Multi-dimensional evaluation method and system for thirst degree of user

Abstract

The invention provides a multi-dimensional evaluation method and system for the thirst degree of a user, and the method comprises the steps: obtaining the body fluid detection data of the user, the blood detection data of the user, and the appearance detection image of the user, and extracting each water shortage characterization feature of the user based on the appearance detection image of the user; identifying the actual water shortage degree of the user through a water shortage degree evaluation model on the basis of each water shortage characterization feature of the user, the thirst degree independently narrated by the user, the body fluid detection data of the user and the blood detection data of the user; and recognizing the thirst degree independently narrated by the user, and recognizing the actual thirst degree of the user in combination with the actual water shortage degree of the user. By adopting the scheme, the evaluation accuracy of the actual thirst degree of the user who is limited to eat water can be improved, and a decision basis is provided for accurately identifying the water shortage condition of the user, preventing dehydration complications and optimizing liquid management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data detection and medical assistance, and particularly relates to a multi-dimensional evaluation method and system for user thirst degree. BACKGROUND

[0002] Users with water intake restrictions, such as heart failure and gastrointestinal bleeding, often experience strong thirst due to the restriction of the intake amount. If the continuous thirst cannot be relieved in time, the user will suffer from strong discomfort, trigger anxiety, depression and other emotions, reduce the compliance of fluid restriction, and thus make the user intake excessive water -> increase blood volume -> increase the burden on the heart / kidney -> trigger complications (such as pulmonary edema and hypertensive crisis) -> further strengthen the treatment restriction demand, form a negative feedback cycle, and thus affect the prognosis. Therefore, it is necessary to accurately evaluate the thirst degree of the user with water intake restriction so as to timely perform individualized intervention.

[0003] The evaluation of the thirst degree is a process of judging the body fluid balance state by comprehensively considering symptoms, signs and objective examinations, and has the characteristics of stage, dynamics and individuality. However, at present, the evaluation of the thirst degree of the user mainly depends on the self-narration of the user, is subjective and has a single dimension, can only obtain the approximate range of the evaluation result of the thirst, and cannot distinguish between “true thirst” (physiological demand) and “false thirst” (dry mouth), so that the evaluation accuracy of the actual thirst degree of the user is low. SUMMARY

[0004] The main purpose of the present application is to provide a multi-dimensional evaluation method and system for user thirst degree, which aims to solve the problem in the prior art that the evaluation is subjective and can only analyze and evaluate the approximate range of the thirst because the method mainly relies on the self-narration of the user, cannot match the real degree of water loss reflected by the body, especially when the user has early dehydration but no thirst, or the user exaggerates the thirst degree due to emotional and psychological factors. The user with water intake restriction has strict requirements for the total intake amount. Therefore, the evaluation of the approximate range of the thirst degree cannot be applied to the user with water intake restriction, and it is necessary to objectively and accurately evaluate the thirst degree to provide a basis for guiding the intake amount.

[0005] To achieve the above-mentioned purpose, the present application provides a multi-dimensional evaluation method for user thirst degree, which comprises the following steps:

[0006] acquiring body fluid detection data of a user, blood detection data of the user and an appearance detection image of the user, and extracting each water loss feature of the user based on the appearance detection image of the user;

[0007] identify a thirst degree range of the user based on the user's each water deficiency feature, and identify an actual water deficiency degree of the user based on the user's body fluid detection data and the user's blood detection data through a water deficiency degree evaluation model;

[0008] identify an actual thirst degree of the user based on the user's thirst degree range and the actual water deficiency degree of the user.

[0009] Optionally, the extracting the user's each water deficiency feature based on the appearance detection image of the user comprises:

[0010] screening a range image of each water deficiency feature range in the appearance detection image of the user through a preset feature range screening model;

[0011] extracting image feature data of each water deficiency feature range through an image feature extraction network based on the range image of each water deficiency feature range, and identifying a user part type corresponding to each water deficiency feature range;

[0012] taking the image feature data corresponding to each user part type as the user's each water deficiency feature.

[0013] Optionally, the identifying the thirst degree range of the user based on the user's each water deficiency feature comprises:

[0014] for each user part type, identifying a sub-thirst degree range corresponding to the user part type through a thirst degree evaluation strategy corresponding to the user part type based on the image feature data of the user part type;

[0015] identifying the thirst degree range of the user through preset thirst degree feature weights of each user part type based on the sub-thirst degree range corresponding to each user part type.

[0016] Optionally, the identifying the actual water deficiency degree of the user based on the user's body fluid detection data and the user's blood detection data through a water deficiency degree evaluation model comprises:

[0017] identifying body fluid excretion data and body fluid content data of the user based on the user's body fluid detection data, and identifying excretion abnormal information of the user based on the user's body fluid excretion data;

[0018] identifying blood content data of the user based on the user's blood detection data, and identifying the actual water deficiency degree of the user through a water deficiency degree evaluation model based on the user's body fluid content data, the user's blood content data, and the user's excretion abnormal information.

[0019] Optionally, the actual water deficiency degree of the user is identified based on the water deficiency degree range of the user and the actual water deficiency degree of the user.

[0020] The frequency of urination of the user and the distribution information of the amount of urination of the user are identified based on the abnormal urination information of the user, and the water deficiency degree range of the user is identified based on the frequency of urination of the user and the distribution information of the amount of urination of the user through a water deficiency evaluation strategy.

[0021] The target substance proportion information of the body fluid of the user and the target substance proportion information of the blood of the user are calculated based on the body fluid content data of the user and the blood content data of the user.

[0022] The actual water deficiency degree of the user is adapted in the water deficiency degree range based on the target substance proportion information of the body fluid and the target substance proportion information of the blood through the water deficiency degree evaluation model.

[0023] Optionally, the actual thirst degree of the user is identified based on the water deficiency degree range of the user and the actual water deficiency degree of the user.

[0024] The thirst degree evaluation value of the user is identified based on the actual water deficiency degree of the user through a thirst degree conversion strategy.

[0025] The actual thirst degree of the user is identified based on the water deficiency degree range of the user and the thirst degree evaluation value of the user.

[0026] In addition, to achieve the above-mentioned purpose, the application further provides a multi-dimensional evaluation system for the thirst degree of a user, which comprises:

[0027] An acquisition module is configured to acquire body fluid detection data of a user, blood detection data of the user, and appearance detection images of the user, and extract various water deficiency characteristic features of the user based on the appearance detection images of the user.

[0028] A first identification module is configured to identify a thirst degree range of the user based on the various water deficiency characteristic features of the user, and identify an actual water deficiency degree of the user through a water deficiency degree evaluation model based on the body fluid detection data of the user and the blood detection data of the user.

[0029] A second identification module is configured to identify an actual thirst degree of the user based on the thirst degree range of the user and the actual water deficiency degree of the user.

[0030] Optionally, the acquisition module is specifically configured to:

[0031] The range image of each water shortage feature range is filtered in the appearance detection image of the user through a preset feature range screening model.

[0032] Based on the range image of each water shortage feature range, image feature data of each water shortage feature range is extracted through an image feature extraction network, and a user part type corresponding to each water shortage feature range is identified.

[0033] The image feature data corresponding to each user part type is taken as each water shortage feature of the user.

[0034] Optionally, the first identification module is specifically configured to:

[0035] For each user part type, a sub-thirst degree range corresponding to the user part type is identified based on the image feature data of the user part type through a thirst degree evaluation strategy corresponding to the user part type.

[0036] Based on the sub-thirst degree range corresponding to each user part type, a thirst degree range of the user is identified through a preset thirst feature weight value of each user part type.

[0037] Optionally, the first identification module is specifically configured to:

[0038] Based on the body fluid detection data of the user, body fluid excretion data and body fluid content data of the user are identified, and excretion abnormal information of the user is identified based on the body fluid excretion data of the user.

[0039] Based on the blood detection data of the user, blood content data of the user is identified, and an actual water shortage degree of the user is identified through a water shortage degree evaluation model based on the body fluid content data of the user, the blood content data of the user, and the excretion abnormal information of the user.

[0040] Optionally, the first identification module is specifically configured to:

[0041] Based on the excretion abnormal information of the user, excretion frequency and excretion amount distribution information of the user are identified, and a water shortage degree range of the user is identified through a water shortage evaluation strategy based on the excretion frequency and the excretion amount distribution information of the user.

[0042] Based on the body fluid content data of the user and the blood content data of the user, body fluid target substance proportion information and blood target substance proportion information of the user are calculated.

[0043] Based on the body fluid target substance proportion information and the blood target substance proportion information, an actual water deficiency degree of the user is identified in the water deficiency degree range by the water deficiency degree evaluation model.

[0044] Optionally, the second identification module is specifically used for:

[0045] Based on the actual water deficiency degree of the user, a thirst degree evaluation value of the user is identified by a thirst degree conversion strategy.

[0046] Based on the thirst degree range of the user and the thirst degree evaluation value of the user, an actual thirst degree of the user is identified.

[0047] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, steps of the method in any one of the first aspect are implemented.

[0048] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores a computer program. When the computer program is executed by a processor, steps of the method in any one of the first aspect are implemented.

[0049] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, steps of the method in any one of the first aspect are implemented.

[0050] This invention provides a multidimensional assessment method and system for a user's thirst level. The method includes: acquiring the user's body fluid detection data, the user's blood detection data, and the user's appearance detection image; extracting various dehydration characteristics of the user based on the user's appearance detection image; identifying the user's thirst level range based on the user's various dehydration characteristics; identifying the user's actual dehydration level based on the user's body fluid detection data and the user's blood detection data using a dehydration level assessment model; and identifying the user's actual thirst level based on the user's thirst level range and the user's actual dehydration level. This solution assesses a user's thirst level from multiple dimensions by combining bodily fluid analysis, blood analysis, and physical appearance analysis. Specifically, during the assessment, based on bodily fluid and blood analysis, the solution utilizes a designed dehydration assessment model to accurately analyze the user's actual dehydration level, thus avoiding delayed thirst assessment. Furthermore, this solution uses the range of thirst levels in the physical appearance image as a limiting standard and the actual degree of dehydration as the identification basis, comprehensively analyzing the user's actual thirst level. This avoids the subjectivity, errors, and limitations of human analysis, thereby comprehensively improving the accuracy of the assessment of the user's actual thirst level. Attached Figure Description

[0051] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart of a multi-dimensional assessment method for user thirst provided in an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of the structure of the multidimensional assessment system for user thirst provided in an embodiment of the present invention;

[0054] Figure 3 An internal structural diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0055] The user thirst degree multi-dimensional evaluation method provided by the embodiments of the present application can be applied to a user thirst degree multi-dimensional evaluation system. Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by one of ordinary skill in the art to which this application belongs. The terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the application. The terms "include" and "have" and any variations thereof in the specification and claims of the application and the above description of drawings are intended to cover non-exclusive inclusion. The terms "first", "second", and the like in the specification and claims of the application or the above description of drawings are used to distinguish different objects, not to describe a specific order.

[0056] Reference herein to "embodiments" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The occurrence of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood that the embodiments described herein can be combined with other embodiments.

[0057] In order to enable those skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings.

[0058] The user thirst degree multi-dimensional evaluation method provided by the embodiments of the present application can be applied to a user thirst degree multi-dimensional evaluation application environment. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction of the terminal and the server. The terminal can be, but is not limited to, various personal computers, notebook computers, etc. The terminal can evaluate the user's thirst degree in multiple dimensions by combining body fluid detection, blood detection, and appearance detection, etc. In the evaluation, the actual water deficiency degree of the user is accurately analyzed based on the body fluid detection and the blood detection through the water deficiency degree evaluation model designed by the present application, thereby avoiding the delay problem of the thirst degree. In addition, the actual thirst degree of the user is comprehensively analyzed based on the thirst degree range in the appearance detection image as a limiting standard and the actual water deficiency degree as a recognition basis, thereby avoiding the subjectivity, error, and limitation of human analysis, and improving the evaluation accuracy of the actual thirst degree of the user.

[0059] In one embodiment, as shown in Figure 1 The user thirst degree multi-dimensional evaluation method is described by taking the terminal as an example, which includes the following steps:

[0060] In step S101, the body fluid detection data of the user, the blood detection data of the user, and the appearance detection image of the user are acquired, and based on the appearance detection image of the user, each water deficiency characteristic feature of the user is extracted.

[0061] In this embodiment, the terminal acquires the body fluid detection data of the user and the blood detection data of the user by receiving the user detection data transmitted by the body fluid detection device and the blood detection device. The user is mainly a population of patients who need to limit water intake. The body fluid detection data includes but is not limited to body fluid discharge data and body fluid content data (i.e., the unit content value of each body fluid substance), and the blood detection data of the user includes blood content data (i.e., the unit content value of each blood substance). Then, the terminal obtains the appearance detection image of the user by image shooting of the appearance of the user and image collection of the eating and action of the user. The appearance detection image includes the lip image, the face image, and the oral cavity image of the user. Then, the terminal extracts each water deficiency characteristic feature of the user based on the appearance detection image of the user. The water deficiency characteristic features include but are not limited to the lip feature, the internal oral cavity skin feature, and the face skin feature, and the specific extraction method will be described in detail later.

[0062] In step S102, based on each water deficiency characteristic feature of the user, the thirst degree range of the user is identified, and based on the body fluid detection data of the user and the blood detection data of the user, the actual water deficiency degree of the user is identified by a water deficiency degree evaluation model.

[0063] In this embodiment, the terminal identifies the thirst degree range of the user based on each water deficiency characteristic feature of the user, and identifies the actual water deficiency degree of the user based on the body fluid detection data of the user and the blood detection data of the user by a water deficiency degree evaluation model. The water deficiency degree evaluation model is a classification evaluation model constructed by using a common machine learning classifier, such as a support vector machine (SVM), a logistic regression (LR), a random forest (RF), and a multi-layer perceptron (MLP). The specific identification process will be described in detail later.

[0064] In step S103, based on the thirst degree range of the user and the actual water deficiency degree of the user, the actual thirst degree of the user is identified.

[0065] In this embodiment, the terminal identifies the actual thirst level of the user based on the thirst level range of the user and the actual water deficiency level of the user. Specifically, the terminal presets a conversion program of the thirst level and the water deficiency level, and the conversion program is a proportion value table, wherein there is a fixed conversion proportion value between different thirst level ranges and water deficiency level ranges. The terminal calculates the thirst level value corresponding to the actual water deficiency level based on the conversion proportion value, and identifies the actual thirst level of the user based on the thirst level range of the user and the calculated thirst level value. The specific identification process will be described in detail later.

[0066] Based on the above scheme, the thirst level of the user is evaluated in multiple dimensions by combining body fluid detection, blood detection, and appearance detection. In this scheme, the actual water deficiency level of the user is accurately analyzed based on the body fluid detection and blood detection through the water deficiency level evaluation model designed in this scheme, thereby avoiding the delayed problem of the thirst level. In addition, the actual thirst level of the user is comprehensively analyzed based on the thirst level range in the appearance detection image as the limiting standard and the actual water deficiency level as the identification basis, thereby avoiding the subjective, error, and limited problems of human analysis, and thereby improving the evaluation accuracy of the actual thirst level of the user.

[0067] Optionally, based on the appearance detection image of the user, the user's water deficiency feature is extracted, including: filtering the range image of each water deficiency feature range in the appearance detection image of the user through a preset feature range filtering model; based on the range image of each water deficiency feature range, extracting the image feature data of each water deficiency feature range through an image feature extraction network, and identifying the user part type corresponding to each water deficiency feature range; and taking the image feature data corresponding to each user part type as the water deficiency feature of the user.

[0068] In this embodiment, the terminal filters the range image of each water deficiency feature range in the appearance detection image of the user through a preset feature range filtering model. The feature range filtering model is a convolutional neural network based on deep learning, which extracts the image of the water deficiency feature range concerned in each appearance detection image to obtain the range image of each water deficiency feature range. The water deficiency feature range includes but is not limited to the mouth range, the oral cavity range, the face range, etc.

[0069] Then, the terminal extracts image feature data of each water shortage representation range through an image feature extraction network based on the range image of each water shortage representation range, and identifies the user part type corresponding to each water shortage representation range. The terminal predefines the correspondence between different water shortage representation ranges and user part types of the user, for example, the mouth range corresponds to the mouth part type of the user, the oral cavity range corresponds to the oral cavity part type of the user, and the face range corresponds to the face part type of the user. The image feature extraction network is a convolutional neural network based on an attention mechanism.

[0070] Finally, the terminal takes the image feature data corresponding to each user part type as the water shortage representation features of the user.

[0071] Based on the above scheme, the image features of specific user parts are extracted to identify water shortage representation features, thereby improving the comprehensiveness and accuracy of water shortage representation identification.

[0072] Optionally, based on the water shortage representation features of the user, the thirst degree range of the user is identified, including: for each user part type, based on the image feature data of the user part type, the sub-thirst degree range corresponding to the user part type is identified through the thirst degree evaluation strategy corresponding to the user part type; based on the sub-thirst degree range corresponding to each user part type, the thirst degree range of the user is identified through the pre-set thirst representation weight value of each user part type.

[0073] In this embodiment, the terminal identifies the sub-thirst degree range corresponding to each user part type based on the image feature data of the user part type through the thirst degree evaluation strategy corresponding to the user part type for each user part type. Each user part type corresponds to a different thirst degree evaluation strategy. Each thirst degree evaluation strategy includes a correspondence between each image feature data range and a thirst degree value, and the terminal identifies the sub-thirst degree value corresponding to each user part type through the correspondence.

[0074] Then, the terminal performs summing processing on the sub-thirst degree values corresponding to each user part type through the pre-set thirst representation weight value of each user part type to obtain the initial thirst degree value of the user. Since there is a time delay between the physical representation and the actual thirst degree, the terminal performs range screening on the initial thirst degree value based on the pre-set degree range width value, that is, screens the thirst degree range with the initial thirst degree value as the center and the degree range width value as the range width, as the thirst degree range of the user.

[0075] Based on the above scheme, the sub-thirst degree values identified by combining different user part types are combined, and then weighted summation is performed to obtain the initial thirst degree value of the user, so that different user performance characteristics and the correlation weight of different part sign representations with the actual thirst degree of the user are considered, thereby intelligently identifying the thirst degree range of the user and improving the identification accuracy of the thirst degree range of the user.

[0076] Optionally, based on the body fluid detection data and the blood detection data of the user, the actual water deficiency degree of the user is identified through a water deficiency degree evaluation model, including: based on the body fluid detection data of the user, the body fluid excretion data and the body fluid content data of the user are identified, and based on the body fluid excretion data of the user, the excretion abnormal information of the user is identified; based on the blood detection data of the user, the blood content data of the user is identified, and based on the body fluid content data, the blood content data, and the excretion abnormal information of the user, the actual water deficiency degree of the user is identified through the water deficiency degree evaluation model.

[0077] In this embodiment, the terminal identifies the body fluid excretion data and the body fluid content data of the user based on the body fluid detection data of the user, and identifies the excretion abnormal information of the user based on the body fluid excretion data of the user. The excretion abnormal information includes but is not limited to the number of excretions per unit time (such as half a day, 1 day, 3 hours, 2 hours, 1 hour, etc.) being lower than a preset number threshold, or the single excretion amount being lower than a preset excretion amount threshold.

[0078] Then, the terminal identifies the blood content data of the user based on the blood detection data of the user, and identifies the actual water deficiency degree of the user based on the body fluid content data, the blood content data, and the excretion abnormal information of the user through the water deficiency degree evaluation model. The specific identification process will be described in detail later.

[0079] Based on the above scheme, the actual water deficiency degree of the user is detected by combining the detection data of the body fluid and the blood, thereby improving the identification accuracy of the actual water deficiency degree of the user.

[0080] Optionally, based on the user's body fluid content data, the user's blood content data, and the user's excretion abnormal information, the actual water deficiency degree of the user is identified through a water deficiency degree evaluation model, including: based on the user's excretion abnormal information, the excretion frequency of the user and the excretion amount distribution information of the user are identified, and based on the excretion frequency of the user and the excretion amount distribution information of the user, the water deficiency degree range of the user is identified through a water deficiency evaluation strategy; based on the user's body fluid content data and the user's blood content data, the target substance proportion information of the user's body fluid and the target substance proportion information of the user's blood are calculated; based on the target substance proportion information of the body fluid and the target substance proportion information of the blood, the actual water deficiency degree of the user is adapted in the water deficiency degree range through the water deficiency degree evaluation model.

[0081] In this embodiment, the terminal identifies the excretion frequency of the user and the excretion amount distribution information of the user based on the user's excretion abnormal information, and identifies the water deficiency degree range of the user based on the excretion frequency of the user and the excretion amount distribution information of the user through a water deficiency evaluation strategy. Among them, the water deficiency evaluation strategy includes the corresponding relationship between different excretion frequency ranges, excretion amount distribution trend ranges, and water deficiency degree ranges, and the terminal identifies the initial water deficiency degree range corresponding to the user based on the corresponding relationship. Then, the terminal adapts the water deficiency degree range corresponding to the initial water deficiency degree range in the body state database based on the user's age, gender, body shape, and diet state information, etc., to obtain the water deficiency degree range of the user. Among them, the body state database includes the corresponding relationship between different age ranges, gender, body shape ranges, and diet state ranges, and water deficiency degree deviation values, and the terminal identifies the water deficiency degree deviation value corresponding to the user through the corresponding relationship, and adjusts the range of the initial water deficiency degree range according to the water deficiency degree deviation value to obtain the water deficiency degree range.

[0082] Then, the terminal calculates the target substance proportion information of the user's body fluid and the target substance proportion information of the user's blood based on the user's body fluid content data and the user's blood content data. Among them, the target substance proportion information of the body fluid is the content proportion value of substances such as urea, uric acid, and inorganic salt. And the target substance proportion information of the blood is the electrolyte ion content proportion information, for example, sodium, potassium, chlorine, calcium, magnesium, etc.

[0083] Finally, the terminal adapts the actual water deficiency degree of the user in the water deficiency degree range based on the body fluid target substance proportion information and the blood target substance proportion information through a water deficiency degree evaluation model. The water deficiency degree evaluation model can generate a water deficiency degree value corresponding to the body fluid target substance proportion information and the blood target substance proportion information. However, the water deficiency degree value may change due to the influence of the body specificity of the user and the body state of different age stages of the user. Therefore, the water deficiency degree value and the water deficiency degree range of the user need to be adapted. When the water deficiency degree value exceeds the water deficiency degree range, the boundary value of the water deficiency degree range closest to the water deficiency degree value is used as the actual water deficiency degree. When the water deficiency degree value does not exceed the water deficiency degree range, the water deficiency degree value is directly used as the actual water deficiency degree.

[0084] Based on the above scheme, the actual water deficiency degree of the user is comprehensively analyzed by combining the excretion information and the substance proportions in the body fluid and the blood. The water deficiency degree range is adaptively adjusted based on the basic information of the body of the user and the diet information, so as to ensure that the actual water deficiency degree obtained conforms to the actual water deficiency degree of the user at present, and the accuracy of obtaining the actual water deficiency degree is improved.

[0085] Optionally, the actual thirst degree of the user is identified based on the thirst degree range of the user and the actual water deficiency degree of the user, including: identifying a thirst degree evaluation value of the user through a thirst degree conversion strategy based on the actual water deficiency degree of the user; and identifying the actual thirst degree of the user based on the thirst degree range of the user and the thirst degree evaluation value of the user.

[0086] In this embodiment, the terminal identifies a thirst degree evaluation value of the user through a thirst degree conversion strategy based on the actual water deficiency degree of the user. Specifically, the terminal first identifies the water deficiency degree range to which the actual water deficiency degree belongs, and then identifies a conversion proportion value corresponding to the water deficiency degree range based on the thirst degree conversion strategy. Then, the terminal multiplies the actual water deficiency degree by the conversion proportion value to obtain the thirst degree evaluation value of the user.

[0087] Finally, the terminal identifies the actual thirst degree of the user based on the thirst degree range of the user and the thirst degree evaluation value of the user. Specifically, since the actual thirst degree of the user has a delay, the evaluation of the thirst degree of the user needs to be judged based on the thirst degree range to obtain the accurate thirst evaluation value of the user at present. Therefore, when the thirst degree evaluation value exceeds the thirst degree range, the terminal uses the boundary value of the thirst degree range closest to the thirst degree evaluation value as the actual thirst degree. When the thirst degree evaluation value does not exceed the thirst degree range, the terminal directly uses the thirst degree evaluation value as the actual thirst degree.

[0088] Based on the above scheme, by taking the thirst degree range in the appearance detection image as the limited standard, and taking the actual water deficiency degree as the identification basis, the actual thirst degree of the user is comprehensively analyzed, the problems of subjectivity, error and limitation of human analysis are avoided, and the evaluation accuracy of the actual thirst degree of the user is comprehensively improved.

[0089] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0090] Based on the same inventive concept, the embodiments of the present application also provide a user thirst degree multi-dimensional evaluation system for implementing the above-mentioned user thirst degree multi-dimensional evaluation method. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, so the specific limitations in one or more user thirst degree multi-dimensional evaluation system embodiments provided below can refer to the limitations of the user thirst degree multi-dimensional evaluation method in the above text, and will not be repeated here.

[0091] Further referring to Figure 2 , as an implementation of the method shown in Figure 1 , the present application provides an embodiment of a user thirst degree multi-dimensional evaluation system 200, which comprises an acquisition module 210, a first identification module 220, and a second identification module 230, wherein:

[0092] The acquisition module 210 is configured to acquire the body fluid detection data of the user, the blood detection data of the user, and the appearance detection image of the user, and extract each water deficiency characteristic feature of the user based on the appearance detection image of the user;

[0093] The first identification module 220 is configured to identify the thirst degree range of the user based on each water deficiency characteristic feature of the user, and identify the actual water deficiency degree of the user by a water deficiency degree evaluation model based on the body fluid detection data of the user and the blood detection data of the user;

[0094] The second identification module 230 is configured to identify an actual thirst degree of the user based on the thirst degree range of the user and an actual water deficiency degree of the user.

[0095] Optionally, the acquisition module 210 is specifically configured to:

[0096] The range image of each water deficiency feature range is filtered from the appearance detection image of the user through a preset feature range screening model;

[0097] The image feature data of each water deficiency feature range is extracted through an image feature extraction network based on the range image of each water deficiency feature range, and the user part type corresponding to each water deficiency feature range is identified;

[0098] The image feature data corresponding to each user part type is taken as each water deficiency feature of the user.

[0099] Optionally, the first identification module 220 is specifically configured to:

[0100] For each user part type, the image feature data of the user part type is taken as the input, and the sub-thirst degree range corresponding to the user part type is identified through the thirst degree evaluation strategy corresponding to the user part type.

[0101] The thirst degree range of the user is identified through the preset thirst feature weight value of each user part type based on the sub-thirst degree range corresponding to each user part type.

[0102] Optionally, the first identification module 220 is specifically configured to:

[0103] The body fluid excretion data and the body fluid content data of the user are identified based on the body fluid detection data of the user, and the excretion abnormal information of the user is identified based on the body fluid excretion data of the user.

[0104] The blood content data of the user is identified based on the blood detection data of the user, and the actual water deficiency degree of the user is identified through a water deficiency degree evaluation model based on the body fluid content data of the user, the blood content data of the user, and the excretion abnormal information of the user.

[0105] Optionally, the first identification module 220 is specifically configured to:

[0106] The excretion frequency and the excretion amount distribution information of the user are identified based on the excretion abnormal information of the user, and the water deficiency degree range of the user is identified through a water deficiency evaluation strategy based on the excretion frequency and the excretion amount distribution information of the user.

[0107] based on the body fluid content data of the user and the blood content data of the user, calculate the body fluid target substance proportion information of the user and the blood target substance proportion information of the user;

[0108] based on the body fluid target substance proportion information and the blood target substance proportion information, adapt the actual water deficiency degree of the user in the water deficiency degree range through the water deficiency degree evaluation model.

[0109] Optionally, the second identification module 230 is specifically configured to:

[0110] based on the actual water deficiency degree of the user, identify the thirst degree evaluation value of the user through a thirst degree conversion strategy;

[0111] based on the thirst degree range of the user and the thirst degree evaluation value of the user, identify the actual thirst degree of the user.

[0112] The above-mentioned various modules in the multi-dimensional evaluation system of the user's thirst degree can be realized by software, hardware and combinations thereof. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to the above-mentioned various modules by the processor.

[0113] In one embodiment, a computer device is provided, which can be a terminal, and the internal structure diagram thereof can be as shown in Figure 3 The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a multi-dimensional evaluation method of a user's thirst degree. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input system of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad or mouse, etc.

[0114] Those skilled in the art can understand that, Figure 3The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the method of any one of the first aspect when executing the computer program.

[0116] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps of the method of any one of the first aspect when executed by a processor.

[0117] In one embodiment, a computer program product is provided, comprising a computer program, and the computer program implementing the steps of the method of any one of the first aspect when executed by a processor.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0120] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0121] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A multidimensional assessment method for user thirst levels, characterized in that, The method includes: Acquire the user's bodily fluid test data, the user's blood test data, and the user's appearance test image, and extract the user's various dehydration characteristics based on the user's appearance test image; Based on the user's various dehydration characteristics, the range of the user's thirst level is identified, and based on the user's body fluid test data and the user's blood test data, the actual degree of dehydration of the user is identified through a dehydration assessment model. The user's actual thirst level is identified based on the range of their thirst level and the user's actual degree of dehydration.

2. The method according to claim 1, characterized in that, The step of extracting various dehydration characteristics of the user based on the user's appearance detection image includes: Using a preset characterization range filtering model, the range images of each water deficiency characterization range are filtered from the user's appearance detection image; Based on the range images of each water shortage characterization range, the image feature data of each water shortage characterization range is extracted through an image feature extraction network, and the user part type corresponding to each water shortage characterization range is identified. The image feature data corresponding to each user's body part type is used as the water deficiency characterization feature of the user.

3. The method according to claim 2, characterized in that, The process of identifying the user's thirst level range based on various dehydration characteristics includes: For each user body part type, based on the image feature data of the user body part type, a thirst level assessment strategy corresponding to the user body part type is used to identify the sub-thirst level range corresponding to the user body part type; Based on the sub-thirst range corresponding to each user body part type, the user's thirst range is identified by using preset thirst representation weight values ​​for each user body part type.

4. The method according to claim 1, characterized in that, The process of identifying the user's actual degree of dehydration based on the user's bodily fluid and blood test data using a dehydration assessment model includes: Based on the user's body fluid detection data, identify the user's body fluid excretion data and body fluid content data, and based on the user's body fluid excretion data, identify the user's abnormal excretion information; Based on the user's blood test data, the user's blood content data is identified. Based on the user's body fluid content data, the user's blood content data, and the user's abnormal excretion information, the user's actual degree of dehydration is identified through a dehydration assessment model.

5. The method according to claim 4, characterized in that, The process of identifying the user's actual degree of dehydration based on the user's body fluid content data, blood content data, and abnormal excretion information, using a dehydration assessment model, includes: Based on the user's abnormal excretion information, the user's excretion frequency and excretion volume distribution information are identified. Based on the user's excretion frequency and excretion volume distribution information, a water shortage assessment strategy is used to identify the range of the user's water shortage degree. Based on the user's body fluid content data and blood content data, calculate the target substance percentage information in the user's body fluid and the target substance percentage information in the user's blood. Based on the percentage information of target substances in the body fluids and the percentage information of target substances in the blood, the dehydration assessment model is used to adapt to the user's actual degree of dehydration within the dehydration range.

6. The method according to claim 5, characterized in that, The step of identifying the user's actual thirst level based on the user's thirst range and the user's actual degree of dehydration includes: Based on the user's actual degree of dehydration, a thirst level assessment value is identified through a thirst level conversion strategy; Based on the user's thirst range and the user's thirst assessment value, the user's actual thirst level is identified.

7. A multidimensional assessment system for user thirst levels, characterized in that, The system includes: The acquisition module is used to acquire the user's body fluid detection data, the user's blood detection data, and the user's appearance detection image, and extract the user's various dehydration characteristics based on the user's appearance detection image; The first identification module is used to identify the range of the user's thirst level based on the user's various dehydration characteristics, and to identify the user's actual degree of dehydration based on the user's body fluid test data and the user's blood test data through a dehydration degree assessment model. The second identification module is used to identify the user's actual thirst level based on the user's thirst level range and the user's actual degree of dehydration.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images