Emotional health data processing system and method and computer equipment

Abstract

The invention provides an emotional health data processing system and method and computer equipment. Based on the method, before specific implementation, continuous sample detection data of a long-term sample test time period of a sample test object can be collected and utilized, and the continuous sample detection data of the long-term sample test time period of the sample test object can be obtained through combined use of logistic regression analysis, a generalized linear mixed effect model, Poisson regression analysis and a latent category mixed effect model. And training to obtain a preset prediction model suitable for emotion health prediction. In specific implementation, firstly, an acquisition module and a processing module are used for acquiring blood cell detection data of a target object in a first time period, and a key feature change track of blood cells of the target object in the first time period is determined according to the blood cell detection data; and determining an emotion health prediction result of the target object according to the key feature change track of the blood cells of the target object in the first time period by using a preset prediction model through a determination module. Therefore, the emotion health condition of the target object can be efficiently, intelligently and automatically determined.

Description

Technical Field

[0001] This specification belongs to the field of artificial intelligence technology, and in particular to emotional health data processing systems, methods, and computer devices. Background Art

[0002] As living standards continue to improve, people are paying more and more attention to their emotional health. However, based on existing methods, it is often difficult to accurately predict users' emotional health in advance.

[0003] To address the above issues, no effective solutions have been proposed so far. Summary of the Invention

[0004] This specification provides an emotional health data processing system, method, and computer device that can automatically predict the emotional health status of a target object efficiently and intelligently.

[0005] This specification provides an emotional health data processing system, including: An acquisition module is configured to acquire blood cell detection data of a target object during a first time period; wherein the blood cell detection data during the first time period includes blood cell detection data at multiple time points; a processing module, configured to process the blood cell detection data of the target object during the first time period, and determine a change trajectory of key features of the blood cells of the target object during the first time period; The determination module is used to determine the emotional health prediction result of the target object according to the change trajectory of the key characteristics of the blood cells of the target object in the first time period using a preset prediction model.

[0006] In one embodiment, the preset prediction model is trained in the following manner: Obtaining sample test data of the sample test object based on the sample test time period; Processing the sample detection data according to preset processing rules to obtain sample training data that meets the requirements; By using the sample training data, logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model are jointly used to train a preset prediction model that meets the requirements.

[0007] In one embodiment, the sample training data is used to train a preset prediction model that meets the requirements by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis, and latent class mixed effects model, including: Splitting the sample training data into a first data set, a second data set, and a third data set; Based on auxiliary reference data, multiple initial models based on latent class mixed effect models were constructed; Using the first data set to train multiple initial models respectively, to obtain corresponding multiple intermediate models; Performing model testing on the plurality of intermediate models using the second data set; and selecting a target intermediate model that meets the requirements from the plurality of intermediate models based on the model testing results; Utilizing the third data set, logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis were used in combination to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that met the requirements.

[0008] In one embodiment, the third data set is used to jointly use logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements, including: The current round of adjustments to the target intermediate model were performed using a combination of logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis in the following manner: Obtain the target intermediate model of the previous round, and use the target intermediate model of the previous round to process the sample training data of the current round in the third data set to obtain the prediction result of the current round; Based on the prediction results of the current round and the primary and secondary labels of the sample training data of the current round, check whether the target intermediate model of the previous round meets the requirements; When it is determined that the target intermediate model of the previous round does not meet the requirements, the sample training data of the current round in the third data set are processed using the first auxiliary model based on logistic regression analysis, the second auxiliary model based on the generalized linear mixed effects model, and the third auxiliary model based on Poisson regression analysis, respectively, to obtain the corresponding first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round; Determining a model adjustment rule for the current round of the target intermediate model of the previous round according to the current round prediction result, the current round first auxiliary result, the current round second auxiliary result, and the current round third auxiliary result; According to the model adjustment rules of the current round, the target intermediate model of the previous round is adjusted to obtain the target intermediate model of the current round.

[0009] In one embodiment, while processing the blood cell detection data of the target object during the first time period and determining the change trajectory of the key characteristics of the blood cells of the target object during the first time period, the acquisition module is further configured to acquire auxiliary reference data of the target object; wherein the auxiliary reference data includes at least one of the following: age, gender, lifestyle, and medical history; The processing module is further configured to construct a joint feature data set of the target object based on the key feature change trajectory of the blood cells of the target object during the first time period and the auxiliary reference data; The determination module is further configured to determine an emotional health prediction result of the target object by processing the joint feature data set of the target object using a preset prediction model.

[0010] In one embodiment, the key characteristics of the blood cells include: key characteristics of red blood cells, key characteristics of white blood cells; The key characteristics of the red blood cells include at least one of the following: red blood cell count, red blood cell distribution width SD, red blood cell distribution width CV, hematocrit, mean corpuscular hemoglobin concentration, mean corpuscular hemoglobin content, mean corpuscular volume, hemoglobin concentration; The key features of the white blood cells include at least one of the following: white blood cell count, neutrophil count, neutrophil percentage, lymphocyte count, lymphocyte percentage, eosinophil count, eosinophil percentage, basophil count, basophil percentage, monocyte count, monocyte percentage, T lymphocyte CD3 count, T lymphocyte CD3 percentage, T lymphocyte CD4 count, T lymphocyte CD4 percentage, T lymphocyte CD8 count, T lymphocyte CD8 percentage, and T lymphocyte CD4 / CD8 ratio.

[0011] In one embodiment, the key features of blood cells further include: key features of platelets and / or composite features between multiple types of blood cells; Wherein, the key characteristics of the platelets include at least: platelet count; The composite feature between the multiple types of blood cells includes at least one of the following: a ratio of the number of monocytes to lymphocytes, a ratio of the number of neutrophils to lymphocytes, and a ratio of the number of platelets to lymphocytes.

[0012] In one embodiment, a prompt module is further included; If it is determined that the target subject has an emotional health risk based on the emotional health prediction result of the target subject, the prompt module is used to generate emotional health risk prompt information; and determine a target emotional health adjustment plan that matches the current emotional health of the target subject based on the key feature change trajectory of the blood cells of the target subject in the first time period; Furthermore, after determining a target emotional health adjustment plan that matches the current emotional health status of the target subject, the acquisition module is further configured to acquire blood cell test data of the target subject for a second time period; wherein the second time period is a time period after the target emotional health adjustment plan begins to be implemented; The processing module is further configured to determine a key feature change trajectory of the target object's blood cells in the second time period based on the blood cell detection data of the target object in the second time period; The determination module is further configured to determine risk change data of the target user's emotional health in the second time period based on the key feature change trajectory of the target user's blood cells in the second time period and the key feature change trajectory of the target user's blood cells in the first time period; The prompt module is also used to update the target emotional health adjustment plan based on the risk change data of the second time period, the key feature change trajectory of the blood cells of the target object in the second time period, and the key feature change trajectory of the blood cells of the target object in the first time period.

[0013] This specification also provides a method for processing emotional health data, including: Acquire blood cell test data of a target object during a first time period; wherein the blood cell test data during the first time period includes blood cell test data at multiple time points; processing the blood cell detection data of the target object during the first time period to determine a change trajectory of key features of the blood cells of the target object during the first time period; A preset prediction model is used to determine the target object's emotional health prediction result based on the key feature change trajectory of the target object's blood cells in the first time period.

[0014] This specification also provides a computer device, including a processor and a memory for storing processor-executable instructions, wherein the processor implements the relevant steps of the emotional health data processing method when executing the instructions.

[0015] Based on the emotional health data processing system, method and computer device provided in this specification, before specific implementation, continuous sample test data of sample test subjects over a longer sample test period can be collected and utilized, and a preset prediction model suitable for emotional health prediction can be trained by jointly using multiple algorithm models such as logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model. During specific implementation, the acquisition module and the processing module first acquire and determine the key feature change trajectory of the target subject's blood cells in the first time period based on the blood cell test data of the target subject; then, the determination module uses the above-mentioned preset prediction model to predict the key feature change trajectory of the target subject's blood cells in the first time period, and determine the target subject's emotional health prediction result. In this way, the data information carried by the target subject's blood cell test data can be effectively mined and fully utilized, and the target subject's emotional health status can be automatically predicted efficiently and intelligently. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of this specification, the following is a brief introduction to the drawings required for use in the embodiments. The drawings described below are only some of the embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a schematic diagram of the structure of an emotional health data processing system provided by an embodiment of this specification; Figure 2 This is a schematic diagram of an embodiment of applying the emotional health data processing system provided by the embodiments of this specification to train a preset prediction model in a scenario example; Figure 3 This is a schematic diagram of an embodiment of applying the emotional health data processing system provided in the embodiments of this specification to process sample test data of a sample test subject in a scenario example; Figure 4 This is a schematic diagram of an embodiment of applying the emotional health data processing system provided by the embodiments of this specification to perform a round of model training adjustments on a preset prediction model in a scenario example; Figure 5 This is a schematic diagram of an embodiment of applying the emotional health data processing system provided by the embodiments of this specification to jointly use multiple algorithm models to train a preset prediction model in a scenario example; Figure 6 is a flowchart of a method for processing emotional health data provided by one embodiment of this specification; Figure 7 This is a schematic diagram of the structural composition of a computer device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0018] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0019] It should be noted that the user-related information and data involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by relevant parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users or relevant parties to choose to authorize or refuse.

[0020] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary and their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0021] See Figure 1 As shown, the embodiment of this specification provides an emotional health data processing system, which can specifically include the following structural modules: The acquisition module 101 may be specifically configured to acquire blood cell detection data of a target object during a first time period; wherein the blood cell detection data during the first time period includes blood cell detection data at multiple time points; The processing module 102 may be specifically configured to process the blood cell detection data of the target object during the first time period, and determine a change trajectory of key features of the blood cells of the target object during the first time period; The determination module 103 may be specifically configured to determine the target object's emotional health prediction result based on the target object's key feature change trajectory of the blood cells during the first time period using a preset prediction model.

[0022] The target object may be a biological object whose emotional health status is to be predicted. Specifically, the target object may be a human user or an animal, such as a monkey or an orangutan.

[0023] The first time period can be specifically understood as a continuous time period (e.g., the last two months). Blood cells of the target subject are tested at at least two different time points within the first time period to obtain blood cell test data for the target subject during the first time period. Accordingly, the blood cell test for the target subject during the first time period can include blood cell test data at multiple time points, specifically at least blood cell test data at two different time points.

[0024] Specifically, for example, the acquisition module may be connected to a physical examination database of a physical examination system of a health center.

[0025] Accordingly, in specific implementation, the target subject can go to the health center for a physical examination every week. During the physical examination, the blood cell test data of the target subject can be collected and stored in the physical examination database of the physical examination system.

[0026] When it is necessary to predict the future (or current) emotional health status of the target object, the emotional health data processing system can use the acquisition module to query the physical examination database of the physical examination system according to the object identification of the target object, and find the blood cell test data of the target object at multiple time points within the first time period (for example, the blood cell test data collected every week in the last two months) as the blood cell test data of the target object in the first time period.

[0027] The key characteristic change trajectory of the blood cells may specifically include the change trajectory of a designated biomarker of the blood cells.

[0028] The above-mentioned preset prediction model can be specifically understood as being obtained by pre-training through the combined use of multiple analysis algorithm models such as logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model. It can predict the current or future emotional health status of the object based on the change trajectory of the key characteristics of the blood cells of the input object over a period of time and the change trend over a period of time, and output an algorithm model with corresponding emotional health prediction results.

[0029] The above-mentioned emotional health prediction results can be used to indicate the future (or current) emotional health status of the target subject. For example, the above-mentioned emotional health prediction results may include: a happiness probability value and a happiness level. For another example, the above-mentioned emotional health prediction results may also include: a depression risk probability value and a depression level. For another example, the above-mentioned emotional health prediction results may also include: an anxiety risk probability value and an anxiety level, etc. Of course, it should be noted that the emotional health prediction results listed above are only exemplary. During specific implementation, the above-mentioned emotional health prediction results may also include other content according to the specific application scenario and processing requirements. This specification does not limit this.

[0030] The emotional health prediction results described above may specifically include: a primary label and a secondary label. The primary label is associated with the probability value of the target emotion of interest (e.g., depression or happiness), while the secondary label is associated with the severity level of the target emotion of interest. Accordingly, based on the emotional health prediction results, the primary label can be used to determine whether the target subject has the target emotion. Furthermore, if the target subject is determined to have the target emotion, the secondary label can be used to further determine the specific severity level of the target emotion. This allows for an accurate and comprehensive determination of the target subject's current or future emotional health. The target emotions described above may include negative emotions, such as depression and anxiety, as well as positive emotions, such as happiness and contentment. If a target subject is predicted to have a negative emotion in the future or currently, it can be determined that the target subject is at risk for emotional health.

[0031] Specifically, the processing module and the determination module can be integrated and deployed on the server side of the health center. Specifically, the server can include a server responsible for data processing in the background that can realize functions such as data transmission and data processing. Specifically, the server can be, for example, an electronic device with data calculation, storage and network interaction functions. Alternatively, the server can also be a software program running in the electronic device to provide support for data processing, storage and network interaction. In this embodiment, the number of servers is not specifically limited. The server can be one server, several servers, or a server cluster formed by several servers.

[0032] Accordingly, during implementation, the emotional health data processing system can first utilize the target subject's blood cell test data from a first time period through a processing module, performing data fitting processing to obtain a trajectory of changes in key blood cell characteristics during the first time period. The determination module then processes the trajectory of changes in key blood cell characteristics during the first time period using a preset prediction model to obtain a prediction result for the target subject's emotional health. Furthermore, the emotional health data processing system can also determine the target subject's current or future emotional health status based on the prediction result.

[0033] In addition, the emotional health data processing system may further include an interactive module, such as a display screen and / or a voice player. Accordingly, in a specific implementation, the emotional health data processing system may also utilize the interactive module to communicate with the target subject or other relevant users about the target subject's current or future emotional health status.

[0034] Based on the above embodiments, by introducing and utilizing a preset prediction model, the relevant information carried by the target object's blood cell test data can be effectively mined and fully utilized, thereby being able to automatically and efficiently determine the target object's emotional health status without increasing the test cost.

[0035] In some embodiments, when the above-mentioned processing module specifically processes the blood cell detection data of the target object in the first time period and determines the change trajectory of the key characteristics of the blood cells of the target object in the first time period, it can include: determining the discrete data and continuous data in the blood cell detection data of the target object in the first time period; and performing corresponding encoding processing on the discrete data and vector mapping on the continuous data to obtain processed data; then, based on the processed data, calculating the key characteristics of the blood cells at multiple time points in the first time period; based on the key characteristics of the blood cells at multiple time points, constructing a curve that can reflect the continuous dynamic changes of the key characteristics of the blood cells in a time period through data fitting, as the change trajectory of the key characteristics of the blood cells in the first time period of the target object.

[0036] In this way, the above-mentioned continuous change trajectory of the key characteristics of blood cells can be used in the future to replace the key characteristics of blood cells at multiple relatively discrete time points. By mining and utilizing the key characteristics of blood cells based on the time continuity relationship, relevant predictions can be made more accurately.

[0037] In some embodiments, in addition to obtaining the key feature change trajectory of the blood cells of the target object during the first time period, auxiliary reference data of the target object may also be obtained simultaneously.

[0038] The auxiliary reference data mentioned above include at least one of the following: age, gender, living habits, medical history, etc.

[0039] Specifically, the above-mentioned living habits may include one or more of the following: smoking habits, drinking habits, staying up late habits, etc. The above-mentioned diseases may include one or more of the following: a history of diabetes, a history of hypertension, etc.

[0040] Furthermore, the auxiliary reference data may also include basic body attribute parameters, such as body fat percentage BMI, etc.

[0041] In a specific implementation, the processing module can construct a joint feature data set of the target object based on the key feature change trajectory of the blood cells of the target object in the first time period and the auxiliary reference data.

[0042] Furthermore, the above-mentioned determination module can use a preset prediction model to process the joint feature data group of the target object to determine the emotional health prediction result of the target object.

[0043] Among them, the above-mentioned determination module uses a preset prediction model to process the joint feature data group of the target object to determine the emotional health prediction result of the target object. During specific implementation, it may include: using a preset prediction model to extract corresponding trajectory features from the key feature change trajectory of the blood cells; and extracting corresponding auxiliary features from the auxiliary reference data in the joint feature data group of the target object; using a first classifier to output the corresponding first prediction result about the primary label based on the curve features and the auxiliary features; using a second classifier to output the corresponding second prediction result about the secondary label based on the first prediction result, the curve features and the auxiliary features; using the output layer based on the first prediction result and the second prediction result, finally generating and outputting the emotional health prediction result of the target object.

[0044] Based on the above embodiment, by further introducing and utilizing the auxiliary reference data of the target object as a covariate for prediction guidance and supplementation, the emotional health prediction result of the target object can be predicted more accurately.

[0045] In some embodiments, the key characteristics of the blood cells may specifically include biomarkers of blood cells that can be directly or indirectly associated with changes in the emotional health of the subject. The blood cells may include: red blood cells, white blood cells, platelets, etc.

[0046] Specifically, the key features of the blood cells may include: key features of red blood cells, key features of white blood cells, etc.

[0047] Among them, the key characteristics of the above-mentioned red blood cells may specifically include at least one of the following: red blood cell count (RBC), red blood cell distribution width SD (RDW-SD), red blood cell distribution width CV (RDW-CV), hematocrit (HCT), mean corpuscular hemoglobin concentration (MCHC), mean corpuscular hemoglobin content (MCH), mean corpuscular volume (MCV), hemoglobin concentration (Hb), etc.

[0048] The red blood cell distribution width (SD) mentioned above refers specifically to the standard deviation of the red blood cell distribution width, a parameter of red blood cell volume heterogeneity that reflects the degree of consistency in red blood cell size and shape. The red blood cell distribution width (CV) mentioned above refers specifically to the coefficient of variation of the red blood cell distribution width, which reflects the degree of dispersion in red blood cell volume.

[0049] Furthermore, the key characteristics of the red blood cells may also include: erythrocyte sedimentation rate (ESR), erythrocyte sedimentation rate equation K value (ESR-K), etc.

[0050] The key features of the above-mentioned white blood cells may include at least one of the following: key features of granulocytes (e.g., neutrophils, eosinophils, basophils, etc.), key features of lymphocytes (e.g., B lymphocytes, T lymphocytes, natural killer cells, etc.), key features of monocytes (e.g., macrophages, dendritic cells, etc.), etc.

[0051] The key features of the above-mentioned white blood cells may specifically include at least one of the following: white blood cell count (WBC), neutrophil count (NeuC), neutrophil percentage (Neu%), lymphocyte count (LymC), lymphocyte percentage (Lym%), eosinophil count (EosC), eosinophil percentage (Eos%), basophil count (BasC), basophil percentage (Bas%), monocyte count (MonC), monocyte percentage (Mon%), and T lymphocyte CD3 count (CD3 count), T lymphocyte CD3 percentage (CD3%), T lymphocyte CD4 count (CD4 count), T lymphocyte CD4 percentage (CD4%), T lymphocyte CD8 count (CD8 count), T lymphocyte CD8 percentage (CD8%), and T lymphocyte CD4 / CD8 ratio.

[0052] The aforementioned T lymphocytes specifically refer to lymphocytes that mature in the thymus and are divided into helper T cells (CD4+) and cytotoxic T cells (CD8+). The aforementioned CD3 specifically refers to the CD3 protein marker commonly carried on the surface of mature T lymphocytes, and its value can reflect the body's cellular immune function. The aforementioned CD4 specifically refers to the CD4 protein marker carried on the surface of helper T cells. The aforementioned CD8 specifically refers to the CD8 protein marker carried on the surface of cytotoxic T cells.

[0053] In some embodiments, the key features of the blood cells may further include: key features of platelets and / or composite features between multiple types of blood cells; Among them, the key characteristics of the platelets mentioned above may at least include: platelet count (PLT) and the like.

[0054] The composite characteristics between the above-mentioned multiple types of blood cells specifically refer to new indicator characteristics formed by the combination of key characteristics of different types of blood cells.

[0055] Specifically, the composite characteristics between the above-mentioned multiple types of blood cells include at least one of the following: a monocyte-to-lymphocyte ratio (MLR), a neutrophil-to-lymphocyte ratio (NLR), a platelet-to-lymphocyte ratio (PLR), etc.

[0056] It should be noted that the aforementioned key characteristics of red blood cells were chosen as the key characteristics of the blood cells to be obtained and used here because of the correlation between oxidative stress and changes in the subject's emotional well-being. Furthermore, relevant research has found that changes in red blood cell indicators (for example, increased RDW) may be associated with hematopoietic dysfunction caused by oxidative damage. Therefore, by introducing and using key characteristics of red blood cells, it is possible to analyze and predict changes in a subject's emotional well-being based on the correlation with oxidative stress.

[0057] The key features of the above-mentioned white blood cells are chosen here as the key features of the blood cells to be obtained and used, taking into account the correlation between inflammation and changes in the subject's emotional health, and the correlation between neuroendocrine interactions and changes in the subject's emotional health. For example, based on relevant research findings, emotional health problems such as depression are associated with chronic low-grade inflammation, and immune disorders can be reflected by using white blood cell subtypes (for example, increased CD4+ T cells and decreased CD8+ T cells). For another example, based on relevant research findings, fluctuations in the monocyte / lymphocyte ratio (MLR) may affect the permeability of the blood-brain barrier and indirectly lead to neuroinflammation, etc. Therefore, by introducing and using the key features of white blood cells, it is possible to analyze and predict changes in the subject's health emotions based on the perspective of inflammation correlation and neuroendocrine interaction correlation.

[0058] Furthermore, the choice of using the composite features between these multiple blood cell types as the key features to be acquired and used here takes into account the correlation between chronic inflammatory pathways and changes in a subject's emotional health. For example, based on relevant research, emotional health issues such as depression are also associated with chronic inflammatory pathways. Therefore, by introducing and using the composite features between multiple blood cell types, it is possible to analyze and predict changes in a subject's emotional health based on the correlation between chronic inflammatory pathways.

[0059] Of course, it should be noted that the key characteristics of blood cells listed above are merely illustrative. During implementation, other appropriate blood cell-related characteristics may be introduced and used, depending on the specific circumstances and processing requirements. This specification does not limit this.

[0060] Based on the above embodiments, the key features of the corresponding blood cells can be obtained and used in a targeted manner according to the blood cell detection data of the target object, so that multiple relevant angles can be integrated at the same time to predict the emotional health status more accurately and comprehensively.

[0061] In some embodiments, see Figure 2 As shown, the preset prediction model can be trained in the following way: S2-1: Obtaining sample test data of the sample test object based on the sample test time period; S2-2: Processing the sample detection data according to preset processing rules to obtain sample training data that meets the requirements; S2-3: Using the sample training data, by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model, a preset prediction model that meets the requirements is trained.

[0062] The sample test subjects may specifically be subjects who have known in advance, agreed to participate in the test, and authorized the use of relevant test data. The sample test data may at least include blood cell test data of the sample test subjects.

[0063] The sample testing time period may vary for different sample test subjects; however, sample test data must be collected at least twice at different times for each sample test subject within the sample testing time period. Within the sample testing time period, each sample test data collection time may be recorded as a test time point. Accordingly, the sample test data corresponding to each sample test subject based on the sample testing time period may include sample test data at multiple test time points.

[0064] Logistic regression analysis, specifically a generalized linear regression model, is often used in data mining. By introducing and using logistic regression analysis, we can focus more on multivariate classification (classifications with more than two categories) involving complex variables, enabling more targeted discovery and utilization of data patterns in complex data for multivariate classification. This logistic regression analysis can specifically be ordered multi-classification logistic regression analysis.

[0065] The generalized linear mixed-effects model (GLMM) described above is a type of hierarchical generalized linear model, an algorithmic model based on statistical distributions. By introducing and using the GLMM, we can focus more on binary classification (classification between two categories) involving complex multivariate variables, enabling more targeted discovery and utilization of data patterns for binary classification in complex data.

[0066] Poisson regression analysis, specifically a generalized linear model based on the Poisson distribution, is often used to analyze the relationship between count-type dependent and independent variables. By introducing and using Poisson regression analysis, we can more effectively uncover temporal relationships between data and specifically identify patterns in data based on time dependence.

[0067] The Latent Class Mixed Model (LCMM) described above specifically refers to an algorithmic model that simultaneously considers fixed effects (systematic influencing factors) and random effects (individual random variation) to perform latent class classification. By introducing and using the latent class mixed effects model, it is more suitable for processing trajectory data and can effectively account for both binary and multivariate classification data patterns.

[0068] Based on the above embodiments, a preset prediction model with relatively good effect can be obtained by jointly using a variety of different model algorithms such as logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model.

[0069] Specifically, the above-mentioned acquisition of the sample test data of the sample test object based on the sample test time period can be implemented in the following manner to acquire the sample test data of the current sample test object among the sample test objects: S1: Collect auxiliary reference data of the current sample test object; S2: Collecting blood cell test data of the current sample test subject at multiple test time points within the sample test time period according to a preset tracking and collection rule; and performing an emotion test related to the target emotion of interest on the current sample test subject to obtain blood cell test data and emotion test results of the sample test subject at multiple test time points; S3: Determine, based on the emotion test results, primary labels and secondary labels for the current sample test subject at multiple test time points; and concatenate the primary labels and secondary labels for the multiple test time points with the blood cell test data corresponding to the same test time point to obtain test data for the multiple test time points; wherein the primary labels include positive labels and negative labels, and the secondary labels include empty labels and multiple degree labels; S4: Arrange the detection data of the multiple test time points in order according to the test time points, and combine them with the auxiliary reference data of the current sample test object to obtain the sample detection data of the current sample test object.

[0070] Specifically, taking depression as the target emotion of concern as an example, the above-mentioned emotion test may be an emotion test based on the SDS.

[0071] Among them, the above-mentioned SDS (Self-rating depression scale) can specifically refer to the Self-rating Depression Scale.

[0072] Accordingly, during specific implementation, a physical examination can be performed on the current sample test subject at the test time to obtain corresponding blood cell test data. Simultaneously, after the physical examination, an SDS-based questionnaire can be sent to the current sample test subject, and feedback from the current sample test subject on the questionnaire can be collected. Based on the feedback, the current sample test subject's emotional test result can be determined by assessing whether the current sample test subject has the target emotion and the specific degree of the target emotion.

[0073] The primary label may be a binary label including a positive label and a negative label. The positive label may be used to indicate the presence of the target emotion, and the negative label may be used to indicate the absence of the target emotion.

[0074] The secondary label can be a multi-element label, including an empty label and multiple degree labels. The empty label can be used to indicate that the degree of the target emotion is 0, that is, there is no target emotion label; the multiple degree labels can be used to indicate different degrees of the target emotion.

[0075] The sample test data of the current sample test object may also carry time information of the test time point of each test data.

[0076] After obtaining the sample test data of the sample test object based on the sample test time period, the discrete data and continuous data in the sample test data can be determined; and by performing corresponding encoding processing on the discrete data and vector mapping on the continuous data, the processed data can be obtained to facilitate subsequent data processing.

[0077] According to the above method, the sample detection data of multiple sample test objects based on the sample test time period can be accurately obtained.

[0078] In some embodiments, see Figure 3 As shown, the above-mentioned sample detection data is processed according to the preset processing rules to obtain sample training data that meets the requirements. In specific implementation, the sample detection data of the current sample test object can be processed according to the preset processing rules in the following manner to obtain sample training data of the current sample test object that meets the requirements: S3-1: According to the preset processing rules, detect whether there is a positive label among the preset number of first-level labels ranked at the top in the sample test data of the current sample test object; S3-2: When it is determined that there is no positive label among the preset number of first-level labels ranked at the top in the sample test data of the current sample test object, calculate the mean and variance of the current test data based on the test data of multiple test time points in the sample test data of the current sample test object; S3-3: Calculating score values of the test data of the sample test data of the current sample test object at multiple test time points based on the mean and variance of the current test data and the test data at multiple test time points; S3-4: Calculate the mean and variance of the current score value based on the score values of the test data at multiple test time points; S3-5: subtracting the average of the current score value from the score values of the test data at the multiple test time points to obtain adjusted score values of the test data at the multiple test time points; S3-6: Divide the adjusted score values of the detection data of multiple test time points by the variance of the current score value to obtain sample training data of the current sample test object that meets the requirements.

[0079] The above-mentioned preset number may be 2 or other numbers.

[0080] In specific implementations, by detecting whether a preset number of first-level labels ranked at the top of the current sample test subject's sample test data contain positive labels, it can be determined whether the current sample test subject initially possessed a relatively clear target emotion. If so, the key features of the current sample test subject's blood cells will not be of much reference value for subsequent training models to predict the emotional health status of other subjects who originally did not possess the target emotion, and may even mislead the model, affecting its accuracy.

[0081] Therefore, when it is determined that at least one positive label exists among the preset number of first-level labels ranked at the top of the sample test data of the current sample test object, the sample test data of the current sample test object can be discarded and not participate in subsequent model training. Conversely, when it is determined that no positive label exists among the preset number of first-level labels ranked at the top of the sample test data of the current sample test object, the sample test data of the current sample test object can continue to be processed to obtain sample training data that meets the requirements for subsequent model training.

[0082] In the above manner, by processing the detection data of each sample test object, the processed data can have relatively good statistical distribution characteristics as a whole, which can be more suitable for subsequent models to analyze data change trajectories, mine and utilize the data patterns, and obtain sample training data with better results and suitable for training preset prediction models.

[0083] In some embodiments, see Figure 4 As shown, the sample training data is used to train a preset prediction model that meets the requirements by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model. When implemented specifically, the following contents may be included: S4-1: Split the sample training data into a first data set, a second data set, and a third data set; S4-2: Based on auxiliary reference data, construct multiple initial models based on latent class mixed effect models; S4-3: using the first data set to train multiple initial models respectively, to obtain corresponding multiple intermediate models; S4-4: Performing model testing on the multiple intermediate models using the second data set; and selecting a target intermediate model that meets the requirements from the multiple intermediate models based on the model testing results; S4-5: Using the third data set, logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis are used in combination to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements.

[0084] During specific implementation, the sample training data may be randomly split into three groups according to corresponding proportions, which are respectively used as the first data set, the second data set and the third data set.

[0085] In specific implementations, auxiliary reference data can also be used as covariates to construct multiple initial models using the latent class mixed effect model as the base model. The multiple initial models include at least one initial model that does not consider the auxiliary reference data and one initial model that considers a class of associated auxiliary reference data.

[0086] Before specific implementation, correlation analysis can be performed on multiple auxiliary reference data based on historical data to obtain correlation analysis results; based on the correlation analysis results, the auxiliary reference data that meet the correlation requirements are divided into a category; and multiple auxiliary reference data groups are obtained; wherein each auxiliary reference data group corresponds to a category.

[0087] In specific implementation, a classification model using the latent class mixed effect model as the basic model can be directly constructed as the initial model without considering the auxiliary reference data, which is recorded as initial model No. 0.

[0088] Furthermore, model adjustment items based on a class of associated auxiliary reference data can be introduced and added to the initial model No. 0, and corresponding adjustments and modifications can be made to the corresponding model to obtain an initial model that takes into account a class of associated auxiliary reference data, such as initial model No. 1, initial model No. 2, initial model No. 3, etc.

[0089] In addition, based on the above-mentioned initial model considering one type of associated auxiliary reference data, according to the correlation analysis results, adjustment items based on the auxiliary reference data associated with other types whose correlation with the auxiliary reference data associated with the previously considered type is greater than a preset correlation threshold can be further added, and corresponding adjustments and modifications can be made to the corresponding model to obtain an initial model considering multiple types of associated auxiliary reference data.

[0090] In this way, multiple initial models that are more comprehensive and have higher coverage can be obtained by taking into account a variety of auxiliary parameter data and a variety of auxiliary reference data combinations.

[0091] In some embodiments, see Figure 5 As shown, the third data set is used in combination with logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements. In specific implementation, the current round of target intermediate model can be adjusted in the following manner by combining logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis: S5-1: Obtain the target intermediate model of the previous round, and use the target intermediate model of the previous round to process the sample training data of the current round in the third data set to obtain the prediction result of the current round; S5-2: Based on the prediction results of the current round and the primary and secondary labels of the sample training data of the current round, check whether the target intermediate model of the previous round meets the requirements; S5-3: When it is determined that the target intermediate model of the previous round does not meet the requirements, the sample training data of the current round in the third data set are processed using a first auxiliary model based on logistic regression analysis, a second auxiliary model based on a generalized linear mixed effects model, and a third auxiliary model based on Poisson regression analysis, respectively, to obtain the corresponding first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round; S5-4: Determining a model adjustment rule for the current round of the target intermediate model of the previous round based on the current round prediction result, the current round first auxiliary result, the current round second auxiliary result, and the current round third auxiliary result; S5-5: According to the model adjustment rules of the current round, the target intermediate model of the previous round is adjusted to obtain the target intermediate model of the current round.

[0092] In specific implementation, when the target intermediate model of the previous round is detected to see whether it meets the requirements based on the prediction results of the current round and the primary and secondary labels of the sample training data of the current round, and it is determined that the target intermediate model of the previous round meets the requirements, the model training can be ended; and the target intermediate model of the previous round is determined to be the preset prediction model that meets the requirements.

[0093] In specific implementation, after the target intermediate model of the current round is obtained through adjustment, the next round of training can be performed in the above manner until the obtained target intermediate model meets the requirements.

[0094] In specific implementation, the above-mentioned use of the first auxiliary model based on logistic regression analysis to process the current round of sample training data in the third data set may include: using the first auxiliary model to process the current round of sample training data, and extracting the prediction reference information generated during the processing; wherein, the prediction reference information may include: odds ratio (OR) and / or 95% confidence interval (CI); according to the above-mentioned prediction reference information, combined with the division rules of the degree level of the target emotion and the time information of the test time point, the corresponding first auxiliary result of the current round is obtained.

[0095] Based on the above method, by introducing and using the first auxiliary model, the advantages and characteristics of logistic regression analysis can be fully utilized. By additionally extracting and using the prediction reference information in the processing process, the changing characteristics of the same sample test object based on time update can be effectively considered, and thus the data patterns involving multivariate classification of individual objects can be more accurately analyzed and processed.

[0096] Accordingly, by utilizing the first auxiliary result of the current round, the network structure involving multi-classification processing in the target intermediate model of the previous round can be adjusted and optimized in a more targeted and effective manner.

[0097] In a specific implementation, the above-mentioned processing of the current round of sample training data in the third data set by using the second auxiliary model based on the generalized linear mixed effect model may include: S1: Determine the object identification of the sample test object in the current round based on the sample training data in the current round; S2: Generate a corresponding random number based on the object ID of the sample test object in the current round as a random intercept term. For example, it can be expressed as: ; S3: adding the random intercept term to the sample training data of the current round to obtain the adjusted sample training data of the current round; S4: Use the second auxiliary model to process the adjusted sample training data of the current round to obtain the corresponding second auxiliary result of the current round.

[0098] The object identifier of the sample test object may be the identity ID of the sample test object.

[0099] Specifically, for example, the core formula model in the second auxiliary model can be configured as follows:

[0100] in, It represents the probability value of predicting the presence of the target emotion when the sample numbered j is tested on the subject i. represents the random intercept term, Represents the key feature influencing items of blood cells, represents the key features of blood cells of sample test subject i with number j, Indicates the data value of the auxiliary reference data (or covariate) numbered k when the sample test object i is numbered j. Indicates the auxiliary reference data impact item numbered k, represents the random response of the sample numbered j when the test subject i is tested, logit represents the logistic regression operation based on the generalized linear mixed effects model, and K is the total number of auxiliary reference data.

[0101] Based on the above method, by introducing and using the second auxiliary model, the advantages and characteristics of the generalized linear mixed effects model can be fully utilized. By additionally adding random intercept terms corresponding to the sample test objects, the individual differences in the multiple tests of different sample test objects can be effectively considered, thereby enabling more accurate analysis and processing of data patterns involving binary classification of individual objects.

[0102] Correspondingly, by utilizing the second auxiliary result of the current round, the network structure involving binary classification processing in the target intermediate model of the previous round can be adjusted and optimized in a more targeted and effective manner.

[0103] In a specific implementation, the above-mentioned processing of the current round of sample training data in the third data set by using the third auxiliary model based on Poisson regression analysis may include: S1: Determine the time interval between two adjacent test time points based on the sample training data of the current round; and calculate the time offset term of the blood cell detection data of the two adjacent test time points based on the time interval, for example, which can be expressed as: log (Days); S2: adding the time offset term to the sample training data of the current round to obtain the adjusted sample training data of the current round; S3: Use the third auxiliary model to process the adjusted sample training data of the current round to obtain the corresponding third auxiliary result of the current round.

[0104] Specifically, for example, the core formula model in the third auxiliary model can be configured as follows:

[0105] in, Indicates the number The probability value of the target emotion predicted by the sample test object, represents the fixed intercept term, represents the influence coefficient of the key characteristics of blood cells, Indicates the number Key characteristics of the blood cells of the test subject in the sample, Indicates the number The influence coefficient of the auxiliary reference data, Indicates the number The sample test object number is The data value of the auxiliary reference data, Indicates the number The time interval between sample test object detections.

[0106] Based on the above method, by introducing and using the third auxiliary model, the advantages of Poisson regression analysis can be fully utilized. By additionally adding the time offset term of the blood cell test data of two adjacent test time points, the impact of the time interval on the test data collected by the two adjacent tests can be effectively considered, thereby enabling more accurate analysis and processing of data patterns based on time continuity relationships.

[0107] Accordingly, by utilizing the third auxiliary result of the current round, the network structure involving the time-continuation relationship processing in the target intermediate model of the previous round can be adjusted and optimized in a more targeted and effective manner.

[0108] In some embodiments, the above-mentioned determination of the model adjustment rules for the current round of the target intermediate model of the previous round based on the prediction result of the current round, the first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round may include the following when implemented: S1: Calculate the first deviation value, the second deviation value, and the third deviation value between the prediction result of the current round and the first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round respectively; S2: Determine a matching target model adjustment rule from a preset model adjustment rule library based on the first deviation value, the second deviation value, and the third deviation value; wherein the preset model adjustment rule library includes a plurality of preset model adjustment rules obtained based on clustering of historical model adjustment records, each preset model adjustment rule corresponding to an interval combination of the first deviation value, the second deviation value, and the third deviation value; S3: Calculate and adjust the target model adjustment rule based on the deviation between the prediction result of the current round and the primary label and secondary label of the sample training data of the current round to obtain the model adjustment rule of the current round for the target intermediate model of the previous round.

[0109] Based on the above embodiments, the advantages and characteristics of different algorithm models can be fully and effectively utilized to perform systematic and precise modifications and adjustments to the target intermediate model so as to efficiently train and obtain a preset prediction model that meets the requirements.

[0110] In some embodiments, the preset prediction model may further specifically include: a first auxiliary sub-model based on logistic regression analysis in parallel, a second auxiliary sub-model based on a generalized linear mixed effects model, a third auxiliary sub-model based on Poisson regression analysis, and a joint prediction sub-model based on a latent class mixed effects model connected in series with the first auxiliary sub-model, the second auxiliary sub-model, and the third auxiliary sub-model.

[0111] Correspondingly, when the above-mentioned determination module specifically uses the preset prediction model to determine the emotional health prediction result of the target object based on the key feature change trajectory of the blood cells of the target object in the first time period, it can include: using the first auxiliary sub-model, the second auxiliary sub-model, and the third auxiliary sub-model in the preset prediction model to respectively process the key feature change trajectory of the blood cells of the target object in the first time period to obtain the corresponding first auxiliary result, second auxiliary result, and third auxiliary result; splicing the first auxiliary result, the second auxiliary result, the third auxiliary result, and the key feature change trajectory of the blood cells of the target object in the first time period to obtain an intermediate joint data group; using the joint prediction sub-model to process the above-mentioned intermediate joint data to obtain and output the corresponding emotional health prediction result.

[0112] In some embodiments, while processing the blood cell detection data of the target subject during the first time period and determining the change trajectory of the key characteristics of the blood cells of the target subject during the first time period, the acquisition module is further configured to acquire auxiliary reference data of the target subject; wherein the auxiliary reference data may specifically include at least one of the following: age, gender, living habits, medical history, etc.; Accordingly, the processing module may be further configured to construct a joint feature data set of the target object based on the key feature change trajectory of the blood cells of the target object during the first time period and the auxiliary reference data; The determination module may also be specifically configured to utilize a preset prediction model to process the joint feature data set of the target object to determine an emotional health prediction result of the target object.

[0113] Based on the above embodiment, by introducing and combining the auxiliary reference data with the key feature change trajectory of the target object's blood cells in the first time period, the emotional health status of the target object can be predicted more accurately.

[0114] In some embodiments, the emotional health data processing system may further include a prompt module; In specific implementation, when it is determined that the target object is at an emotional health risk based on the emotional health prediction result of the target object, the prompt module can be used to generate emotional health risk prompt information; and based on the key feature change trajectory of the target object's blood cells in the first time period, determine the target emotional health adjustment plan that matches the current emotional health status of the target object.

[0115] Among them, the above-mentioned emotional health risk prompt information can be specifically used to prompt whether the target object has negative target emotions (for example, depression, anxiety, etc.) in the future or currently.

[0116] Specifically, based on the emotional health prediction result of the target object, when it is predicted that the target object will have a negative target emotion in the future, it can be determined that the target object has an emotional health risk.

[0117] In a specific implementation, a preset adjustment plan library can be queried based on the key feature change trajectory of the target subject's blood cells during the first time period to find the preset emotional health adjustment plan with the highest degree of match between the key feature change trajectory template of the blood cells and the key feature change trajectory of the target subject's blood cells during the first time period, and the preset emotional health adjustment plan is used as the matching target emotional health adjustment plan. The preset adjustment plan library can store multiple preset emotional health adjustment plans, each of which corresponds to at least one key feature change trajectory template of the blood cells.

[0118] Based on the above-mentioned target emotional health adjustment plan, appropriate emotional adjustment interventions can be carried out on the target subjects in a targeted manner to alleviate negative target emotions and / or increase positive target emotions (for example, happiness, etc.).

[0119] Before specific implementation, a large number of historical emotional health adjustment records can be collected; and the historical emotional health adjustment records with expected adjustment effects can be screened out from the historical emotional health adjustment records as sample emotional adjustment records; based on the sample emotional adjustment records, the corresponding sample emotional adjustment schemes and the key feature change trajectories of blood cells are determined; the sample emotional adjustment schemes are clustered to obtain multiple clusters; wherein each cluster contains one or more identical or similar sample emotional adjustment schemes; based on the multiple clusters, the corresponding multiple preset emotional health adjustment schemes are determined. Further, the key feature change trajectories of blood cells corresponding to the sample emotional adjustment schemes contained in each cluster can be fused and sorted to determine the key feature change trajectory template of blood cells corresponding to the preset emotional health adjustment scheme of the cluster; and then the corresponding preset emotional health adjustment scheme and the key feature change trajectory template of blood cells are associated and stored in the corresponding database to obtain the above-mentioned preset adjustment scheme library.

[0120] During specific implementation, the prompt module can add the above-mentioned target emotional health adjustment plan to the corresponding emotional health risk prompt information; and then send the emotional health risk prompt information to the target object or other relevant users, so as to intelligently and accurately assist the target object in targeted emotional adjustment to ensure that the target object's emotions are as healthy and stable as possible.

[0121] In some embodiments, after determining the target emotional health adjustment plan that matches the current emotional health of the target subject, the acquisition module may further be used to acquire blood cell test data of the target subject for a second time period; wherein the second time period is a time period after the target emotional health adjustment plan is started; The processing module may also be configured to determine a key feature change trajectory of the target object's blood cells in the second time period based on the blood cell detection data of the target object in the second time period; The determination module may also be configured to determine risk change data for the second time period regarding the emotional health of the target user based on the key feature change trajectory of the target object's blood cells in the second time period and the key feature change trajectory of the target object's blood cells in the first time period; The prompt module can also be used to update the target emotional health adjustment plan based on the risk change data of the second time period, the key feature change trajectory of the blood cells of the target object in the second time period, and the key feature change trajectory of the blood cells of the target object in the first time period.

[0122] In a specific implementation, during the second time period of the target subject's emotional adjustment under the targeted emotional health adjustment plan, blood cell test data of the target subject can be collected multiple times at different time points to obtain the target subject's blood cell test data for the second time period. Based on the target subject's blood cell test data for the second time period, the target subject's emotional health changes during the second time period can be continuously tracked and analyzed by determining and utilizing the trajectory of changes in key characteristics of the target subject's blood cells during the second time period based on the targeted emotional health adjustment plan.

[0123] Furthermore, the risk change data of the second time period regarding the emotional health of the target user can be determined using a preset prediction model based on the key feature change trajectory of the blood cells of the target object in the second time period and the key feature change trajectory of the blood cells of the target object in the first time period; and then, based on the risk change data, the execution effect of the target emotional health adjustment plan is evaluated; and based on the evaluation results, it is determined whether the currently used target emotional health adjustment plan needs to be modified and updated.

[0124] According to the evaluation results, when it is determined that the emotional health status of the target subject has improved and the rate of improvement is in line with expectations, the current target emotional health adjustment plan can continue to be implemented for the target subject.

[0125] On the contrary, if the assessment results show that the target subject's emotional health has not improved, or has improved but the rate of improvement is not as expected, the current target emotional health adjustment method can be modified and adjusted based on the risk change data of the second time period, the key feature change trajectory of the target subject's blood cells in the second time period, and the key feature change trajectory of the target subject's blood cells in the first time period, to update the target emotional health adjustment plan. Furthermore, the updated target emotional health adjustment plan can be subsequently executed on the target subject to effectively adjust the target subject's emotions and ensure that the target subject's emotions are as healthy and stable as possible.

[0126] As can be seen from the above, based on the emotional health data processing system provided by the embodiment of this specification, before specific implementation, it is possible to collect and utilize continuous sample test data of the sample test subject for a longer sample test period, and train a preset prediction model suitable for emotional health prediction by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model. During specific implementation, first, the acquisition module and the processing module are used to obtain and determine the key feature change trajectory of the blood cells of the target object in the first time period based on the blood cell test data of the target object; then, the determination module uses the preset prediction model to determine the emotional health prediction result of the target object based on the key feature change trajectory of the blood cells of the target object in the first time period. In this way, the data information carried by the blood cell test data of the target object can be effectively mined and fully utilized, and the emotional health status of the target object can be automatically determined efficiently and intelligently.

[0127] See Figure 6 As shown, the embodiment of this specification also provides a method for processing emotional health data, which may include the following contents during implementation: S601: Acquire blood cell test data of a target object in a first time period; wherein the blood cell test data in the first time period includes blood cell test data at multiple time points; S602: Processing the blood cell detection data of the target object in the first time period to determine a key feature change trajectory of the blood cells of the target object in the first time period; S603: Determine the target object's emotional health prediction result based on the target object's key feature change trajectory of the blood cells during the first time period using a preset prediction model.

[0128] In some embodiments, the preset prediction model is trained in the following manner: sample test data of the sample test object based on the sample test time period is obtained; the sample test data is processed according to preset processing rules to obtain sample training data that meets the requirements; and the sample training data is used to train a preset prediction model that meets the requirements by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model.

[0129] In some embodiments, the sample training data is used to train a preset prediction model that meets the requirements by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model. In specific implementation, it can include: splitting the sample training data into a first data set, a second data set, and a third data set; constructing multiple initial models based on the latent class mixed effects model based on auxiliary reference data; using the first data set to train multiple initial models respectively to obtain corresponding multiple intermediate models; using the second data set to perform model testing on the multiple intermediate models; and based on the model test results, screening out a target intermediate model that meets the requirements from the multiple intermediate models; using the third data set, jointly using logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis, to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements.

[0130] In some embodiments, the third data set is used in combination with logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements. In specific implementation, the target intermediate model of the current round can be adjusted in the following manner by combining logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis: obtaining the target intermediate model of the previous round, and using the target intermediate model of the previous round to process the sample training data of the current round in the third data set to obtain the prediction results of the current round; detecting whether the target intermediate model of the previous round meets the requirements based on the prediction results of the current round and the primary labels and secondary labels of the sample training data of the current round; When it is determined that the target intermediate model of the previous round does not meet the requirements, the first auxiliary model based on logistic regression analysis, the second auxiliary model based on the generalized linear mixed effects model, and the third auxiliary model based on Poisson regression analysis are used to process the sample training data of the current round in the third data set to obtain the corresponding first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round; based on the prediction result of the current round, the first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round, the model adjustment rules of the current round for the target intermediate model of the previous round are determined; based on the model adjustment rules of the current round, the target intermediate model of the previous round is adjusted to obtain the target intermediate model of the current round.

[0131] In some embodiments, while processing the blood cell detection data of the target subject during the first time period and determining the change trajectory of the key characteristics of the blood cells of the target subject during the first time period, the method may further include: obtaining auxiliary reference data of the target subject; wherein the auxiliary reference data includes at least one of the following: age, gender, lifestyle, and medical history; Accordingly, a joint feature data group of the target object is constructed based on the key feature change trajectory of the blood cells of the target object in the first time period and the auxiliary reference data; and the preset prediction model is used to process the joint feature data group of the target object to determine the emotional health prediction result of the target object.

[0132] In some embodiments, the key features of the blood cells may specifically include: key features of red blood cells, key features of white blood cells, etc.; The key features of the red blood cells may include at least one of the following: red blood cell count, red blood cell distribution width SD, red blood cell distribution width CV, hematocrit, mean corpuscular hemoglobin concentration, mean corpuscular hemoglobin content, mean corpuscular volume, hemoglobin concentration, etc.; The key features of the white blood cells may include at least one of the following: white blood cell count, neutrophil count, neutrophil percentage, lymphocyte count, lymphocyte percentage, eosinophil count, eosinophil percentage, basophil count, basophil percentage, monocyte count, monocyte percentage, T lymphocyte CD3 count, T lymphocyte CD3 percentage, T lymphocyte CD4 count, T lymphocyte CD4 percentage, T lymphocyte CD8 count, T lymphocyte CD8 percentage, T lymphocyte CD4 / CD8 ratio, etc.

[0133] In some embodiments, the key features of the blood cells may further include: key features of platelets and / or composite features between multiple types of blood cells; The key characteristics of the platelets may include at least: platelet count, etc.; The composite characteristics between the multiple types of blood cells may specifically include at least one of the following: a ratio of the number of monocytes to lymphocytes, a ratio of the number of neutrophils to lymphocytes, a ratio of the number of platelets to lymphocytes, etc.

[0134] In some embodiments, when the method is implemented, it may also include: generating emotional health risk prompt information when it is determined that the target object is at emotional health risk based on the emotional health prediction result of the target object; and determining a target emotional health adjustment plan that matches the current emotional health status of the target object based on the key feature change trajectory of the target object's blood cells in the first time period.

[0135] In some embodiments, after determining a target emotional health adjustment plan that matches the current emotional health of the target subject, the method further includes: obtaining blood cell test data of the target subject for a second time period; wherein the second time period is a time period after the target emotional health adjustment plan is started; Accordingly, the key feature change trajectory of the target object's blood cells in the second time period can be determined based on the blood cell detection data of the target object in the second time period; the risk change data of the target user's emotional health in the second time period can be determined based on the key feature change trajectory of the target object's blood cells in the second time period and the key feature change trajectory of the target object's blood cells in the first time period; the target emotional health adjustment plan can be updated based on the risk change data of the second time period, the key feature change trajectory of the target object's blood cells in the second time period and the key feature change trajectory of the target object's blood cells in the first time period.

[0136] As can be seen above, the emotional health data processing method provided in the embodiments of this specification first obtains and determines the key feature change trajectory of the target subject's blood cells during a first time period based on the target subject's blood cell test data during the first time period. Then, a preset prediction model is used to determine the target subject's emotional health prediction result based on the key feature change trajectory of the target subject's blood cells during the first time period. This allows for efficient and intelligent automatic determination of the target subject's emotional health status.

[0137] This specification provides a computer device, referring to Figure 7 The computer device includes a network communication port 701, a processor 702, and a memory 703, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0138] The network communication port 701 can be used to obtain blood cell detection data of a target object in a first time period. The blood cell detection data in the first time period includes blood cell detection data at multiple time points.

[0139] The processor 702 can be specifically used to process the blood cell detection data of the target object in the first time period, determine the key feature change trajectory of the blood cells of the target object in the first time period; and use a preset prediction model to determine the emotional health prediction result of the target object based on the key feature change trajectory of the blood cells of the target object in the first time period.

[0140] The memory 703 may be specifically used to store corresponding instruction programs, and relevant data such as preset prediction models.

[0141] Based on the above method, the relevant structural performance of computer equipment can be effectively utilized, the data processing speed of electronic equipment can be improved, and emotional health data processing can be efficiently realized.

[0142] In this embodiment, the network communication port 701 can be a virtual port that is bound to different communication protocols, thereby being capable of sending or receiving different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0143] In this embodiment, the processor 702 can be implemented in any appropriate manner. For example, the processor can take the form of a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, an embedded microcontroller, etc. This specification is not intended to limit this.

[0144] In this embodiment, the memory 703 may include multiple levels. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with a storage function that does not have a physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0145] An embodiment of this specification also provides a computer-readable storage medium based on the above-mentioned emotional health data processing method, wherein the computer-readable storage medium stores computer program instructions, which, when executed, implement the following: obtaining blood cell detection data of a target object for a first time period; wherein the blood cell detection data of the first time period includes blood cell detection data of multiple time points; processing the blood cell detection data of the target object for the first time period to determine the key feature change trajectory of the blood cells of the target object for the first time period; and using a preset prediction model to determine the emotional health prediction result of the target object based on the key feature change trajectory of the blood cells of the target object for the first time period.

[0146] In this embodiment, the storage medium includes, but is not limited to, random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured in accordance with a standard specified by a communication protocol and used for network connection and communication.

[0147] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be repeated here.

[0148] An embodiment of the present specification also provides a computer program product, which at least includes a computer program, and when the computer program is executed by a processor, implements the following method steps: obtaining blood cell detection data of a target object in a first time period; wherein the blood cell detection data in the first time period includes blood cell detection data at multiple time points; processing the blood cell detection data of the target object in the first time period to determine a key feature change trajectory of the target object's blood cells in the first time period; and using a preset prediction model to determine an emotional health prediction result of the target object based on the key feature change trajectory of the target object's blood cells in the first time period.

[0149] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described in terms of functions and are divided into various modules and described separately. Of course, when implementing this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, 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, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0150] Although this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the steps among many, and does not represent the only execution order. When the device or client product is actually executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, product or device. Without further restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. Words such as first, second, etc. are used to indicate names and do not indicate any particular order.

[0151] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0152] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer-readable storage media, including storage devices.

[0153] As can be seen from the above description of the embodiments, those skilled in the art will clearly understand that this specification can be implemented using software plus a necessary general-purpose hardware platform. Based on this understanding, the technical solution of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (such as a personal computer, mobile terminal, server, or network device) to execute the methods described in various embodiments or portions of the embodiments of this specification.

[0154] The various embodiments in this specification are described in a progressive manner. References to the common or similar parts of the various embodiments are sufficient. Each embodiment focuses on the differences from the other embodiments. This specification can be used in a variety of general-purpose or specialized computer system environments or configurations. For example, personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0155] Although the present specification has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present specification without departing from the spirit of the present specification. It is intended that the appended claims include these modifications and variations without departing from the spirit of the present specification.

Claims

1. An emotional health data processing system, characterized in that: include: An acquisition module, configured to acquire blood cell detection data of a target object during a first time period; wherein the blood cell detection data during the first time period includes blood cell detection data at multiple time points; a processing module, configured to process the blood cell detection data of the target object during the first time period, and determine a change trajectory of key features of the blood cells of the target object during the first time period; The determination module is used to determine the emotional health prediction result of the target object according to the change trajectory of the key characteristics of the blood cells of the target object in the first time period using a preset prediction model.

2. The system according to claim 1, wherein: The preset prediction model is trained in the following manner: Obtaining sample test data of the sample test object based on the sample test time period; Processing the sample detection data according to preset processing rules to obtain sample training data that meets the requirements; By using the sample training data, logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model are jointly used to train a preset prediction model that meets the requirements.

3. The system according to claim 2, characterized in that The sample training data is used to train a preset prediction model that meets the requirements by jointly using logistic regression analysis, generalized linear mixed effects model, Poisson regression analysis and latent class mixed effects model, including: Splitting the sample training data into a first data set, a second data set, and a third data set; Based on auxiliary reference data, multiple initial models based on latent class mixed effect models were constructed; Using the first data set to train multiple initial models respectively, to obtain corresponding multiple intermediate models; Performing model testing on the plurality of intermediate models using the second data set; and selecting a target intermediate model that meets the requirements from the plurality of intermediate models based on the model testing results; Utilizing the third data set, logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis were used in combination to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that met the requirements.

4. The system according to claim 3, characterized in that The third data set is used to jointly use logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis to perform multiple rounds of adjustments on the target intermediate model to obtain a preset prediction model that meets the requirements, including: The current round of adjustments to the target intermediate model were performed using a combination of logistic regression analysis, generalized linear mixed effects model, and Poisson regression analysis in the following manner: Obtain the target intermediate model of the previous round, and use the target intermediate model of the previous round to process the sample training data of the current round in the third data set to obtain the prediction result of the current round; Based on the prediction results of the current round and the primary and secondary labels of the sample training data of the current round, check whether the target intermediate model of the previous round meets the requirements; When it is determined that the target intermediate model of the previous round does not meet the requirements, the sample training data of the current round in the third data set are processed using the first auxiliary model based on logistic regression analysis, the second auxiliary model based on the generalized linear mixed effects model, and the third auxiliary model based on Poisson regression analysis, respectively, to obtain the corresponding first auxiliary result of the current round, the second auxiliary result of the current round, and the third auxiliary result of the current round; Determining a model adjustment rule for the current round of the target intermediate model of the previous round according to the current round prediction result, the current round first auxiliary result, the current round second auxiliary result, and the current round third auxiliary result; According to the model adjustment rules of the current round, the target intermediate model of the previous round is adjusted to obtain the target intermediate model of the current round.

5. The system according to claim 1, wherein: While processing the blood cell detection data of the target object during the first time period and determining the change trajectory of the key characteristics of the blood cells of the target object during the first time period, the acquisition module is further configured to acquire auxiliary reference data of the target object; wherein the auxiliary reference data includes at least one of the following: age, gender, living habits, and medical history; The processing module is further configured to construct a joint feature data set of the target object based on the key feature change trajectory of the blood cells of the target object during the first time period and the auxiliary reference data; The determination module is further configured to determine an emotional health prediction result of the target object by processing the joint feature data set of the target object using a preset prediction model.

6. The system according to claim 1, wherein: The key characteristics of the blood cells include: key characteristics of red blood cells, key characteristics of white blood cells; The key characteristics of the red blood cells include at least one of the following: red blood cell count, red blood cell distribution width SD, red blood cell distribution width CV, hematocrit, mean corpuscular hemoglobin concentration, mean corpuscular hemoglobin content, mean corpuscular volume, hemoglobin concentration; The key features of the white blood cells include at least one of the following: white blood cell count, neutrophil count, neutrophil percentage, lymphocyte count, lymphocyte percentage, eosinophil count, eosinophil percentage, basophil count, basophil percentage, monocyte count, monocyte percentage, T lymphocyte CD3 count, T lymphocyte CD3 percentage, T lymphocyte CD4 count, T lymphocyte CD4 percentage, T lymphocyte CD8 count, T lymphocyte CD8 percentage, and T lymphocyte CD4 / CD8 ratio.

7. The system according to claim 6, characterized in that The key features of blood cells also include: key features of platelets and / or composite features between multiple types of blood cells; Wherein, the key characteristics of the platelets include at least: platelet count; The composite feature between the multiple types of blood cells includes at least one of the following: a ratio of the number of monocytes to lymphocytes, a ratio of the number of neutrophils to lymphocytes, and a ratio of the number of platelets to lymphocytes.

8. The system according to claim 1, wherein: Also includes a prompt module; When it is determined that the target object has an emotional health risk based on the emotional health prediction result of the target object, the prompt module is used to generate emotional health risk prompt information; and determining a target emotional health adjustment plan that matches the current emotional health of the target subject based on the change trajectory of the key characteristics of the blood cells of the target subject during the first time period; Furthermore, after determining a target emotional health adjustment plan that matches the current emotional health status of the target subject, the acquisition module is further configured to acquire blood cell test data of the target subject for a second time period; wherein the second time period is a time period after the target emotional health adjustment plan begins to be implemented; The processing module is further configured to determine a key feature change trajectory of the target object's blood cells in the second time period based on the blood cell detection data of the target object in the second time period; The determination module is further configured to determine risk change data of the target user's emotional health in the second time period based on the key feature change trajectory of the target user's blood cells in the second time period and the key feature change trajectory of the target user's blood cells in the first time period; The prompt module is also used to update the target emotional health adjustment plan based on the risk change data of the second time period, the key feature change trajectory of the blood cells of the target object in the second time period, and the key feature change trajectory of the blood cells of the target object in the first time period.

9. A method for processing emotional health data, characterized in that: include: Acquire blood cell test data of a target object during a first time period; wherein the blood cell test data during the first time period includes blood cell test data at multiple time points; processing the blood cell detection data of the target object during the first time period to determine a change trajectory of key characteristics of the blood cells of the target object during the first time period; A preset prediction model is used to determine the target object's emotional health prediction result based on the key feature change trajectory of the target object's blood cells in the first time period.

10. A computer device, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the steps of the method according to claim 9 are implemented when the processor executes the instructions.

Images