CN115881297A - User portrait system based on organ state data - Google Patents
User portrait system based on organ state data Download PDFInfo
- Publication number
- CN115881297A CN115881297A CN202111142369.2A CN202111142369A CN115881297A CN 115881297 A CN115881297 A CN 115881297A CN 202111142369 A CN202111142369 A CN 202111142369A CN 115881297 A CN115881297 A CN 115881297A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- model
- predetermined
- data
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Embodiments of the present disclosure disclose a user representation system based on organ state data. One embodiment of the method comprises: the data sensor is used for acquiring an organ state data set of a user and acquiring an alarm threshold; a processor to generate a set of evaluation scores; generating an evaluation result set; sending the evaluation result set to the prepositive equipment; the front-end equipment displays the evaluation result set and sends the evaluation starting information input by the user to the processor; and the processor is also used for responding to each evaluation result in the evaluation result set and sending out alarm prompt information by the front-end equipment in response to the evaluation result being larger than the alarm threshold value. The processor with the structure automatically generates the health condition evaluation result set of the user represented by the sensory state data set of the user acquired by the data sensor by utilizing the predetermined first evaluation template set and the second evaluation template set, so that the health condition evaluation time is shortened, and the consumed evaluation resources are saved.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a user representation system based on organ status data.
Background
With the continuous improvement of living standard of residents in China, personal health is more and more emphasized, and health management inclines from disease treatment to disease prevention. Physical examination is used as an important means for health monitoring, data in a physical examination report is analyzed, follow-up physical examination data and treatment data are tracked, and the relation between related data and diseases can be analyzed. The device or the system for carrying out the health portrait according to the physical examination or clinic data can assist in predicting and early warning the health condition of the user.
However, when generating a user health representation using a device or system equipment, there are often technical problems as follows:
first, when a neural network model is used for user health portrayal based on physical examination or diagnosis data in the prior art, due to the fact that massive heterogeneous data exists, the running speed of a device or a system is very slow, and the real-time application requirement of the health portrayal cannot be met.
Secondly, the neural network model has a complex structure and many parameters, and even if advanced methods such as a pre-training model are applied, huge computing resources are consumed, the requirement on a server is very high, and great training pressure is caused. In addition, the neural network model is a black box model, so that the interpretability is poor and the user acceptance is low.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a user representation system based on organ status data to address one or more of the technical problems mentioned in the background section above.
Some embodiments of the present disclosure provide a user representation system based on organ state data, the method comprising: the data sensor is used for acquiring an organ state data set of a user and acquiring an alarm threshold; a processor for generating a set of assessment scores using the set of organ state data and a predetermined set of first assessment templates; generating an evaluation result set according to the evaluation score set and a predetermined second evaluation template set; sending the evaluation result set to the prepositive equipment; the front-end equipment displays the evaluation result set and sends the evaluation starting information input by the user to the processor; the processor is further used for responding to the assessment result larger than an alarm threshold value for each assessment result in the assessment result set and controlling the front-end equipment to send out alarm prompt information, wherein the alarm prompt information represents abnormal organ state
The above embodiments of the present disclosure have the following beneficial effects: by the aid of the organ state data-based user representation system, the health condition evaluation result set of the user represented by the sensory state data set of the user acquired by the data sensor is automatically generated by the first evaluation template set and the second evaluation template set which are determined in advance, health condition evaluation time is shortened, and consumed evaluation resources are saved. Specifically, the inventor finds that the reason for the poor working level of the current user health representation system is that: in the prior art, when a neural network model is used for user health portrait based on physical examination or diagnosis data, the running speed of a device or a system is very slow due to the existence of massive heterogeneous data, and the real-time application requirement of the health portrait cannot be met. Based on this, firstly, some embodiments of the present disclosure propose a data sensor for acquiring a set of organ state data of a user and obtaining an alarm threshold. Next, a processor is configured to generate an evaluation score set using the organ state data set and a predetermined first evaluation template set, and generate an evaluation result set according to the evaluation score set and a predetermined second evaluation template set. Specifically, the processor generates an evaluation result set by using a first evaluation template set and a second evaluation template set which are determined in advance. Then, the processor transmits the evaluation result set to the front-end device, and the front-end device displays the evaluation result set and transmits evaluation start information input by the user to the processor. And finally, the processor is further used for responding to each evaluation result in the evaluation result set and sending out alarm prompt information by the front-end equipment, wherein the alarm prompt information represents that the organ state is abnormal. According to the embodiment, a neural network model does not need to be called or operated, the evaluation result set is generated by directly utilizing the first evaluation template set and the second evaluation template set which are determined in advance, the processing speed is high, the required computing resources are small, and the application level of the health portrait system is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
FIG. 1 is an exemplary system architecture of a user representation system based on organ state data of some embodiments of the present disclosure;
FIG. 2 is a timing diagram of one embodiment of a user representation system based on organ state data according to the present disclosure;
FIG. 3 is a flow diagram of one embodiment of a user representation system based on organ state data, according to the present disclosure;
FIG. 4 is a flow diagram for one embodiment of a training step for evaluating a model, according to the present disclosure;
fig. 5 is a schematic block diagram of a terminal device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and the embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 illustrates an exemplary system architecture 100 of a user representation system based on organ state data according to embodiments of the present application.
As shown in fig. 1, the system architecture 100 may include a data sensor 101, a processor 102, a front-end device 103, and a network 104. Network 104 is used to provide a medium for communication links between data sensor 101, processor 102, and front-end device 103. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may interact with the processor 102 via the network 104 using the data sensor 101 and the head end device 103 to receive or send messages or the like. The data sensor 101 may be a computer, a camera, or the like, and is used to acquire the organ status data set and the alarm threshold of the user.
The processor 102 may provide various services, for example, the processor 102 may generate a set of assessment scores using a set of organ state data received from the data sensor 101 and a predetermined set of first assessment templates; generating an evaluation result set according to the evaluation score set and a predetermined second evaluation template set; and sending the evaluation result set to the prepositive equipment. The processor 102 is further configured to, for each evaluation result in the evaluation result set, control the front-end device 103 to issue an alarm prompt message in response to the evaluation result being greater than an alarm threshold, where the alarm prompt message indicates that the organ state is abnormal.
It should be noted that the user representation system based on organ state data provided by the embodiments of the present application is generally executed by the processor 102. It should be understood that the number of data sensors, processors, head end devices and networks in fig. 1 is merely illustrative. There may be any number of data sensors, processors, head end devices, and networks, as desired for the implementation.
With continued reference to FIG. 2, a timing sequence 200 for one embodiment of a user representation system based on organ state data is shown, in accordance with the present application.
The user representation system based on organ state data in the embodiment of the application can comprise: a data sensor (e.g., data sensor 101 shown in fig. 1), a processor (e.g., processor 102 shown in fig. 1), and a head-end device (e.g., head-end device 103 shown in fig. 1). The system comprises a data sensor, a data processing unit and a warning processing unit, wherein the data sensor is used for collecting an organ state data set of a user and acquiring a warning threshold 201; a processor for generating a set of assessment scores using the set of organ state data and a predetermined set of first assessment templates; generating an evaluation result set according to the evaluation score set and a predetermined second evaluation template set; sending the evaluation result set to the front-end device 202; the front-end equipment displays the evaluation result set and sends evaluation starting information input by a user to the processor 203; the processor is further configured to, for each evaluation result in the evaluation result set, control the front-end device to send out an alarm prompt message 204 in response to the evaluation result being greater than an alarm threshold. Wherein the alarm prompt information represents that the organ state is abnormal.
With further reference to FIG. 3, a flow 300 of one embodiment of a user representation system based on organ state data in accordance with the present application is illustrated. The process 300 of the organ state data based user representation system includes the steps of:
In some embodiments, a data sensor of an executive (e.g., a server as shown in FIG. 1) of a user representation system based on organ state data is used to collect a user's organ state data set and obtain an alarm threshold. In particular, the set of organ state data of the user may be medical data of the user in a medical data platform. In particular, the medical data platform may include, but is not limited to, one of: hospital Information Systems (HIS), medical imaging and Communication Systems (PACS), laboratory Information Management Systems (LIS), and Remote Access Service Systems (RAS). The user's organ state data set may include, but is not limited to, one of: a basic information data set, a symptom sign data set, a test data set, an examination data set, and a diagnosis data set. In particular, the alarm threshold may be a threshold that characterizes a health state of the user.
In some embodiments, the processor of the executing subject is configured to generate a set of assessment scores using the set of organ state data and a predetermined set of first assessment templates; generating an evaluation result set according to the evaluation score set and a predetermined second evaluation template set; and sending the evaluation result set to the prepositive equipment. Wherein the evaluation score set comprises a first number of evaluation score sets, the evaluation score sets are used for representing evaluation information of a specific organ, the evaluation result set comprises a first number of evaluation results, the evaluation results represent organ states, and the evaluation result set represents organ state portrayal of a user.
In some optional implementations of some embodiments, the processor, prior to generating the set of assessment scores using the set of organ state data and the predetermined first set of assessment templates, is further to: acquiring a historical organ state data set; preprocessing the historical organ state data set to obtain a preprocessed historical organ state data set; generating a historical organ state feature set based on the preprocessed historical organ state data set; and generating a first evaluation template set and a second evaluation template set based on the historical organ state feature set and a predetermined evaluation model. In particular, the set of historical organ state data may be medical data of the user in a medical data platform.
And preprocessing the historical organ state data set to obtain a preprocessed historical organ state data set. Specifically, the preprocessing may be to perform quality control processing on the historical organ state data set according to a predefined quality control rule, so as to obtain a preprocessed historical organ state data set whose validity and sparsity are both in a preset range. In particular, the predefined quality control rules may be non-null rules. The historical organ state data is deleted in response to a proportion of values in the historical organ state data being not less than 15%. In particular, the predefined quality control rule may also be a date rule. In particular, years may be defined as 2016-2021, months of 01-12, and days of 01-31. Wherein the maximum date is 31 when the month is 1, 3, 5, 7, 8, 10 and 12, the maximum date is 30 when the month is 4, 6, 9 and 11, the maximum date is 29 when the month is 2 and the judged year is leap year, otherwise, the maximum date is 28. The whole piece of historical organ state data which fails the date check is deleted.
And generating a historical organ state feature set based on the preprocessed historical organ state data set. Specifically, the duplicate removal and normalization processing is performed on each diagnosis name included in the pre-processing historical organ state data set to obtain a first pre-processing historical organ state data set. And carrying out normalization and structuralization processing on each test result data, examination data and physical examination sign data contained in the first preprocessed historical organ state data set to obtain a second preprocessed historical organ state data set. And according to historical experience, corresponding each second preprocessed historical organ state data in the second preprocessed historical organ state data set to the organ identification set to obtain a third preprocessed historical organ state data feature set. Specifically, the organ identification set includes a heart identification, a brain identification, a lung identification, a liver and gall identification, a pancreas identification, a kidney identification, a gastrointestinal identification, a blood system identification, a skin identification, and a bone joint identification. In particular, table 1 gives an example of a third set of pre-processed historical organ state data feature sets. One row in table 1 corresponds to one set of the third pre-processed historical organ state data characteristics, and one cell in table 1 corresponds to one set of the third pre-processed historical organ state data characteristics.
TABLE 1
Optionally, for each third pre-processed historical organ state data feature set in the third pre-processed historical organ state data feature set, the third pre-processed historical organ state data feature set is processed by using a binary classification model, so as to obtain a fourth pre-processed historical organ state feature sequence corresponding to the third pre-processed historical organ state data feature set. Specifically, the binary model may be a Light Gradient Boosting Machine (LightGBM). Specifically, a first number of fourth pre-processed historical organ state features before the fourth pre-processed historical organ state feature sequence can be selected according to historical experience to generate a historical organ state feature set, so as to obtain a historical organ state feature set. In particular, table 2 gives an example of a set of historical organ state features. One row in table 2 corresponds to one set of historical organ state features, and one cell in table 2 corresponds to one set of historical organ state features.
TABLE 2
And generating a first evaluation template set and a second evaluation template set based on the historical organ state feature set and a predetermined evaluation model. Wherein the predetermined evaluation model comprises a first number of pre-trained regression models that generate an output using the following equation:
where, logic () is the regression function, p is the regression probability, x is the feature data set of the input regression model, x = { x = { (x) } 0 ,x 1 ,...,x n X is the characteristic data in x, i is the count, n is the total number of the characteristic data in x, x 0 Is the first feature data in x, x 1 Is the second feature data in x, x n N +1 th feature data in x, y is regression index, ω is weight vector, ω = { ω = { [ ω ]) 0 ,ω 1 ,...,ω n }，ω 0 Is the first weight in ω, ω 1 Is the second weight in ω, ω n Is the n +1 th weight in ω, and φ () is the output function, φ (ω) T x) is the output of the regression model. The first number of pre-trained regression models corresponds to a first number of pre-determined assessment categories.
Optionally, the predetermined first evaluation template set is obtained by the following step one.
The method comprises the following steps: a first set of evaluation templates is generated.
The method comprises the steps of firstly, obtaining a predetermined evaluation category index set, wherein the evaluation category index set comprises a first number of evaluation category index sets. Specifically, the evaluation category index set may correspond to evaluation category index information of one organ identifier. The set of assessment category indicators may be predetermined based on historical diagnostic conditions.
And secondly, for each predetermined evaluation category index set in the predetermined evaluation category index set, determining a reference index set and a risk index set of the predetermined evaluation category index set to obtain a reference index set and a risk index set. In particular, the reference index set may correspond to a risk profile reference value for an organ identity, and the reference index set may be predetermined based on historical diagnostic profiles. The set of risk indicators may correspond to extreme severity of risk reference values for an organ identity, and the set of risk indicators may be predetermined based on historical diagnosis.
And thirdly, for each predetermined evaluation category index set in the predetermined evaluation category index set, generating a first evaluation template of the predetermined evaluation category index set according to the historical organ state data set, the reference index set of the predetermined evaluation category index set and the risk index set of the predetermined evaluation category index set to obtain a first evaluation template set. And the elements in the first evaluation template are arrays consisting of element values, categories, risk scores and first evaluation result values. Specifically, for each predetermined evaluation category index set in the predetermined evaluation category index set, a distance between each piece of historical organ state data in the historical organ state data set and the predetermined evaluation category index set and a risk index set corresponding to the predetermined evaluation category index set is calculated, and a first evaluation template is generated to obtain a first evaluation template set. In particular, table 3 gives an example of a first evaluation template. In table 3, for the element values whose category is "age" has a value range of "31 to 40", the risk score is determined to be "2".
TABLE 3
Optionally, the predetermined second evaluation template set is obtained by the following step two.
Step two: a predetermined second set of evaluation templates is generated.
A first step of, for each first evaluation template in the first evaluation template set, generating first evaluation data of the first evaluation template by using the following formula to obtain a first evaluation data set:
wherein i is a cycle count, X is an element value of an element in the first evaluation template, k is a number of elements in the first evaluation template,
is the first evaluation data, beta is the risk score corresponding to the element in the first evaluation template, beta i A risk score, X, for the ith element in the first assessment template i Is the element value of the ith element in the first evaluation template.
In a second step, a second evaluation score sequence is determined. Specifically, the first evaluation data in the first evaluation data set are sorted from large to small, and the sorted result is determined as a second evaluation score sequence.
And thirdly, generating a predetermined second evaluation template set according to the second evaluation score sequence and the first evaluation data set. Specifically, table 4 gives an example of a second evaluation template.
| Scoring | Probability of |
| 0 | 0.00 |
| 1 | 0.00 |
| 2 | 0.01 |
| 3 | 0.01 |
| 4 | 0.01 |
| 5 | 0.02 |
| 6 | 0.04 |
| 7 | 0.05 |
| 8 | 0.05 |
| 9 | 0.07 |
| 10 | 0.09 |
| 11 | 0.10 |
| 12 | 0.15 |
| 13 | 0.20 |
| 14 | 0.25 |
| 15 | 0.31 |
TABLE 4
In some optional implementations of some embodiments, the processor generates the set of assessment scores using the set of organ state data and a predetermined first set of assessment templates. And performing filling and scoring on the organ state data set of the user according to a first evaluation template set determined in advance to obtain an evaluation score set. Specifically, the "age" of the organ status data in the organ status data set may be 55, and an evaluation score of 4 may be obtained according to the predetermined first evaluation template set illustrated in table 3. The organ status data "body mass index" in the organ status data set may be 30, and an evaluation score of 3 may be obtained according to the predetermined first evaluation template exemplified in table 3. And generating an evaluation result set according to the evaluation score set and a second predetermined evaluation template set. And matching the evaluation score data set with a second evaluation template set determined in advance to obtain an evaluation result set. Specifically, according to the predetermined second evaluation template illustrated in table 4, the probability value corresponding to the evaluation score of 4 is 0.01, and the probability value corresponding to the evaluation score of 3 is 0.01. And summing all probability values generated after the evaluation score set is matched with the corresponding predetermined second evaluation template to generate an evaluation result so as to obtain an evaluation result set. And sending the evaluation result set to the prepositive equipment.
Optional contents in the above step 302, namely: the invention discloses a method for generating a first evaluation template set and a second evaluation template set by using a predetermined evaluation model, which is used as an invention point of an embodiment of the disclosure, and solves the technical problems mentioned in the background technology. In addition, the neural network model is a black box model, so that the interpretability is poor and the user acceptance is low. ". Factors that lead to poor application of neural network models tend to be as follows: the neural network model has complex structure, large parameter quantity, poor interpretability and very low operation efficiency, and consumes huge computing resources. If the above factors are solved, the effect of improving the application level of the model can be achieved. To achieve this, the present disclosure introduces a first number of pre-trained regression models to construct a predetermined evaluation model. The regression model is a linear model in nature, the number of parameters is small, the interpretability is strong, the model structure is simple, the parameter quantity is small, and resources are greatly saved. By calling the evaluation model constructed by using the regression model, the training time is short, the resource requirement is low, and the interpretability of the output result is strong, so that the application level of the model is improved, and the technical problem II is solved.
In some embodiments, the front-end device of the execution subject displays the evaluation result set, and transmits evaluation start information input by a user to the processor. Specifically, the front-end device may be a computer, and the front-end device may also be a mobile phone.
And step 304, the processor is further configured to, for each evaluation result in the evaluation result set, in response to the evaluation result being greater than the alarm threshold, control the front-end device to send out alarm prompt information.
In some embodiments, the processor of the execution subject is further configured to, for each evaluation result in the evaluation result set, control the front-end device to issue an alarm prompt message in response to the evaluation result being greater than an alarm threshold. Wherein the alarm prompt information represents that the organ state is abnormal.
Optionally, the processor is further configured to, for each evaluation result in the evaluation result set, control the front-end device to display the evaluation result in response to the evaluation result not being greater than the alarm threshold.
One embodiment presented in fig. 3 has the following beneficial effects: the data sensor is used for acquiring an organ state data set of a user and acquiring an alarm threshold; a processor to generate a set of evaluation scores; generating an evaluation result set; sending the evaluation result set to the prepositive equipment; the front-end equipment displays the evaluation result set and sends the evaluation starting information input by the user to the processor; and the processor is also used for responding to each evaluation result in the evaluation result set and sending out alarm prompt information by the front-end equipment in response to the fact that the evaluation result is larger than the alarm threshold value. The processor of the embodiment automatically generates the health condition evaluation result set of the user represented by the sensory state data set of the user acquired by the data sensor by using the predetermined first evaluation template set and the second evaluation template set, so that the health condition evaluation time is shortened, and the consumed evaluation resources are saved.
With continued reference to FIG. 4, a flowchart 400 of one embodiment of the training steps for evaluating a model according to the present disclosure is shown. The training step may include the steps of:
In some embodiments, the subject of execution of the training step may be the same as or different from the subject of execution of the user representation system based on organ state data (e.g., the processor shown in FIG. 1). If the two parameters are the same, the executing agent of the training step may store the model structure information and the parameter values of the model parameters of the trained evaluation model locally after the evaluation model is trained. If not, the executing agent of the training step may send the model structure information and the parameter values of the model parameters of the trained evaluation model to the executing agent of the user representation system based on the organ state data after the evaluation model is trained.
In some embodiments, the agent performing the training step may obtain the sample set locally or remotely from other terminal devices networked with the agent. Wherein the samples in the sample set include a sample feature dataset and a sample evaluation category corresponding to the sample feature dataset. Specifically, the sample set may be generated according to the historical organ state feature set, and in addition, each historical organ state feature set in the historical organ state feature set needs to be manually labeled in a category manner in advance to obtain the sample set.
In some embodiments, the performing agent of this training step may first determine the model structure of the initial assessment model. In particular, the initial evaluation model may include a first number of pre-trained regression models. The regression model is a linear model in nature, the model structure is simple, the parameter quantity is small, and the regression process can be observed, and is not a black box model.
In some embodiments, the subject performing the training step trains the evaluation model by using the feature data set included in the samples in the sample set as an input of the initial evaluation model and using the evaluation category of the pre-obtained samples corresponding to the input feature data set as an expected output of the initial evaluation model.
Specifically, the feature data set of the selected sample is input to the initial evaluation model, and the evaluation category of the selected sample is obtained. The feature data set of the selected sample is compared to the corresponding sample evaluation category. And determining whether the initial evaluation model reaches a preset optimization target according to the comparison result. Specifically, the optimization goal may be less than a predetermined threshold, or the optimization goal may be reaching a predetermined number of iterations. In response to determining that the initial evaluation model meets the optimization goal, determining the initial evaluation model as an evaluation model.
In response to determining that the initial evaluation model is not trained, adjusting relevant parameters in the initial evaluation model, and reselecting a sample from the sample set, using the adjusted initial evaluation model as the initial evaluation model, and performing the training step again.
One embodiment given in fig. 4 has the following beneficial effects: by training the evaluation model in the execution subject, the evaluation model composed of the regression model can be obtained, the training pressure is low, the resource consumption is saved, the training process is visible, and the model training level is improved.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use in implementing a terminal device of an embodiment of the present disclosure. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 506 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM503 are connected to each other through a bus 504. An Input/Output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: a storage section 506 including a hard disk and the like; and a communication section 507 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 507 performs communication processing via a network such as the internet. The driver 508 is also connected to the I/O interface 505 as necessary. A removable medium 509 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 508 as necessary so that the computer program read out therefrom is mounted into the storage section 506 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 507 and/or installed from the removable medium 509. The above-described functions defined in the method of the present disclosure are performed when the computer program is executed by a Central Processing Unit (CPU) 501. It should be noted that the computer readable medium in the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the C language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept as defined above. For example, the above features and the technical features disclosed in the present disclosure (but not limited to) having similar functions are replaced with each other to form the technical solution.
Claims (10)
1. A user representation system based on organ state data, comprising:
the data sensor is used for acquiring an organ state data set of a user and acquiring an alarm threshold;
a processor for generating a set of assessment scores using the set of organ state data and a predetermined first set of assessment templates; generating an evaluation result set according to the evaluation score set and a predetermined second evaluation template set; sending the evaluation result set to a front-end device;
the front-end equipment displays the evaluation result set and sends evaluation starting information input by a user to the processor;
the processor is further configured to, for each evaluation result in the evaluation result set, in response to the evaluation result being greater than the alarm threshold, control the front-end device to send out alarm prompt information, where the alarm prompt information indicates that the organ state is abnormal.
2. The method of claim 1, wherein the processor is further configured to:
for each evaluation result in the evaluation result set, in response to the evaluation result not being greater than the alarm threshold, controlling the front-end device to display the evaluation result.
3. The method of claim 2, wherein the set of assessment scores comprises a first number of assessment scores for characterizing assessment information of a particular organ, the set of assessment results comprises a first number of assessment results, the assessment results characterizing an organ state, the set of assessment results characterizing an organ state representation of the user.
4. The method of any of claims 1-3, wherein the processor, prior to generating the set of assessment scores using the set of organ state data and the predetermined set of first assessment templates, is further configured to:
acquiring a historical organ state data set;
preprocessing the historical organ state data set to obtain a preprocessed historical organ state data set;
generating a historical organ state feature set based on the preprocessed historical organ state data set;
generating the first evaluation template set and the second evaluation template set based on the historical organ state feature set and a predetermined evaluation model.
5. The method of claim 4, wherein the predetermined evaluation model comprises a first number of pre-trained regression models that generate an output using the equation:
where, logic () is a regression function, p is a regression probability, x is a feature data set input to the regression model, and x = { x = { (x) } 0 ,x 1 ,...,x n X is the characteristic data in x, i is the count, n is the total number of the characteristic data in x, x 0 Is the first feature data in x, x 1 Is the second feature data in x, x n N +1 th feature data in x, y is regression index, ω is weight vector, ω = { ω = { [ ω ]) 0 ,ω 1 ,...,ω n }，ω 0 Is the first weight in ω, ω 1 Is the second weight in ω, ω n Is the n +1 th weight in ω, φ () is an output function, φ (ω) T x) is the output of the regression model.
6. The method of claim 5, wherein the first number of pre-trained regression models corresponds to a first number of pre-determined assessment categories.
7. The method of claim 6, wherein the pre-trained evaluation model is obtained by:
determining a model structure of an initial evaluation model and initializing model parameters of the initial evaluation model;
obtaining a sample set, wherein samples in the sample set comprise a sample feature data set and a sample evaluation category corresponding to the sample feature data set;
selecting samples from the sample set, and performing the following training steps:
inputting a sample characteristic data set of the selected sample into an initial evaluation model to obtain an evaluation category of the sample;
comparing the evaluation category of the selected sample with the corresponding sample evaluation category;
determining whether the initial evaluation model is trained according to the comparison result;
in response to determining that training of an initial assessment model is complete, determining the initial assessment model as a pre-trained assessment model.
8. The method of any of claims 1-7, wherein the processor is further configured to:
in response to determining that the initial evaluation model is not trained, adjusting relevant parameters in the initial evaluation model, and reselecting samples from the sample set, continuing to perform the training step using the adjusted initial evaluation model as the initial evaluation model.
9. The method of claim 8, wherein the predetermined first set of assessment templates is obtained by:
acquiring a predetermined evaluation category index set, wherein the evaluation category index set comprises a first number of evaluation category index sets;
for each predetermined evaluation category index set in the predetermined evaluation category index set, determining a reference index set and a risk index set of the predetermined evaluation category index set to obtain a reference index set and a risk index set;
for each predetermined evaluation category index set in the predetermined evaluation category index set, generating a first evaluation template of the predetermined evaluation category index set according to the historical organ state data set, the reference index set of the predetermined evaluation category index set and the risk index set of the predetermined evaluation category index set to obtain the first evaluation template set, wherein elements in the first evaluation template are an array consisting of element values, categories, risk scores and first evaluation result values.
10. The method of claim 9, wherein the predetermined second set of assessment templates is obtained by:
for each first evaluation template in the first evaluation template set, generating first evaluation data for the first evaluation template using the following formula to obtain a first evaluation data set:
wherein i is a cycle count, X is an element value of an element in the first evaluation template, k is a number of elements in the first evaluation template,
for the first evaluation data, β is the risk score corresponding to the element in the first evaluation template, β i A risk score, X, for the ith element in the first evaluation template i The element value of the ith element in the first evaluation template;
determining a second evaluation score sequence;
generating the predetermined second evaluation template set according to the second evaluation score sequence and the first evaluation data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142369.2A CN115881297A (en) | 2021-09-28 | 2021-09-28 | User portrait system based on organ state data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142369.2A CN115881297A (en) | 2021-09-28 | 2021-09-28 | User portrait system based on organ state data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115881297A true CN115881297A (en) | 2023-03-31 |
Family
ID=85763414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111142369.2A Pending CN115881297A (en) | 2021-09-28 | 2021-09-28 | User portrait system based on organ state data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115881297A (en) |
-
2021
- 2021-09-28 CN CN202111142369.2A patent/CN115881297A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112071425B (en) | Data processing method and device, computer equipment and storage medium | |
| CN111915584A (en) | Focus follow-up assessment method and system based on CT (computed tomography) image | |
| CN111008957A (en) | Medical information processing method and device | |
| CN111956214A (en) | QRS wave automatic detection method based on U-net end-to-end neural network model | |
| CN111291131A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN113488167A (en) | Intelligent medical information optimization method applied to big data and intelligent medical server | |
| CN114730392A (en) | Analysis device, analysis method, and analysis program | |
| CN113360611A (en) | AI diagnosis method, device, storage medium and equipment based on inspection result | |
| KR102033484B1 (en) | Method and apparatus for setting normal reference range in clinical inspection of pets using generative adversary network | |
| CN111657921A (en) | Real-time electrocardio abnormality monitoring method and device, computer equipment and storage medium | |
| CN115526882A (en) | Medical image classification method, device, equipment and storage medium | |
| CN115881297A (en) | User portrait system based on organ state data | |
| CN113780457B (en) | Abnormality detection method, device, equipment and medium for traditional Chinese medicine resource consumption | |
| CN113017634B (en) | Emotion evaluation method, emotion evaluation device, electronic device, and computer-readable storage medium | |
| CN115240843A (en) | Fairness prediction system based on structure causal model | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN113782192A (en) | Grouping model construction method based on causal inference and medical data processing method | |
| CN111915553A (en) | Part identification method and device based on time sequence modeling | |
| CN115831356B (en) | Auxiliary prediction diagnosis method based on artificial intelligence algorithm | |
| CN110889836A (en) | Image data analysis method and device, terminal equipment and storage medium | |
| CN115114950B (en) | Method, device and equipment for testing decision uncertainty | |
| US20240062907A1 (en) | Predicting an animal health result from laboratory test monitoring | |
| CN117116476B (en) | Downstream task prediction method and device and computer readable storage medium | |
| US20220310259A1 (en) | System And Method For Determning Status Of Health Of Animals Arriving At A Feed Location | |
| US20230238139A1 (en) | Method and system for diagnostic analyzing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |