from the medical data, and obtain multimodal data related to the user.

[0029] In a specific application scenario, the medical portrait system also includes a data update module, through which the basic portrait data can be updated.

[0030] It should be noted that the smart device will inform the user in advance of the purpose of the interaction data, and needs to obtain multimodal data related to the user on the premise that the user chooses to agree.

[0031] It can be understood that the modalities of multimodal data include at least text, voice, image and video.

[0032] S102: Based on each basic portrait data of the user under the medical portrait system, determine the user's medical assessment data, and use all the user's basic portrait data and medical assessment data to build a user portrait of the user under the medical portrait system.

[0033] Specifically, based on each basic portrait data of the user under the medical portrait system, the corresponding medical assessment data of the user is determined, and all the basic portrait data and medical assessment data of the user are used to construct a user portrait of the user under the medical portrait system. By integrating and processing all the basic portrait data and medical assessment data of the user, the accuracy of user portrait construction is improved.

[0034] In one application, the basic portrait data of the user in the medical portrait system corresponds to time information, and the corresponding medical assessment data of the user is determined based on the time information of each basic portrait data.

[0035] In one application scenario, the medical assessment data of the corresponding user is determined based on the time sequence of each basic portrait data.

[0036] In another application mode, the basic portrait data of the user in the medical portrait system corresponds to type information, and the corresponding medical assessment data of the user is determined based on the type information of each basic portrait data.

[0037] In one application scenario, based on the data type of each basic portrait data, the medical assessment data of the corresponding user is determined.

[0038] It should be noted that when different types of basic portrait data are included in the same day within the same time period, the medical assessment data of the corresponding user will be determined first based on the time sequence.

[0039] For example, a user interacts with a smart device for four consecutive days. On the first day, the user uploads a report image and has multiple rounds of conversations with the smart device. On the second and third days, the user only has multiple rounds of conversations with the smart device. On the fourth day, the user uploads a new report image and has multiple rounds of conversations with the smart device. At this time, the interaction content between the user and the smart device will be saved in chronological order.

[0040] The above scheme obtains a medical portrait system including multiple basic categories, extracts basic portrait data matching each basic category from multimodal data related to the user, and improves the comprehensiveness of the basic portrait data of the user by extracting basic portrait data matching multiple basic categories. Based on each basic portrait data of the user under the medical portrait system, the corresponding medical assessment data of the user is determined, and the user portrait of the user under the medical portrait system is constructed by using all the basic portrait data and medical assessment data of the user. By integrating and processing all the basic portrait data and medical assessment data of the user together, the accuracy of user portrait construction is improved.

[0041] In one embodiment, the medical portrait system is pre-constructed, and each user corresponds to the same medical portrait system, and the multiple basic categories in the medical portrait system are at least related to the user's personal information and user medical information.

[0042] Specifically, each user corresponds to the same medical portrait system, which can ensure the consistency of the overall process of all users in building user portraits. Different users can obtain each user's matching basic portrait data related to user personal information and user medical information under different basic categories, thereby ensuring the matching degree between the user portrait and the user.

[0043] In some implementation scenarios, user personal information may include the user's basic information and living habits as basic categories, and user medical information may include the user's health history, examination report, symptoms and signs, and medication data as basic categories. Among them, the basic category is directly related to the implementation scenario. In different implementation scenarios, basic categories that match the scenario can be defined, and this application does not make specific restrictions on this.

[0044] In one embodiment, see Figure 3 , Figure 3 yes Figure 1 A flowchart of an implementation method corresponding to part of step S101 in the embodiment includes:

[0045] S301: Acquire multimodal data obtained during the interaction with the user; wherein the multimodal data is acquired from at least one of user conversation data, user uploaded data, and device synchronization data during the interaction.

[0046] Specifically, multimodal data obtained from at least one of user conversation data, user uploaded data, and device synchronization data obtained during the interaction with the user is obtained.

[0047] It can be understood that user conversation data is data generated by the conversation between the smart device and the user, user uploaded data is data uploaded by the user to the smart device, and device synchronization data is data automatically synchronized and uploaded by the medical device connected to the smart device.

[0048] S302: Extracting a data subset matching each basic category from the multimodal data, and obtaining basic portrait data matching each basic category based on the data subset corresponding to each basic category.

[0049] Specifically, the multimodal data is extracted and sorted according to different basic categories to obtain a data subset matching each basic category, and based on the data subset corresponding to each basic category, basic portrait data matching each basic category is obtained.

[0050] In some implementation scenarios, a traditional neural network model is used to extract a data subset matching each basic category from the multimodal data, and an attention mechanism is used to perform weight processing on the data subset corresponding to each basic category to obtain basic portrait data matching each basic category.

[0051] In some implementation scenarios, an intelligent analysis model is used to extract data subsets matching each basic category from multimodal data, and at least part of the data subsets of the basic categories are structured in a structured manner matching the basic categories to obtain basic portrait data matching each basic category.

[0052] Specifically, by utilizing the multimodal data analysis capability of the intelligent analysis model, data subsets matching each basic category are extracted from the multimodal data, and at least part of the data subsets are structured in a structured manner matching the basic categories, thereby obtaining basic portrait data matching each basic category.

[0053] For example, the intelligent analysis model can extract the user's medication history from the conversation with the user and associate the medication history with the matching medication data. It can also recognize the report photo uploaded by the user as text and associate the recognized report text with the matching examination report.

[0054] Optionally, the intelligent analysis model is a generative large language model, which may include but is not limited to deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTM), and generative pre-trained Transformer models, etc. No specific restrictions are made on the specific structure and deployment of the large language model.

[0055] In one embodiment, see Figure 4 , Figure 4 yes Figure 1 Schematic diagram of a flow chart of an implementation method corresponding to step S102 in FIG. Step S102 specifically includes:

[0056] S401: Based on the basic portrait data of the user distributed in time series under the medical portrait system, determine the basic change trend of each basic portrait data corresponding to the user.

[0057] Specifically, each basic portrait data has corresponding time information. Based on the basic portrait data of the user distributed in chronological order under the medical portrait system, the basic change trend of each basic portrait data corresponding to the user is determined.

[0058] S402: Determine the user's medical assessment data based on all basic change trends corresponding to the user.

[0059] Specifically, based on all the basic change trends corresponding to the user, the user's medical assessment data is determined, and through a comprehensive interpretation of all the basic change trends, the obtained medical assessment data is made more comprehensive and accurate, thereby improving the accuracy of the subsequent user portrait.

[0060] For example, the basic change trends of each basic portrait data corresponding to the user may include: changes in heart rate uploaded synchronously by medical equipment, changes in important indicator items in the report form, and changes in the patient's medication status, etc. By comprehensively interpreting all basic change trends, the user's medical assessment data is determined to prompt changes in the user's health, such as possible health risk factors.

[0061] S403: Integrate all basic portrait data and medical assessment data of the user using an intelligent analysis model to obtain a user portrait of the user under the medical portrait system.

[0062] Specifically, an intelligent analysis model is used to organize and integrate all the user's basic portrait data and medical data, so as to obtain a comprehensive and accurate user portrait under the medical portrait system.

[0063] In one embodiment, before step S102, it also includes: determining an associated role related to the user based on all basic portrait data corresponding to the user; wherein the associated role corresponds to at least one of the user's family relationship and the user's work relationship; classifying and archiving all basic portrait data corresponding to the user according to the user himself and the associated role; wherein, when the associated role related to the user is obtained, the user himself and the associated role respectively correspond to the user portrait under the medical portrait system.

[0064] Specifically, based on all basic portrait data corresponding to the user, the associated role corresponding to at least one of the user's family relationship and work relationship is determined, and all basic portrait data corresponding to the user are classified and archived according to the relationship between the user and the associated role. Then, all basic portrait data and medical assessment data including the user and the associated role are integrated and processed separately, so as to obtain user portraits of the user and the associated role under the medical portrait system.

[0065] In some implementation scenarios, all basic portrait data corresponding to the user and the associated roles are first classified and archived according to the relationship between the user and the associated roles, and then all basic portrait data of the user and the associated roles are integrated and processed in chronological order or type. For example, all interaction content (text, images and videos) between the user and the intelligent analysis model on the same day are integrated together. At the same time, all interaction content can also be integrated according to type, and the same data can be saved in different archives at the same time, so that the intelligent analysis model can efficiently generate medical assessment data corresponding to each role, and establish user portraits for each role respectively, so that users can obtain user portraits of associated roles in a timely manner, thereby improving user convenience.

[0066] In a specific implementation scenario, the user himself and the user's father each have a smart device, and corresponding application software is downloaded on the smart devices. The application software also has user portraits of the user himself and the user's father. After the user himself and the user's father are associated, when the user's father's user portrait needs to be updated and the user's father does not know how to operate it, the user himself can select the father's user portrait in his own application software and update the data, and then synchronously upload the updated father's user portrait. At this time, the user portrait on the user's father's own application software will also be updated to the latest user portrait accordingly, thereby improving the portability of user use.

[0067] It can be understood that when there is only one user, the relationship between the user and the associated role is an empty set.

[0068] In one application method, step S402 specifically includes: determining the user's own evaluation data based on all basic change trends corresponding to the user himself, and determining the associated evaluation data corresponding to the associated role based on all basic change trends corresponding to the associated role; determining the user's own medical evaluation data and the medical evaluation data of the associated role based on the user's own evaluation data and the associated evaluation data.

[0069] Specifically, based on all basic change trends corresponding to the user, the user's own evaluation data is determined, based on all basic change trends corresponding to the user's associated roles, the associated evaluation data corresponding to the associated roles are determined, and based on the user's own evaluation data and the associated evaluation data of the associated roles, the user's own medical evaluation data and the medical evaluation data of the associated roles are determined. By jointly determining the medical evaluation data of the user and the associated roles through the user's own evaluation data and the associated evaluation data of the associated roles, the determined medical evaluation data can be further made comprehensive and accurate, thereby further improving the accuracy of the subsequent user portrait.

[0070] In one application scenario, by linking the user's own assessment data and the associated assessment data of multiple different family members in the family, the user's own potential risk of genetic diseases can be prompted.

[0071] In a specific application scenario, if the user's father suffers from hereditary heart disease, the user's father's associated evaluation data and the user's own evaluation data can be linked to indicate that the user may also suffer from hereditary heart disease, thereby enabling the user to prevent and treat the disease in advance.

[0072] In another specific application scenario, when the user's father has symptoms of chest tightness and weakness, the user can ask the intelligent analysis model, for example, send a message to the intelligent analysis model, "My father came back from a walk in the evening and said he felt a little chest tightness and weakness." The intelligent analysis model will first identify the keywords "father" and "chest tightness," obtain the associated role of the user's father, and analyze the associated medical data of the user's father. After the analysis is completed, further questions will be asked to the user, such as "Hello, did your father's chest tightness appear suddenly or persist?" The user answers "suddenly" according to the actual situation. The intelligent analysis model further asks questions based on the user's answer, such as "Does your father have other symptoms when he has chest tightness, such as sweating, nausea, vomiting, etc." The user answers "No, I just feel chest tightness and weakness." The intelligent analysis model further asks questions based on the user's answer, such as "Does your father have any previous diseases, such as high blood pressure, diabetes, heart disease, etc?" The user answers "My father has high Blood pressure and history of coronary heart disease", at this time, the intelligent analysis model will provide users with condition analysis, external suggestions and precautions, among which, the condition analysis includes "according to your description, your father has a history of hypertension and coronary heart disease, and now has symptoms of chest tightness and weakness, which may be aggravated symptoms of coronary heart disease, or it may be caused by other reasons", and external suggestions include "it is recommended that your father go to the hospital immediately, preferably to the cardiology department. The doctor may do an electrocardiogram, cardiac ultrasound and other examinations for him to determine the condition", and precautions include "1. On the way to the hospital, try to keep your father calm and avoid emotional excitement; 2. If your father has symptoms such as shortness of breath, sweating, nausea, vomiting, etc., you should call the emergency number immediately; 3. Your father needs to insist on taking drugs for hypertension and coronary heart disease, and adjust the dosage and type of drugs according to the doctor's advice", and the intelligent analysis model will also add the user's father's hypertension and coronary atherosclerotic heart disease identified to the corresponding basic category of health history in the user's father's medical portrait system.

[0073] In another application scenario, by linking the user's own assessment data and the associated assessment data of the spouse, the user's own disease risk can be prompted.

[0074] In a specific application scenario, if the user and his / her spouse have been eating high-fat and high-salt foods for a long time, and the spouse has symptoms of diarrhea and vomiting, but the user himself / herself has not yet shown such symptoms, the user's own disease risk can be prompted by linking the spouse's associated assessment data and the user's own assessment data.

[0075] In another application scenario, by linking the user's own assessment data and the associated assessment data of multiple colleagues in the same work unit, the user's potential occupational disease risks can be prompted.

[0076] In a specific application scenario, if the user recently starts working in the steel industry, and several colleagues who have been working in this industry for a long time develop symptoms such as dizziness and tinnitus, the user can be reminded that if he continues to work in the steel industry, he will also be exposed to noise for a long time, resulting in noise occupational diseases and serious impact on his health.

[0077] In one application method, after step S102, it also includes: displaying the user portrait of the user in the medical portrait system to the user; in response to obtaining the user's editing instructions, using the intelligent analysis model to adjust the displayed user portrait according to the editing instructions to obtain an adjusted user portrait.

[0078] Specifically, after obtaining the user portrait, the user portrait is displayed to the user, and the user can edit the user portrait. When the user's editing instructions are received, the intelligent analysis model is used to adjust the displayed user portrait according to the editing instructions to obtain the adjusted user portrait, thereby further improving the accuracy of user portrait construction.

[0079] In one application scenario, when the report image uploaded by the user is not clear, resulting in recognition errors by the intelligent analysis model and making the user portrait finally constructed inaccurate, the user can re-edit the user portrait. The intelligent analysis model receives editing instructions for the user portrait through a dialogue interface with the user, and sends a confirmation instruction after the user has re-edited the user portrait, so as to improve the accuracy of the final adjusted user portrait.

[0080] See also Figure 5 , Figure 5 It is a structural diagram of an implementation method of a user portrait construction system of the present application, and the user portrait construction system 50 includes: an acquisition module 501 and a construction module 502, the acquisition module 501 is used to acquire a medical portrait system including multiple basic categories, and extract basic portrait data matching each of the basic categories from the multimodal data related to the user; the construction module 502 is used to determine the medical assessment data of the user based on each of the basic portrait data of the user under the medical portrait system, and use all the basic portrait data and the medical assessment data of the user to construct a user portrait of the user under the medical portrait system.

[0081] In the above scheme, the acquisition module 501 acquires a medical portrait system including multiple basic categories, extracts basic portrait data matching each basic category from the multimodal data related to the user, and improves the comprehensiveness of the basic portrait data of the user by extracting the basic portrait data matching multiple basic categories. The construction module 502 determines the corresponding medical assessment data of the user based on each basic portrait data of the user under the medical portrait system, and uses all the basic portrait data and medical assessment data of the user to construct a user portrait of the user under the medical portrait system. By integrating all the basic portrait data and medical assessment data of the user together, the accuracy of user portrait construction is improved.

[0082] Optionally, the medical portrait system is pre-constructed, and each user corresponds to the same medical portrait system, and the multiple basic categories in the medical portrait system are at least related to the user's personal information and user medical information.

[0083] Optionally, the acquisition module 501 is also used to acquire multimodal data obtained during the interaction with the user; wherein the multimodal data is acquired from at least one of the user conversation data, user uploaded data and device synchronization data during the interaction process; a data subset matching each basic category is extracted from the multimodal data, and basic portrait data matching each basic category is obtained based on the data subset corresponding to each basic category.

[0084] Optionally, the acquisition module 501 is also used to extract data subsets matching each basic category from the multimodal data using an intelligent analysis model, and to perform structured processing on at least part of the data subsets of the basic categories in a structured manner matching the basic categories, to obtain basic portrait data matching each basic category.

[0085] Optionally, construction module 502 is also used to determine the basic change trend of each basic portrait data corresponding to the user based on the basic portrait data of the user distributed in time series under the medical portrait system; determine the medical assessment data of the user based on all basic change trends corresponding to the user; and use an intelligent analysis model to integrate all the basic portrait data and medical assessment data of the user to obtain a user portrait of the user under the medical portrait system.

[0086] Optionally, the acquisition module 501 is also used to determine the associated role related to the user based on all basic portrait data corresponding to the user; wherein the associated role corresponds to at least one of the user's family relationship and the user's work relationship; all basic portrait data corresponding to the user are classified and archived according to the user himself and the associated role; wherein, when the associated role related to the user is obtained, the user himself and the associated role respectively correspond to the user portrait under the medical portrait system.

[0087] Optionally, the acquisition module 501 is also used to determine the personal evaluation data corresponding to the user based on all basic change trends corresponding to the user himself, and determine the associated evaluation data corresponding to the associated role based on all basic change trends corresponding to the associated role; based on the personal evaluation data and the associated evaluation data, determine the medical evaluation data of the user himself and the medical evaluation data of the associated role.

[0088] Optionally, the construction module 502 is also used to display the user portrait of the user in the medical portrait system to the user; in response to obtaining the user's editing instructions, the displayed user portrait is adjusted according to the editing instructions using the intelligent analysis model to obtain an adjusted user portrait.

[0089] It can be understood that the user portrait construction system 50 can implement the user portrait construction method mentioned in any of the above-mentioned embodiments. For the description of the relevant content, please refer to the detailed description of the above-mentioned method embodiment, and this application will not go into details.

[0090] See also Figure 6 , Figure 6 It is a structural diagram of an embodiment of an electronic device of the present application. The electronic device 60 includes: a memory 602 and a processor 600 coupled to each other. The memory 602 stores program instructions, and the processor 600 is used to execute the program instructions to implement the user portrait construction method mentioned in any of the above embodiments. For the description of the relevant content, please refer to the detailed description of the above method embodiment, and the present application will not repeat it. Specifically, the electronic device 60 includes but is not limited to: a desktop computer, a laptop computer, a tablet computer, a server, etc., which are not limited here. In addition, the processor 600 can also be called a CPU (Center Processing Unit). The processor 600 may be an integrated circuit chip with signal processing capabilities. The processor 600 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 600 can be implemented by an integrated circuit chip.

[0091] See also Figure 7 , Figure 7It is a schematic diagram of the structure of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 70 stores program instructions 700 that can be executed by a processor. When the program instructions 700 are executed by the processor, the user portrait construction method mentioned in any of the above embodiments is implemented. For the description of the relevant content, please refer to the detailed description of the above method embodiment, and this application will not repeat it.

[0092] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0094] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0096] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for constructing a user portrait, characterized in that: include: Acquire a medical portrait system including a plurality of basic categories, and extract basic portrait data matching each of the basic categories from multimodal data related to the user; Based on each type of basic portrait data of the user under the medical portrait system, the medical assessment data of the user is determined, and a user portrait of the user under the medical portrait system is constructed by utilizing all of the basic portrait data and the medical assessment data of the user.

2. The method according to claim 1, characterized in that The medical portrait system is pre-constructed, and each user corresponds to the same medical portrait system. The multiple basic categories in the medical portrait system are at least related to the user's personal information and user medical information.

3. The method according to claim 1, characterized in that The extracting basic portrait data matching each basic category from the multimodal data related to the user includes: Acquire multimodal data obtained during the interaction with the user; wherein the multimodal data is obtained from at least one of user conversation data, user uploaded data, and device synchronization data during the interaction; A data subset matching each of the basic categories is extracted from the multimodal data, and basic portrait data matching each of the basic categories is obtained based on the data subset corresponding to each of the basic categories.

4. The method according to claim 3, characterized in that The extracting of a data subset matching each of the basic categories from the multimodal data, and obtaining basic portrait data matching each of the basic categories based on the data subset corresponding to each of the basic categories, includes: An intelligent analysis model is used to extract data subsets matching each of the basic categories from the multimodal data, and at least part of the data subsets of the basic categories are structured in a structured manner matching the basic categories to obtain basic portrait data matching each of the basic categories.

5. The method according to claim 1, characterized in that The determining the medical assessment data of the user based on each of the basic portrait data of the user under the medical portrait system, and constructing the user portrait of the user under the medical portrait system by using all of the basic portrait data and the medical assessment data of the user, comprises: Based on the basic portrait data of the user distributed in time series under the medical portrait system, determining a basic change trend of each type of the basic portrait data corresponding to the user; Determining medical assessment data of the user based on all the basic change trends corresponding to the user; An intelligent analysis model is used to integrate all of the basic portrait data and the medical assessment data of the user to obtain a user portrait of the user under the medical portrait system.

6. The method according to claim 5, characterized in that Before determining the medical assessment data of the user based on each of the basic portrait data of the user under the medical portrait system, and constructing the user portrait of the user under the medical portrait system by using all of the basic portrait data and the medical assessment data of the user, the method further includes: Based on all the basic portrait data corresponding to the user, determining an associated role related to the user; wherein the associated role corresponds to at least one of the family relationship of the user and the work relationship of the user; All the basic portrait data corresponding to the user are classified and archived according to the user himself and the associated role; wherein, when the associated role related to the user is obtained, the user himself and the associated role respectively correspond to the user portrait under the medical portrait system.

7. The method according to claim 6, characterized in that The determining of the medical assessment data of the user based on all the basic change trends corresponding to the user includes: Based on all the basic change trends corresponding to the user, determine the personal evaluation data corresponding to the user, and based on all the basic change trends corresponding to the associated role, determine the associated evaluation data corresponding to the associated role; Based on the personal evaluation data and the associated evaluation data, the medical evaluation data of the user himself and the medical evaluation data of the associated role are determined.

8. The method according to claim 1, characterized in that After determining the medical assessment data of the user based on each of the basic portrait data of the user under the medical portrait system, and constructing the user portrait of the user under the medical portrait system by using all the basic portrait data and the medical assessment data of the user, the method further includes: Displaying the user portrait of the user under the medical portrait system to the user; In response to obtaining the editing instruction from the user, the displayed user portrait is adjusted according to the editing instruction using the intelligent analysis model to obtain an adjusted user portrait.

9. A user portrait construction system, characterized in that: include: An acquisition module, the acquisition module is used to acquire a medical portrait system including multiple basic categories, and extract basic portrait data matching each of the basic categories from multimodal data related to the user; A construction module is used to determine the medical assessment data of the user based on each type of basic portrait data of the user under the medical portrait system, and to construct a user portrait of the user under the medical portrait system using all the basic portrait data and the medical assessment data of the user.

10. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Multi-dimensional personal health portrait system and method

    CN111710385A

  • Health index analysis method and device based on multi-dimensional data, equipment and medium

    CN114496264A

  • Health information reminding method and device, electronic equipment and storage medium

    CN114550927A

  • Health state evaluation method and device and computer equipment

    CN114883013A

  • User health portrait generation method and device based on wearable device

    CN116246793A

Cited By

  • Tumor patient portrait construction method and system based on multi-source heterogeneous data

    CN121281729A