Method and system for managing infusion based on artificial intelligence

Abstract

The invention belongs to the field of intelligent medical care, and discloses a method and system for managing infusion based on artificial intelligence. According to the invention, the infusion tube data, the infusion tube monitoring image data, the patient information feature data and the infusion reminding level are utilized to construct the multi-mode infusion management model; the constructed multi-mode infusion management model generates a current infusion reminding level for medical personnel in the infusion process of a patient according to real-time infusion tube data, real-time infusion tube monitoring image data and real-time patient information feature data which are received by a medical station and collected by each piece of medical equipment; the current infusion reminding level is sent to a screen of a nurse station and handheld terminal equipment, medical staff are reminded to go to a corresponding ward to withdraw a needle in time, transmission of infusion reminding level information is stopped, and accurate infusion nursing is achieved. According to the intelligent infusion monitoring system, infusion of infusion patients in all wards can be monitored in real time by medical staff, the intelligent infusion monitoring effect is achieved, the work intensity of ward patrol of the medical staff is reduced, and the doctor-patient contradiction is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent medical care technology, and in particular relates to a method and system for managing infusion based on artificial intelligence. Background Art

[0002] According to a survey by the National Health Commission in 2023, 90% of hospitalized patients require infusion treatment, of which 50% have no bedside companion, 22% of infusion patients are children, 26% of them have doctor-patient conflicts during infusion, and the average infusion time is 220 minutes per person. Clinical nurses spend 30% of their time on resolving patient infusion issues. Reducing doctor-patient conflicts during infusion, improving the safety of infusion medication, and improving patient satisfaction have become urgent issues that need to be addressed.

[0003] With existing infusion, after the liquid is infused, the nurse receives a message and then removes the needle. At the same time, during the infusion process, the patient cannot rest, and medical staff need to observe the liquid situation at all times to prevent the situation where the liquid is infused and the medical staff cannot be notified in time, which causes blood to return. When medical staff observe the infusion for a long time, it is easy to cause visual fatigue and increase mental stress for medical staff. In addition, during the infusion, medical staff will increase the frequency of bed inspections. A department is calculated based on 50 patients, and inspecting a patient for one minute, which takes 50 minutes. By the end of the infusion of the entire ward, the nurse has trained the bed no less than 3 times. In addition, each patient notifies the termination of the infusion and the removal of the needle. This workload is very large and time-consuming and labor-intensive. Such high-intensity work brings great mental and physical exhaustion.

[0004] For some patients with limited mobility or the elderly, nursing staff are needed to monitor the infusion during the infusion and notify the nurse as soon as the infusion is completed, which greatly increases labor costs. Because there are too many patients receiving infusions, the bells at the nurse station ring one after another after the infusion is completed, which also affects the patients' rest.

[0005] The following infusion management methods exist in the prior art. The first type of infusion monitoring is a stand-alone version that cannot be connected to the Internet. That is, after the liquid is infused, there is a dripping sound, but it is only limited to use in the ward, which affects the rest of other patients in the room. The nurse cannot receive the infusion completion signal and still needs to be manually notified to change the liquid or terminate the infusion. The second type of traditional weighing infusion alarm device cannot accurately alarm immediately after the liquid is injected, and the operation is complicated. A large number of parameters need to be entered before use. Since the weight of the infusion bottle or infusion bag generated by each manufacturer is different, it will cause misreporting and omissions. In addition, the interconnected terminal screen cannot reflect whether there is a prompt for whether the patient is allergic to the drug, and display the power of the device, etc.

[0006] Therefore, there is an urgent need for a method and system for managing infusion based on artificial intelligence, which can reduce the frequency of nurses' bed rounds, reduce the workload of medical staff, accurately identify infusion conditions, interconnect with medical station terminals, correctly alarm the infusion conditions in the ward, and promptly remind medical staff to remove needles, thereby reducing the occurrence of medical conflicts. Summary of the invention

[0007] In order to solve the above technical problems, the present invention proposes a method and system for managing infusion based on artificial intelligence.

[0008] In a first aspect of the present invention, a method for managing infusion based on artificial intelligence is provided, characterized in that the method comprises:

[0009] Acquire first infusion tube data and first infusion tube monitoring image data of the infusion tube, first patient information feature data of the patient, and a first infusion reminder level;

[0010] A first infusion management vector feature composed of the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data;

[0011] constructing a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level;

[0012] Receive the second infusion tube data and the second infusion tube monitoring image data of the infusion tube and the second patient information feature data of the patient, generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data and the second patient information feature data, use the multimodal infusion management model to process the second infusion management vector feature to generate a second infusion reminder level, and remind medical staff to perform infusion care according to the second infusion reminder level.

[0013] Furthermore, the first infusion tube data or the second infusion tube data uses an infusion monitor infrared probe stuck on the upper end of the infusion tube drip pot to check the liquid in the infusion tube. The first infusion tube data or the second infusion tube data is specifically the height of the first liquid to be infused or the height of the second liquid to be infused detected by the infrared probe with the upper end of the infusion tube drip pot as the origin.

[0014] Further, the first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image;

[0015] The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

[0016] Furthermore, before constructing or utilizing the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts, and the threshold variance R between the target feature parts and the non-target feature parts is defined.

[0017] Furthermore, the mean of the sum of the image feature grayscale values ​​greater than the threshold variance R in the first infusion tube monitoring image data or the second infusion tube monitoring image data is used as the first target feature value or the second target feature value.

[0018] Furthermore, the first height of the liquid to be infused, the first target characteristic value and the first patient information characteristic data are bonded together to obtain a first infusion management vector characteristic, and the second height of the liquid to be infused, the second target characteristic value and the second patient information characteristic data are bonded together to obtain a second infusion management vector characteristic.

[0019] Furthermore, the multimodal infusion management model adopts an improved Fisher criterion-based classifier.

[0020] A system for managing infusion based on artificial intelligence is also provided, the system comprising an infusion monitor module, a ward infusion tube monitoring module, a nurse station patient information storage module, a nurse station image processing module, a multimodal infusion management model building module, and an infusion reminder module, characterized in that:

[0021] The infusion monitor module is used to collect and obtain the first infusion tube data of the infusion tube, and is also used to obtain the second infusion tube data of the infusion tube;

[0022] The ward infusion tube monitoring module is used to collect and obtain the first infusion tube monitoring image data of the infusion tube, and is also used to obtain the second infusion tube monitoring image data of the infusion tube;

[0023] The patient information storage module of the nurse station is used to receive the first patient information feature of the patient, the second patient information feature of the patient, the first infusion reminder level, and the second infusion management vector feature and the second infusion reminder level;

[0024] The nurse station image processing module is used to generate a first infusion management vector feature based on the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data, and is also used to generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data, and the second patient information feature data;

[0025] The multimodal infusion management model construction module receives the first infusion management vector feature from the nurse station image processing module, and constructs a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level;

[0026] The infusion reminder module receives the second infusion management vector feature, calls the multimodal infusion management model in the multimodal infusion management model construction module, processes to obtain the second infusion reminder level, and sends the second infusion reminder level to the large screen of the nurse station and the display screen of the medical staff's handheld device for reminder.

[0027] Further, the first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image;

[0028] The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

[0029] Furthermore, before constructing or utilizing the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts, and the threshold variance R between the target feature parts and the non-target feature parts is defined.

[0030] The method and system for managing infusion based on artificial intelligence of the present invention are different from the traditional method of processing by combining the weight of the infusion tube with the image. The present invention uses the infusion liquid level height in combination with the infusion liquid image feature value obtained after processing and combines the patient's characteristic information to determine the infusion reminder level. The improved machine learning algorithm is used to make the infusion reminder of the infusion tube in a specific application scenario more accurate, and the image feature difference between the drip pot and the infusion bag is considered for weight distribution, ignoring the inaccurate infusion monitoring caused by the different sizes of infusion bags caused by different manufacturers, so as to meet the medical staff's real-time monitoring of the infusion of the infusion patients in each ward, realize the intelligent infusion monitoring effect, reduce the work intensity of the medical staff's ward rounds, and reduce the doctor-patient conflicts, so as to reduce the frequency of nurses' bed rounds, reduce the work intensity of the medical staff, accurately identify the infusion situation, interconnect with the medical station terminal, correctly alarm the infusion situation of the ward, and promptly remind the medical staff to remove the needle, thereby reducing the occurrence of medical conflicts. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of a method for managing infusion based on artificial intelligence of the present invention;

[0032] Figure 2This is a schematic diagram of the structure of an artificial intelligence-based infusion management system of the present invention;

[0033] Figure 3 It is a classification principle diagram of the classifier based on Fisher's criterion in the present invention;

[0034] Figure 4 This is a target characteristic part diagram of the infusion tube in an embodiment of the present invention;

[0035] Among them, 1 represents an infusion bag, and 2 represents a drip pot;

[0036] Figure 5 This is a schematic diagram of infusion monitoring in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0038] The first embodiment of the present invention:

[0039] In a first aspect of the present invention, in order to solve the above technical problems, a method for managing infusion based on artificial intelligence is provided, characterized in that the method comprises:

[0040] Acquire first infusion tube data and first infusion tube monitoring image data of the infusion tube, first patient information feature data of the patient, and a first infusion reminder level;

[0041] A first infusion management vector feature composed of the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data;

[0042] constructing a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level;

[0043] Receive the second infusion tube data and the second infusion tube monitoring image data of the infusion tube and the second patient information feature data of the patient, generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data and the second patient information feature data, use the multimodal infusion management model to process the second infusion management vector feature to generate a second infusion reminder level, and remind medical staff to perform infusion care according to the second infusion reminder level.

[0044] In this embodiment, the first infusion reminder level and the second infusion reminder level include a vector representation of the remaining infusion time and the reminder signal. For example, the infusion reminder level vector L (0, 600, 0) indicates the primary infusion reminder level, and there are 600 seconds left for the infusion tube to be completed, no countdown is performed, and a level 0 signal green signal is sent to the nurse station large screen and mobile terminal device. For example, the infusion reminder level vector L (-1, 60, 1) indicates the intermediate infusion reminder level, and there are 60 seconds left for the infusion tube to be completed, a 60-second countdown is performed, and a level 1 signal yellow signal is sent to the nurse station large screen and mobile terminal device. The infusion reminder level vector L can be set according to the needs of the technician. For example, the infusion reminder level vector L (1, 30, 2) indicates the advanced infusion reminder level, and there are 30 seconds left for the infusion tube to be completed, a 30-second countdown is performed, and a level 2 signal red signal is sent to the nurse station large screen and mobile terminal device. The infusion reminder level vector L can be set according to the needs of the technician.

[0045] Furthermore, the first infusion tube data or the second infusion tube data uses an infusion monitor infrared probe stuck on the upper end of the infusion tube drip pot to check the liquid in the infusion tube. The first infusion tube data or the second infusion tube data is specifically the height of the first liquid to be infused or the height of the second liquid to be infused detected by the infrared probe with the upper end of the infusion tube drip pot as the origin.

[0046] Further, the first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image;

[0047] The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

[0048] Furthermore, before constructing or using the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts. The threshold variance R between the target feature parts and the non-target feature parts is defined as:

[0049]

[0050] In the formula, t1 is the ratio of the grayscale value of the target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t2 is the ratio of the grayscale value of the non-target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t3 is the ratio of the grayscale value of the target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, t4 is the ratio of the grayscale value of the non-target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, G is the total average grayscale of the infusion bag image, G0 is the average grayscale of the target feature part of the infusion bag image, G1 is the average grayscale of the non-target feature part of the infusion bag image, A is the total average grayscale of the dripping pot image, A0 is the average grayscale of the target feature part of the dripping pot image, A1 is the average grayscale of the non-target feature part of the dripping pot image, and k1 and k2 are weight coefficients.

[0051] Furthermore, the mean of the sum of the image feature grayscale values ​​greater than the threshold variance R in the first infusion tube monitoring image data or the second infusion tube monitoring image data is used as the first target feature value or the second target feature value.

[0052] Furthermore, the first height of the liquid to be infused, the first target characteristic value and the first patient information characteristic data are bonded together to obtain a first infusion management vector characteristic, and the second height of the liquid to be infused, the second target characteristic value and the second patient information characteristic data are bonded together to obtain a second infusion management vector characteristic.

[0053] Furthermore, the multimodal infusion management model adopts an improved Fisher criterion-based classifier, and the calculation formula is as follows:

[0054]

[0055] Where X is the input infusion management vector feature, g(X) is the output infusion reminder level, and W T is the normal vector perpendicular to the hyperplane, t1 is the ratio of the grayscale value of the target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t2 is the ratio of the grayscale value of the non-target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t3 is the ratio of the grayscale value of the target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, t4 is the ratio of the grayscale value of the non-target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, k1 and k2 are weight coefficients, k1+k2=1.

[0056] In this embodiment, the value of g(X) is used to output the infusion reminder level L. If the value of g(X) is less than 0, the intermediate infusion reminder level is output; if it is equal to 0, the primary infusion reminder level is output; if it is greater than 0, the advanced infusion reminder level is output. The value of g(X) is the product of the characteristic vectors in the output infusion reminder level vector L.

[0057] A system for managing infusion based on artificial intelligence is also provided, the system comprising an infusion monitor module, a ward infusion tube monitoring module, a nurse station patient information storage module, a nurse station image processing module, a multimodal infusion management model building module, and an infusion reminder module, characterized in that:

[0058] The infusion monitor module is used to collect and obtain the first infusion tube data of the infusion tube, and is also used to obtain the second infusion tube data of the infusion tube;

[0059] The ward infusion tube monitoring module is used to collect and obtain the first infusion tube monitoring image data of the infusion tube, and is also used to obtain the second infusion tube monitoring image data of the infusion tube;

[0060] The patient information storage module of the nurse station is used to receive the first patient information feature of the patient, the second patient information feature of the patient, the first infusion reminder level, and the second infusion management vector feature and the second infusion reminder level;

[0061] The nurse station image processing module is used to generate a first infusion management vector feature based on the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data, and is also used to generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data, and the second patient information feature data;

[0062] The multimodal infusion management model construction module receives the first infusion management vector feature from the nurse station image processing module, and constructs a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level;

[0063] The infusion reminder module receives the second infusion management vector feature, calls the multimodal infusion management model in the multimodal infusion management model construction module, processes to obtain the second infusion reminder level, and sends the second infusion reminder level to the large screen of the nurse station and the display screen of the medical staff's handheld device for reminder.

[0064] Further, the first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image;

[0065] The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

[0066] Furthermore, before constructing or using the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts. The threshold variance R between the target feature parts and the non-target feature parts is defined as:

[0067]

[0068] In the formula, t1 is the ratio of the grayscale value of the target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t2 is the ratio of the grayscale value of the non-target feature part of the infusion bag image to the overall grayscale value of the infusion bag image, t3 is the ratio of the grayscale value of the target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, t4 is the ratio of the grayscale value of the non-target feature part of the dripping pot image to the overall grayscale value of the dripping pot image, G is the total average grayscale of the infusion bag image, G0 is the average grayscale of the target feature part of the infusion bag image, G1 is the average grayscale of the non-target feature part of the infusion bag image, A is the total average grayscale of the dripping pot image, A0 is the average grayscale of the target feature part of the dripping pot image, A1 is the average grayscale of the non-target feature part of the dripping pot image, and k1 and k2 are weight coefficients.

[0069] The method and system for managing infusion based on artificial intelligence of the present invention are different from the traditional method of processing by combining the weight of the infusion tube with the image. The present invention uses the infusion liquid level height in combination with the infusion liquid image feature value obtained after processing and combines the patient's characteristic information to determine the infusion reminder level. The improved machine learning algorithm is used to make the infusion reminder of the infusion tube in a specific application scenario more accurate, and the weight distribution is performed considering the image feature difference between the drip pot and the infusion bag, which satisfies the medical staff's real-time monitoring of the infusion of the infusion patients in each ward, realizes the intelligent infusion monitoring effect, reduces the work intensity of the medical staff's ward rounds, and reduces the doctor-patient conflicts, thereby reducing the frequency of nurses' bed rounds, reducing the work intensity of the medical staff, accurately identifying the infusion situation, interconnecting with the medical station terminal, correctly alarming the infusion situation in the ward, and promptly reminding the medical staff to remove the needle, reducing the occurrence of medical conflicts.

[0070] A combination of multiple embodiments of the present invention can achieve all of the above effects, but it is not required that each embodiment of the present invention achieve all of the above advantages and effects, because each embodiment of the present invention can constitute an independent technical solution and make one or more contributions to the prior art.

[0071] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for managing infusion based on artificial intelligence, characterized in that: The method comprises: Acquire first infusion tube data and first infusion tube monitoring image data of the infusion tube, first patient information feature data of the patient, and a first infusion reminder level; A first infusion management vector feature composed of the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data; constructing a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level; Receive the second infusion tube data and the second infusion tube monitoring image data of the infusion tube and the second patient information feature data of the patient, generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data and the second patient information feature data, use the multimodal infusion management model to process the second infusion management vector feature to generate a second infusion reminder level, and remind medical staff to perform infusion care according to the second infusion reminder level.

2. The method for managing infusion based on artificial intelligence according to claim 1, characterized in that: The first infusion tube data or the second infusion tube data uses an infusion monitor infrared probe stuck on the upper end of the infusion tube drip pot to check the liquid in the infusion tube. The first infusion tube data or the second infusion tube data is specifically the height of the first liquid to be infused or the height of the second liquid to be infused detected by the infrared probe with the upper end of the infusion tube drip pot as the origin.

3. The method for managing infusion based on artificial intelligence according to claim 1, characterized in that: The first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image; The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

4. The method for managing infusion based on artificial intelligence as claimed in claim 3, characterized in that: Before constructing or using the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts, and the threshold variance R between the target feature parts and the non-target feature parts is defined.

5. The method for managing infusion based on artificial intelligence as claimed in claim 4, characterized in that: The mean value of the sum of the image feature grayscale values ​​greater than the threshold variance R in the first infusion tube monitoring image data or the second infusion tube monitoring image data is used as the first target feature value or the second target feature value.

6. The method for managing infusion based on artificial intelligence according to claim 5, characterized in that: The first height of the liquid to be infused, the first target characteristic value and the first patient information characteristic data are bonded to obtain the first infusion management vector feature, and the second height of the liquid to be infused, the second target characteristic value and the second patient information characteristic data are bonded to obtain the second infusion management vector feature.

7. The method for managing infusion based on artificial intelligence according to claim 6, characterized in that: The multimodal infusion management model adopts an improved classifier based on Fisher's criterion.

8. An artificial intelligence-based infusion management system, the system comprising an infusion monitor module, a ward infusion tube monitoring module, a nurse station patient information storage module, a nurse station image processing module, a multimodal infusion management model construction module, and an infusion reminder module, characterized in that: The infusion monitor module is used to collect and obtain the first infusion tube data of the infusion tube, and is also used to obtain the second infusion tube data of the infusion tube; The ward infusion tube monitoring module is used to collect and obtain the first infusion tube monitoring image data of the infusion tube, and is also used to obtain the second infusion tube monitoring image data of the infusion tube; The patient information storage module of the nurse station is used to receive the first patient information feature of the patient, the second patient information feature of the patient, the first infusion reminder level, and the second infusion management vector feature and the second infusion reminder level; The nurse station image processing module is used to generate a first infusion management vector feature based on the first infusion tube data, the first infusion tube monitoring image data, and the first patient information feature data, and is also used to generate a second infusion management vector feature based on the second infusion tube data, the second infusion tube monitoring image data, and the second patient information feature data; The multimodal infusion management model construction module receives the first infusion management vector feature from the nurse station image processing module, and constructs a multimodal infusion management model by using the first infusion management vector feature and the first infusion reminder level; The infusion reminder module receives the second infusion management vector feature, calls the multimodal infusion management model in the multimodal infusion management model construction module, processes to obtain the second infusion reminder level, and sends the second infusion reminder level to the large screen of the nurse station and the display screen of the medical staff's handheld device for reminder.

9. The artificial intelligence-based infusion management system according to claim 8, characterized in that: The first infusion tube monitoring image data or the second infusion tube monitoring image data includes an infusion bag image and a drip pot image; The first patient information characteristic data of the patient or the second patient information characteristic data of the patient includes the severity of the patient's illness and the age of the patient.

10. The artificial intelligence-based infusion management system according to claim 9, characterized in that: Before constructing or using the multimodal infusion management model, target feature processing is performed on the infusion bag image and the drip pot image of the first infusion tube monitoring image data or the second infusion tube monitoring image data to separate the target feature parts from the non-target feature parts, and the threshold variance R between the target feature parts and the non-target feature parts is defined.

Images