A patient behavior map generation intervention method and system based on image recognition

Abstract

The application provides a patient behavior atlas generation intervention method and system based on image recognition, and belongs to the technical field of image processing, and specifically comprises the following steps: based on the image analysis strategy of the examination item of a patient, when it is determined that the image analysis strategy needs to be updated, an intervention delay patient is determined based on the image analysis strategy; based on the monitoring data of the queuing time length of the examination item of the intervention delay patient, the similarity of the queuing time length of each examination item is determined; based on the similarity of the examination item in the intervention delay patient and other examination items and the queuing time length, a delay impact item in the examination item is determined; and whether the overall update processing of the image analysis strategy of the examination item needs to be performed is determined by using the change of the delay impact item in different time periods, so that the queuing time of the patient is reduced.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and in particular relates to an intervention method and system for generating patient behavior maps based on image recognition. Background Technology

[0002] Hospital outpatient clinics experience high patient traffic, often resulting in long queues and consequently, prolonged waiting times and poor patient experiences. Existing technologies determine queue lengths by analyzing surveillance images, as illustrated in invention patent application CN202510480373.1, "A Method, Apparatus, Device, and Storage Medium for Detecting Queue Time." However, these solutions suffer from the following technical problems:

[0003] To improve patient access efficiency, analyzing the queuing data of patients' pending examinations can provide guidance on the order of these examinations, thereby significantly reducing consultation time. Therefore, how to analyze and process patient trajectories to improve the accuracy of guiding the order of examinations and minimize consultation time has become an urgent technical problem to be solved.

[0004] To address the aforementioned technical issues, this application provides a patient behavior atlas generation intervention method and system based on image recognition. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] Specifically, this application provides an intervention method for generating patient behavior maps based on image recognition, which includes:

[0007] S1 uses patient visit data to determine the examination items to be performed on patients, and uses the examination item data of patients with examination items to determine the image analysis strategy for each examination item.

[0008] S2 determines when an image analysis strategy needs to be updated based on the patient's examination items. It then identifies patients with delayed intervention in the behavioral profile based on the image analysis strategy. Based on the monitoring data of the queuing time of the examination items of the patients with delayed intervention, it determines the similarity of the queuing time of each examination item. Based on the similarity of the examination items with other examination items in the patients with delayed intervention and the queuing time, it determines the delayed items among the examination items.

[0009] S3 uses the impact of delays at different times on project changes to determine whether an overall update of the image analysis strategy for the project needs to be performed.

[0010] The beneficial effects of this invention are as follows:

[0011] Based on the similarity of examination items with other examination items in patients with delayed intervention and the queuing time, the delayed items in the examination items are identified. This allows for the determination of the impact of the identification and processing delay on the intervention accuracy of the patient's behavioral map in patients with delayed intervention due to the similarity of the examination items with other examination items and the existence of queuing time. This enables the screening of delayed items that have a significant impact on the intervention accuracy of patients with delayed intervention, and also lays the foundation for determining the image analysis strategy update processing scheme for examination items based on the changes in delayed items.

[0012] By utilizing the changes in the impact of delays on items at different time periods, it is determined whether a comprehensive update of the image analysis strategy for the examination items is needed. This avoids the technical problem of a significant impact on the accuracy of intervention in the behavioral maps of delayed patients when there are many delayed items or when the changes are drastic. By timely updating the overall image analysis strategy, the accuracy of intervention in the behavioral maps of delayed patients is ensured, and the waiting time for patients is reduced.

[0013] Furthermore, the items to be examined for the patient are determined based on the analysis results of the patient's medical records.

[0014] Furthermore, the method for determining the image analysis strategy for the inspection item is as follows:

[0015] Based on the data of patients with the stated examination items, determine the number of patients with the stated examination items to be examined.

[0016] Based on the number of examination items to be performed on patients with the aforementioned examination items, patients requiring intervention are identified among those patients with the aforementioned examination items.

[0017] Using the patients with the intervention needs, determine the image analysis strategy for the examination items.

[0018] Furthermore, determine whether a comprehensive update of the image analysis strategy for the inspection project is necessary, specifically including:

[0019] Based on the data on the delay impact of items in different time periods, the data on the delay impact of items in different time periods are determined, and based on the data on the delay impact of items, the patient data on items with delay impact in different time periods are determined;

[0020] Based on the changes in the delay-affected items, determine the change data of the delay-affected items in different time periods compared to the previous time period, and determine the delay-affected items that have changed in different time periods based on the change data.

[0021] Based on patient data on items with time delays at different time periods and the items with changing time delays, it is determined whether a comprehensive update of the image analysis strategy for the examination items is required.

[0022] It should be noted that the time period is divided according to the update processing cycle of the delayed impact items. Specifically, the time period between the update processing times of two adjacent delayed impact items is taken as the time period, that is, the time period between the beginning and end of the update processing cycle is taken as the time period.

[0023] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described patient behavior atlas generation intervention method based on image recognition when running the computer program.

[0024] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0025] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0026] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart of an intervention method for generating patient behavior maps based on image recognition;

[0028] Figure 2 This is a flowchart illustrating the method for determining the image analysis strategy for the project.

[0029] Figure 3 It is a flowchart for determining the image analysis strategy update process that needs to be performed;

[0030] Figure 4 This is a flowchart illustrating the methods for determining the impact of delays on a project.

[0031] Figure 5 It is a framework diagram of a computer system. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0033] In this application, by recognizing the patient's examination items and behavioral trajectories, and based on the detection data of the queuing time for different examination items, reminders are given to the patient, specifically outputting reminders to the patient's hospital wristband or mobile device, thereby reducing the patient's queuing time and improving the examination efficiency. Furthermore, based on the queuing time of different examination items and the distribution data of different patients, the image analysis strategy is determined, which also improves the efficiency and real-time performance of image analysis and processing for examination items.

[0034] Example 1

[0035] like Figure 1 As shown, this application provides an intervention method for generating patient behavior maps based on image recognition, specifically including:

[0036] S1 uses patient visit data to determine the examination items to be performed on patients, and uses the examination item data of patients with examination items to determine the image analysis strategy for each examination item.

[0037] Furthermore, the items to be examined for the patient are determined based on the analysis results of the patient's medical records.

[0038] Specifically, such as Figure 2 As shown, the method for determining the image analysis strategy for the inspection item is as follows:

[0039] Based on the data of patients with the stated examination items, determine the number of patients with the stated examination items to be examined.

[0040] Based on the number of examination items to be performed on patients with the aforementioned examination items, patients requiring intervention are identified among those patients with the aforementioned examination items.

[0041] Using the patients with the intervention needs, determine the image analysis strategy for the examination items.

[0042] It should be noted that the items to be inspected are those that have not yet been inspected.

[0043] It is understood that the patients requiring intervention are those who have the required number of examinations but do not meet the requirements. Since these patients have a large number of examinations to be performed, there is a high demand for recommendations on the order of examinations based on the queuing time of each examination. Therefore, they are considered as patients requiring intervention.

[0044] It should be noted that when there are newly added patients requiring intervention in different time periods within the recent preset time period for the examination item, the image analysis strategy for the examination item is determined to be real-time image analysis processing, that is, image analysis processing is performed in the area where the examination item is located at different times to determine the queuing time.

[0045] In one possible specific embodiment, if the number of patients with the examination items is more than three, then the patients with the examination items are determined to be patients requiring intervention. If there are new patients requiring intervention every five minutes in the most recent hour, then the image analysis strategy for the examination items is determined to be real-time image analysis processing. When there are new patients requiring intervention every five minutes in the most recent hour, then image analysis processing is performed in the area where the examination items are located according to a preset time period. In one possible embodiment, the preset time period is 30 seconds.

[0046] S2 determines when an image analysis strategy needs to be updated based on the patient's examination items. It then identifies patients with delayed intervention in the behavioral profile based on the image analysis strategy. Based on the monitoring data of the queuing time of the examination items of the patients with delayed intervention, it determines the similarity of the queuing time of each examination item. Based on the similarity of the examination items with other examination items in the patients with delayed intervention and the queuing time, it determines the delayed items among the examination items.

[0047] Specifically, such as Figure 3 As shown, the image analysis strategy update process needs to be determined, specifically including:

[0048] Based on the image analysis strategy of the patient's examination items, the examination items that are subject to image analysis processing in the area where the examination items are located according to a preset time period are identified and designated as delayed examination items.

[0049] Based on the composition data of the patient's delayed examination items, determine the weight value of the patient's delayed impact;

[0050] Based on the time delay impact weight values ​​for different patients, it is determined whether the image analysis strategy needs to be updated.

[0051] In one possible embodiment, the delay impact value is the percentage of the delayed examination item in the patient's scheduled examination items.

[0052] It should be noted that when the average value of the delay impact weights in different patients does not meet the requirements, the impact of delayed examination items is relatively large. Therefore, in such cases, it is determined that the image analysis strategy needs to be updated.

[0053] In one possible specific embodiment, when the average value of the delay impact weights across different patients is greater than 0.5, it is determined that an update to the image analysis strategy is required.

[0054] Furthermore, the patient with the delayed intervention is a patient whose examination items include delayed examination items.

[0055] Furthermore, the queuing time for the examination item is determined based on the time from the patient queuing to the completion of the examination.

[0056] It is understood that the similarity of the queuing time of the items to be inspected is determined based on the deviation of the queuing time of different items to be inspected at the time of image analysis processing.

[0057] Specifically, such as Figure 4 As shown, the method for determining the delay impact items in the inspection items is as follows:

[0058] Based on the similarity of the examination item with other examination items in patients with delayed intervention, the deviation of the queuing time of the examination item at the moment of image analysis and processing from the queuing time of other examination items is determined.

[0059] The moment when the deviation does not meet the requirements is taken as the moment when the queuing time of the inspection item is similar to that of other items to be inspected. The similar queuing time of the inspection item is determined by using the similar queuing time moment.

[0060] Based on the number of similar queue time items for the examination items in different patients with delayed intervention, similar queue time item data for different patients with delayed intervention is determined, and based on the similar queue time item data, it is determined whether the examination item is a delay-affecting item.

[0061] It is understood that when the inspection item is not an inspection item that undergoes image analysis processing in the area where the inspection item is located according to a preset time period, it is determined that the inspection item is not an item affected by delay.

[0062] In one possible embodiment, when the examination item is an examination item that performs image analysis processing in the area where the examination item is located according to a preset time cycle, if there are no similar queuing time items for the examination item or if the average queuing time of the examination item in different image analysis processing meets the requirements, then its queuing time is short or there are no similar queuing time items. In this case, it will not affect the guidance accuracy of the patient's behavior map. Therefore, based on this, it is determined that the examination item does not belong to the delayed impact item.

[0063] Additionally, it should be noted that when there are similar queuing time items for the examination items and the average queuing time of the examination items for different image analysis processing does not meet the requirements, the number of similar queuing time items for patients with interference delays is used as a basis to determine the proportion of the number of similar queuing time items in the examination items to be examined in the patients with interference delays, and this proportion is used as the interference influence ratio. When the interference influence ratio of patients with interference delays for the examination items does not meet the requirements, the examination item is determined to be a delayed examination item.

[0064] In one specific embodiment, if the number of patients with interference delay of the examination item is more than 10 and the interference influence ratio is greater than 0.3, then the influence of the examination item is relatively high, and it is determined that the interference influence ratio of the patients with interference delay of the examination item does not meet the requirements.

[0065] S3 uses the impact of delays at different times on project changes to determine whether an overall update of the image analysis strategy for the project needs to be performed.

[0066] Specifically, determine whether a comprehensive update of the image analysis strategy for the inspection project is needed, including:

[0067] Based on the data on the delay impact of items in different time periods, the data on the delay impact of items in different time periods are determined, and based on the data on the delay impact of items, the patient data on items with delay impact in different time periods are determined;

[0068] Based on the changes in the delay-affected items, determine the change data of the delay-affected items in different time periods compared to the previous time period, and determine the delay-affected items that have changed in different time periods based on the change data.

[0069] Based on patient data on items with time delays at different time periods and the items with changing time delays, it is determined whether a comprehensive update of the image analysis strategy for the examination items is required.

[0070] Optionally, determine whether a comprehensive update of the image analysis strategy for the inspected items is required, specifically including:

[0071] Based on the data on the impact of delays on the project at different time periods, determine the data on the impact of delays on the project at different time periods;

[0072] Based on the changes in the delay-affected items, determine the change data of the delay-affected items in different time periods compared to the previous time period, and determine the delay-affected items that have changed in different time periods based on the change data.

[0073] Based on the time-delay impact items that change in different time periods, the time periods in which the time-delay impact items change are identified, and the overall update processing of the image analysis strategy for whether the inspection items need to be carried out is determined based on the time periods in which the time-delay impact items change and the time-delay impact item data in different time periods.

[0074] In one possible embodiment, when the delay impact data of the project does not meet the requirements in different time periods, i.e. when the number is large, if the overall update of the image analysis strategy of the examination project is not performed, the intervention of the patient's behavioral map will have a certain delay. Therefore, it is determined that the overall update of the image analysis strategy of the examination project is required.

[0075] Additionally, it can be understood that when the delay impact data in different time periods meets the requirements, the impact weight value is determined based on the number of time periods with changing delay impact items and the number of delay impact items in different time periods. When the impact weight value is greater than the preset weight threshold, it is determined that the overall update processing of the image analysis strategy for the inspection items needs to be performed.

[0076] In one possible embodiment, the influence weight value is determined based on the number of time periods with changing delay impact items and the number of delay impact items in different time periods. The more time periods with changing delay impact items and the greater the number of delay impact items in different time periods, the greater the influence weight value. In one possible embodiment, this is determined using an expert algorithm.

[0077] Example 2

[0078] Secondly, such as Figure 5 As shown, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described patient behavior atlas generation intervention method based on image recognition when running the computer program.

[0079] Optionally, the method for determining the image analysis strategy for the inspection item is as follows:

[0080] Based on the data of patients with the stated examination items, determine the number of patients with the stated examination items to be examined.

[0081] Based on the number of examination items to be performed on patients with the aforementioned examination items, patients requiring intervention are identified among those patients with the aforementioned examination items.

[0082] The image analysis strategy for the examination items is determined by using the number of newly added patients requiring intervention within the most recent preset time period.

[0083] It is understandable that when the number of new patients requiring intervention within the most recent preset time period exceeds the preset threshold for the number of new patients, the image analysis strategy for the examination item is determined to be real-time image analysis processing, that is, image analysis processing is performed in the area where the examination item is located at different times to determine the queuing time. If the number of new patients requiring intervention within the most recent preset time period exceeds the preset threshold for the number of new patients, image analysis processing is performed in the area where the examination item is located according to the preset time period.

[0084] Example 3

[0085] Furthermore, the method for determining the delay impact items in the inspection items is as follows:

[0086] Based on the similarity of the examination item with other examination items in patients with delayed intervention, the deviation of the queuing time of the examination item at the moment of image analysis and processing from the queuing time of other examination items is determined.

[0087] The moment when the deviation does not meet the requirements is taken as the moment when the queuing time of the inspection item is similar to that of other items to be inspected. The similar queuing time of the inspection item is determined by using the similar queuing time moment.

[0088] Based on the queue time of the examination item and similar queue time items for the examination item in patients with delayed intervention, it is determined whether the examination item is a delay-affecting item.

[0089] It should be noted that when the examination items are processed by image analysis in the area where the examination items are located at a preset time period, if there are similar queuing time items among patients with delayed intervention, and if there is a delay in updating their queuing time, it is inevitable that there may be technical problems in the process of guiding the examination order of the examination items to be examined in patients with delayed intervention, and therefore, this may be regarded as a delayed item.

[0090] It should be noted that the similar queuing time items refer to other items to be inspected that have similar queuing times to the inspection item. In other words, when the inspection item is undergoing image analysis processing, if the proportion of the other items to be inspected that have similar queuing times to the inspection item is within a preset range, then the similar queuing time items have similar queuing times. At the same time, there are also times that do not belong to the similar queuing time periods. Based on this, the other items to be inspected are determined to be similar queuing time items.

[0091] In one embodiment, if the proportion of times when the image analysis processing of the inspection item is similar to that of the other items to be inspected and the inspection item is between 0.3 and 0.7, then the other items to be inspected are indeed items with similar queue times to the inspection item.

[0092] In one embodiment, the similar queuing time is the moment when the deviation between the queuing time of the inspection item and the queuing time of other items to be inspected during the image analysis processing is less than a preset time. In a possible embodiment, the preset time is 1 minute.

[0093] It is understood that when the inspection item is not an inspection item that undergoes image analysis processing in the area where the inspection item is located according to a preset time period, it is determined that the inspection item is not an item affected by delay.

[0094] Additionally, it should be noted that when the examination item is one that undergoes image analysis processing in the area where the examination item is located according to a preset time cycle, if there are no similar queuing time items for the examination item or if the average queuing time of the examination item in different image analysis processing meets the requirements, then its queuing time is short or there are no similar queuing time items. In this case, it will not affect the guidance accuracy of the patient's behavior map. Therefore, based on this, it is determined that the examination item does not belong to the items affected by delay.

[0095] In another embodiment, when there are similar queuing time items among the inspection items and the average queuing time of the inspection items for different image analysis processing does not meet the requirements, if the number of similar queuing time items does not meet the requirements, then since the number of similar queuing time items is large, the inspection item is determined to be a delay-affecting item.

[0096] In another possible embodiment, if the number of similar queue length items meets the requirement, the number of patients with interference delays due to similar queue length items for the examination item is obtained. If the number of patients with interference delays due to similar queue length items for the examination item does not meet the requirement, then the examination item is determined to be a delay-affecting item. If the number of patients with interference delays due to similar queue length items for the examination item meets the requirement, then the examination item is determined not to be a delay-affecting item.

[0097] In one specific embodiment, if the average queuing time for different image analysis processing items of the examination item is less than 5 minutes, then it is determined that the average queuing time for different image analysis processing items of the examination item meets the requirements, and the examination item is determined not to be a delay-affecting item. If the number of patients affected by the interference of the examination item with similar queuing time items is more than 20, then it is determined that the number of patients affected by the interference of the examination item with similar queuing time items does not meet the requirements, and the examination item is determined to be a delay-affecting item.

[0098] Example 4

[0099] Furthermore, determine whether a comprehensive update of the image analysis strategy for the inspection project is necessary, specifically including:

[0100] Based on the data on the delay impact of items in different time periods, the data on the delay impact of items in different time periods are determined, and based on the data on the delay impact of items, the patient data on items with delay impact in different time periods are determined;

[0101] Based on the changes in the delay-affected items, determine the change data of the delay-affected items in different time periods compared to the previous time period, and determine the delay-affected items that have changed in different time periods based on the change data.

[0102] Based on patient data on items with time delays at different time periods and the items with changing time delays, it is determined whether a comprehensive update of the image analysis strategy for the examination items is required.

[0103] It should be noted that the time period is divided according to the update processing cycle of the delayed impact items. Specifically, the time period between the update processing times of two adjacent delayed impact items is taken as the time period, that is, the time period between the beginning and end of the update processing cycle is taken as the time period.

[0104] It is understood that the delay in the time period affects the update processing result of the project data at the update processing time of the project with delay in the previous time period.

[0105] Specifically, when the data on delays in different time periods do not meet the requirements, i.e. when the number is large, failure to update the overall image analysis strategy for the examination items will result in a certain delay in the intervention of the patient's behavioral atlas. Therefore, it is determined that an overall update of the image analysis strategy for the examination items is necessary.

[0106] Additionally, it is understandable that when the data on delayed-impact items in different time periods meet the requirements, but the data on patients with delayed-impact items in different time periods do not meet the requirements, the number of patients affected by the delayed-impact items is relatively large. Therefore, based on this, it is determined that an overall update of the image analysis strategy for the examination items is required.

[0107] Furthermore, when the patient data for items with delay effects in different time periods meet the requirements, if both the patient data and the data for items with delay effects in different time periods are within the preset range, then the number of items with delay effects and the number of patients with delay effects are relatively small. Therefore, it is determined that there is no need to perform an overall update of the image analysis strategy for the examination items, but only the image analysis strategy for items with delay effects needs to be updated, thereby reducing the analysis and processing cycle of items with delay effects.

[0108] Furthermore, if patient data on delayed-impact items exists in different time periods and the data on delayed-impact items is uneven within a preset range, delayed-impact items that are inconsistent with those in the previous time period will be considered as delayed-impact items that have changed in that time period. When delayed-impact items that have changed exist in all different time periods or the number of time periods with delayed-impact items that have changed does not meet the requirements, it is determined that an overall update of the image analysis strategy for the examination items is required. Conversely, when the number of time periods with delayed-impact items that have changed meets the requirements, it is determined that an overall update of the image analysis strategy for the examination items is not required, and only the image analysis strategy for delayed-impact items needs to be updated, thereby reducing the analysis and processing cycle for delayed-impact items.

[0109] In one possible specific embodiment, when the number of delay-affected items in different time periods is not less than 4, it is determined that the delay-affected item data in different time periods does not meet the requirements, and it is determined that the overall update of the image analysis strategy for the examination items is required. When the number of delay-affected items in different time periods is not less than 4, if the proportion of patients with delay-affected items in different time periods is greater than 0.3, it is determined that the patient data with delay-affected items in different time periods does not meet the requirements, and it is determined that the overall update of the image analysis strategy for the examination items is required.

[0110] In another possible specific embodiment, if the proportion of patients with delayed-effect items in different time periods is less than 0.1 and the number of delayed-effect items in different time periods is no more than 1, then it is determined that the patient data and delayed-effect item data in different time periods are within the preset range. Therefore, it is determined that there is no need to perform an overall update of the image analysis strategy for the examination items, but only the image analysis strategy for delayed-effect items needs to be updated, thereby reducing the analysis and processing cycle of delayed-effect items. When the number of time periods with changed delayed-effect items is greater than the preset number, i.e., more than 15, it is determined that the number of time periods with changed delayed-effect items does not meet the requirements, and it is determined that an overall update of the image analysis strategy for the examination items is required.

[0111] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0112] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0113] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A patient behavior atlas generation intervention method based on image recognition, characterized in that, Specifically, it includes: Based on the patient's medical data, the examination items to be performed for the patient are determined. Based on the examination item data of patients with examination items, the image analysis strategy for each examination item is determined. Based on the image analysis strategy for the patient's examination items, when it is determined that the image analysis strategy needs to be updated, the image analysis strategy is used to identify patients with delayed intervention in the behavioral spectrum. Based on the monitoring data of the queuing time of the examination items of the patients with delayed intervention, the similarity of the queuing time of each examination item is determined. Based on the similarity of the examination items with other examination items in the patients with delayed intervention and the queuing time, the delayed items in the examination items are determined. By utilizing the impact of delays on project changes at different time periods, it can be determined whether an overall update of the image analysis strategy for the project needs to be performed. Determine whether a comprehensive update to the image analysis strategy for the inspection project is necessary, specifically including: Based on the data on the delay impact of items in different time periods, the data on the delay impact of items in different time periods are determined, and based on the data on the delay impact of items, the patient data on items with delay impact in different time periods are determined; Based on the changes in the delay-affected items, determine the change data of the delay-affected items in different time periods compared to the previous time period, and determine the delay-affected items that have changed in different time periods based on the change data. Based on patient data on items with time delays at different time periods and the items with changing time delays, it is determined whether a comprehensive update of the image analysis strategy for the examination items is required.

2. The patient behavior atlas generation intervention method based on image recognition as described in claim 1, characterized in that, The tests to be performed on the patient are determined based on the analysis results of the patient's medical records.

3. The patient behavior atlas generation intervention method based on image recognition as described in claim 1, characterized in that, The method for determining the image analysis strategy for the inspection items is as follows: Based on the data of patients with the stated examination items, determine the number of patients with the stated examination items to be examined. Based on the number of examination items to be performed on patients with the aforementioned examination items, patients requiring intervention are identified among those patients with the aforementioned examination items. Using the patients with the intervention needs, determine the image analysis strategy for the examination items.

4. The patient behavior atlas generation intervention method based on image recognition as described in claim 3, characterized in that, The items to be inspected are those that have not yet been inspected.

5. The patient behavior atlas generation intervention method based on image recognition as described in claim 1, characterized in that, The image analysis strategy needs to be updated, specifically including: Based on the patient's image analysis strategy for the items to be examined, determine when an update to the image analysis strategy is needed. Based on the image analysis strategy of the patient's examination items, the examination items that are subject to image analysis processing in the area where the examination items are located according to a preset time period are identified and designated as delayed examination items. Based on the composition data of the patient's delayed examination items, determine the weight value of the patient's delayed impact; Based on the time delay impact weight values ​​for different patients, it is determined whether the image analysis strategy needs to be updated.

6. The patient behavior atlas generation intervention method based on image recognition as described in claim 5, characterized in that, The delay impact value is the percentage of the delayed examination items in the patient's scheduled examination items.

7. The patient behavior atlas generation intervention method based on image recognition as described in claim 1, characterized in that, The patients referred to as having delayed intervention are those whose examination items include delayed examination items.

8. The patient behavior atlas generation intervention method based on image recognition as described in claim 1, characterized in that, The queuing time for the examination item is determined based on the time from when the patient queues for the examination to when the examination is completed.

9. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes an intervention method for generating a patient behavior map based on image recognition as described in any one of claims 1-8.

Images