Intelligent sensing positioning method of CT code scanning device

Abstract

The invention relates to the technical field of intelligent control of medical imaging equipment, and discloses an intelligent sensing and positioning method of a CT (Computed Tomography) code scanning device, which comprises the following steps of: acquiring historical sensing data to construct an initial positioning set; analyzing historical coordinate attribute matching to generate a second positioning set; analyzing a behavior pattern of the scanning device; screening a third positioning set based on the positioning suitability; and positioning is optimized in combination with real-time feedback. Through a multi-stage set screening mechanism, the problems of poor dynamic adaptability and low historical data utilization rate in traditional CT positioning are solved. According to the technical scheme, firstly, sensing types and position precision features are extracted to construct an initial set, then coordinate quantity is reduced through attribute matching degree sorting, then device behavior patterns (such as updating frequency) are quantified to evaluate positioning adaptability, and finally, optimal coordinates are selected according to real-time operation types. According to the method, the multi-target scanning efficiency and the deep tissue positioning precision are remarkably improved, and the method has wide application value in the field of medical imaging.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of medical imaging equipment, and in particular to an intelligent sensing positioning method for a CT code scanning device. Background Art

[0002] In modern medical diagnosis, CT scanning is an important imaging method. Its accuracy and efficiency directly impact the diagnosis and treatment of diseases. The sensor positioning of the CT scanner is a key step in the CT scanning process. It determines the position accuracy and scanning range of the scan, which in turn affects the quality of the CT image and the accuracy of the diagnosis.

[0003] Traditional sensor positioning methods for CT scanners have numerous shortcomings. These methods often rely on single-sensor data for positioning, making it difficult to comprehensively consider the characteristics of multiple sensor types. This limits positioning accuracy and reliability. For example, relying solely on infrared sensor data for positioning in complex medical environments can be subject to interference from other infrared signals, thus affecting positioning effectiveness. Traditional methods lack in-depth analysis and matching of historical positioning data attributes, making it impossible to effectively select positioning coordinates that match current scanning requirements. This can result in the selection of inappropriate positioning coordinates during the scanning process, compromising scanning accuracy and efficiency.

[0004] Traditional methods fail to fully consider the sensory behavior patterns of the scanning device and are unable to optimize the positioning process based on behavioral characteristics such as the device's positioning update frequency. For example, when the scanning device's positioning update frequency is high, traditional methods may be unable to adjust the positioning strategy in a timely manner, resulting in increased positioning error. When faced with multi-target positioning operations, traditional methods have limited processing capabilities and cannot efficiently handle the screening and optimization of multiple positioning coordinates, which can easily lead to positioning confusion and affect the overall scanning effect.

[0005] During the positioning process, traditional methods lack effective utilization of real-time scanning feedback records and are unable to dynamically optimize positioning based on real-time feedback information, resulting in poor adaptability of positioning and difficulty in meeting the needs of different scanning scenarios and patients.

[0006] With the continuous development of medical imaging, higher requirements are being placed on the accuracy and efficiency of CT scanning. Therefore, there is an urgent need for an intelligent sensor positioning method that can comprehensively consider multiple sensor characteristics, deeply analyze historical data attributes, combine device sensor behavior patterns, effectively handle multi-target positioning operations, and dynamically optimize based on real-time feedback. This method can improve the positioning accuracy and scanning efficiency of CT scanners and provide more accurate imaging evidence for medical diagnosis. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent sensing positioning method for a CT scanning device to solve the problems raised in the above background technology.

[0008] To achieve the above-mentioned object, the present invention provides the following technical solution: an intelligent sensing positioning method for a CT code scanning device, the method comprising:

[0009] S1, collect CT scan historical sensor data, extract sensor positioning features, and build an initial positioning set of the scan area;

[0010] S2. Analyzing the attribute matching between the historical positioning coordinates and the coordinates in the initial positioning set based on the historical CT scanning sensor data, and selecting a second positioning set for the scan area;

[0011] S3, analyzing the sensor behavior pattern of the scanning device based on the historical sensor data of the CT scan;

[0012] S4. Filtering a third positioning set of the scanning area based on the positioning compatibility between the sensing behavior pattern analysis device of the scanning device and the coordinates in the second positioning set;

[0013] S5. Obtain corresponding coordinate information in the third positioning set according to the CT real-time scanning feedback record, and optimize the positioning during the scanning process.

[0014] Preferably, the S1 includes the following specific steps:

[0015] S101. Inputting historical CT scan sensor data into a sensor data acquisition module, and extracting sensor positioning features from the sensor data, wherein the sensor positioning features include sensor type features and position accuracy features;

[0016] S102 : Filter out coordinates containing the sensing type features in the scanning area management module according to the sensing type features and output them in the form of an initial positioning set.

[0017] Preferably, S2 includes the following specific steps:

[0018] S201. Acquire historical sensor data from a scanning device, analyze features of historical positioning coordinates based on the historical sensor data, wherein the features of the historical positioning coordinates include coordinate identification features and attribute features, select historical positioning coordinates containing position accuracy features based on the coordinate identification features and the position accuracy features, and simultaneously acquire attribute features of the coordinates in the initial positioning set;

[0019] S202: Analyze the attribute matching degree between the filtered historical positioning coordinates and the coordinates in the initial positioning set based on the attribute characteristics of the filtered historical positioning coordinates and the attribute characteristics of the coordinates in the initial positioning set;

[0020] S203: Sort the attribute matching degrees in descending order, filter out the coordinates corresponding to the set sequence number, and output them in the form of a second positioning set.

[0021] Preferably, S3 includes the following specific steps:

[0022] S301, extracting the scanning time and positioning depth from the filtered historical sensor data, obtaining the scanning time interval between two adjacent historical sensor data, averaging the obtained scanning time intervals to obtain an average scanning time interval, and averaging the obtained positioning depths to obtain an average positioning depth;

[0023] S302: Compare the average scanning time interval with a preset first time interval threshold and a second time interval threshold, and determine the sensing behavior pattern of the scanning device. If the average scanning time interval is less than or equal to the first time interval threshold, determine that the device has a high positioning update frequency. If the average scanning time interval is greater than the first time interval threshold and the scanning time interval is less than the second time interval threshold, determine that the device has a medium positioning update frequency. If the average scanning time interval is greater than or equal to the second time interval threshold, determine that the device has a low positioning update frequency.

[0024] S303: Obtain a sensing positioning mode score value according to the sensing behavior mode of the scanning device.

[0025] Preferably, the S4 includes the following specific steps:

[0026] S401, obtaining the sensing features and location depth of the coordinates in the second positioning set, and analyzing the positioning compatibility of the device and the coordinates in the second positioning set based on the sensing positioning mode score, the average positioning depth, the sensing features and location depth of the coordinates in the second positioning set;

[0027] S402: Sort the positioning adaptability in descending order, filter out the coordinates corresponding to the set sequence number, and output them in the form of a third positioning set.

[0028] Preferably, the S5 includes the following specific steps:

[0029] Obtain CT real-time scanning feedback records to analyze whether the scanning device has multi-target positioning operations. If the device does not have multi-target positioning operations, obtain the coordinate information with the highest positioning match in the third positioning set, and optimize positioning during the scanning process. If the device has multi-target positioning operations, obtain the coordinate information corresponding to the set sequence number in the third positioning set, and optimize positioning during the scanning process.

[0030] Preferably, the sensing type characteristics include infrared, laser, and electromagnetic specific sensing characteristics, and the position accuracy characteristics include accuracy characteristics of coordinate accuracy, scanning range, and positioning duration.

[0031] Preferably, the positioning compatibility analysis between the device and the coordinates in the second positioning set includes the matching degree between the sensing positioning mode score value and the coordinate sensing feature, and the matching degree between the average positioning depth and the position depth.

[0032] Preferably, the attribute matching degree is analyzed by performing a correspondence analysis on the attribute features of the filtered historical positioning coordinates and the attribute features of the coordinates in the initial positioning set, and calculating the ratio of the number of matching attribute items to the total number of attribute items.

[0033] Preferably, the method for analyzing whether the scanning device has a multi-target positioning operation is to count the proportion of the number of times multiple coordinates are simultaneously positioned in the CT real-time scanning feedback record to the total number of scans. If the proportion exceeds a preset multi-target positioning threshold, it is determined that the device has a multi-target positioning operation.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] In terms of improving positioning accuracy, this method collects historical CT scanning sensor data, extracts sensor positioning features including sensor type features and position accuracy features, constructs an initial positioning set, and further screens out a second positioning set by analyzing the attribute matching between the historical positioning coordinates and the coordinates in the initial positioning set. Combined with the sensing behavior pattern of the scanning device, the positioning adaptability of the device and the coordinates in the second positioning set is analyzed to obtain a third positioning set, and finally optimizes the positioning based on real-time scanning feedback. This series of steps, through layer-by-layer screening and optimization, ensures that the final selected positioning coordinates are highly matched with the actual scanning requirements, thereby significantly improving the accuracy of positioning. For example, in the attribute matching analysis, by performing a corresponding analysis of the attribute features of the filtered historical positioning coordinates and the attribute features of the coordinates in the initial positioning set, and statistically calculating the proportion of matching attribute items, coordinates with high attribute matching can be accurately screened out, reducing positioning errors caused by attribute mismatches.

[0036] In terms of improving scanning efficiency, this method analyzes the sensor behavior patterns of the scanning device, such as calculating the average scanning time interval to determine the positioning update frequency. It then obtains a sensor positioning pattern score based on different behavior patterns. This score and other factors are then combined in the positioning adaptability analysis to more rationally select positioning coordinates, enabling the scanning device to perform positioning updates at a more optimal frequency and method, reducing unnecessary positioning operations and wasted time, and improving scanning efficiency. For example, if the positioning update frequency of the device is determined to be high, the strategy can be adjusted in a timely manner to avoid the impact of excessive updates on scanning progress. If the frequency is low, corresponding measures can be taken to ensure timely positioning.

[0037] In terms of multi-target positioning processing capabilities, this method can count the proportion of simultaneous positioning of multiple coordinates to the total number of scans during real-time scan feedback recording and processing to determine whether a multi-target positioning operation has occurred. If so, the coordinate information within the set sequence number in the third positioning set is obtained for optimized positioning. This processing method can effectively handle multi-target positioning scenarios, ensuring accurate and orderly positioning when multiple positioning targets are present, avoiding positioning confusion and improving the device's ability to work in complex scenarios.

[0038] In terms of dynamic adaptability, this method leverages real-time CT scan feedback to implement different positioning optimization strategies depending on whether the device is performing multi-target positioning operations. When multi-target positioning is not performed, the coordinates with the highest positioning match are selected; when multi-target positioning is performed, coordinates within a set sequence are selected, enabling dynamic adjustment of the positioning process. This optimization approach based on real-time feedback enables the positioning method to better adapt to different scanning scenarios and actual needs, improving the adaptability and flexibility of the entire CT scanning system.

[0039] In terms of comprehensive performance improvement, this method organically combines the analysis of sensor data, the utilization of historical data, the combination of device behavior patterns, and the optimization of real-time feedback through the synergistic effect of multiple steps. It not only improves the positioning accuracy and scanning efficiency, but also enhances the device's ability to handle multi-target positioning and dynamic adaptability, thereby comprehensively improving the comprehensive performance of the CT scanning device, providing more reliable and efficient technical support for medical CT scanning, and helping to improve the accuracy of disease diagnosis and the efficiency of treatment plan formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a working principle diagram of the intelligent sensing and positioning method of the CT code scanning device described in the present invention;

[0041] Figure 2 Design diagrams constructed for the initial positioning set;

[0042] Figure 3 Design drawings screened for the second positioning set;

[0043] Figure 4 Design diagram for sensor behavior pattern analysis;

[0044] Figure 5 Design drawings for screening and optimization of the third positioning set. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] See also Figure 1-Figure 5 The present invention relates to an intelligent sensing and positioning method for a CT code scanning device, and the specific implementation steps are as follows:

[0047] S1. Collect historical CT scan sensor data, extract sensor positioning features, and construct an initial positioning set for the scan area. The sensor data acquisition module inputs historical CT scan sensor data. Sensor positioning features are extracted from the sensor data. These features include sensor type features (such as infrared, laser, and electromagnetic sensor features) and position accuracy features (including coordinate accuracy, scanning range, and positioning duration). Based on these sensor type features, the scan area management module selects coordinates containing these sensor type features and outputs them as an initial positioning set.

[0048] S2. Analyze the attribute matching between the historical positioning coordinates and the coordinates in the initial positioning set based on the historical CT scanning sensor data, and select the second positioning set of the scanning area. Obtain the historical sensor data of the scanning device, analyze the characteristics of the historical positioning coordinates, which include coordinate identification characteristics and attribute characteristics, and select the historical positioning coordinates containing the position accuracy characteristics based on the coordinate identification characteristics and position accuracy characteristics. At the same time, obtain the attribute characteristics of the coordinates in the initial positioning set. Analyze the attribute characteristics of the filtered historical positioning coordinates and the attribute characteristics of the coordinates in the initial positioning set item by item, and calculate the ratio of the number of matching attribute items to the total number of attribute items to analyze the attribute matching between the two. Sort the attribute matching in descending order, select the coordinates corresponding to the set sequence number, and output them as the second positioning set.

[0049] S3. Analyze the sensor behavior pattern of the scanning device based on the historical CT scan sensor data. Extract the scan time and positioning depth from the filtered historical sensor data, obtain the scan time interval between two adjacent historical sensor data, average the multiple scan time intervals to obtain the average scan time interval, and average the multiple positioning depths to obtain the average positioning depth. Compare the average scan time interval with a preset first time interval threshold and a second time interval threshold. If the average scan time interval is less than or equal to the first time interval threshold, determine that the device positioning update frequency is high; if the average scan time interval is greater than the first time interval threshold and less than the second time interval threshold, determine that the device positioning update frequency is medium; if the average scan time interval is greater than or equal to the second time interval threshold, determine that the device positioning update frequency is low. Then, obtain a sensor positioning pattern score based on the sensor behavior pattern.

[0050] S4. Analyze the compatibility of the device and the coordinates in the second positioning set based on the sensing behavior pattern of the scanning device, and select a third positioning set for the scanning area. Obtain the sensing characteristics and location depth of the coordinates in the second positioning set. Combined with the sensing positioning pattern score and the average location depth, analyze the compatibility of the device and the coordinates in the second positioning set. This compatibility analysis includes the degree of match between the sensing positioning pattern score and the sensing characteristics of the coordinates, and the degree of fit between the average location depth and the location depth. Sort the positioning compatibility in descending order, select the coordinates corresponding to the set sequence number, and output them as the third positioning set.

[0051] S5. Obtain the corresponding coordinate information in the third positioning set based on the CT real-time scan feedback record, and optimize positioning during the scanning process. Obtain the CT real-time scan feedback record, and count the proportion of the number of times multiple coordinates are simultaneously located to the total number of scans. If this proportion exceeds a preset multi-target positioning threshold, it is determined that the device has performed a multi-target positioning operation. In this case, obtain the coordinate information corresponding to the set sequence number in the third positioning set. If the device has not performed a multi-target positioning operation, obtain the coordinate information in the third positioning set with the highest positioning match, and optimize positioning during the scanning process.

[0052] Example 1:

[0053] This embodiment primarily refines step S1. Historical CT scan sensor data is input into the sensor data acquisition module. This historical sensor data represents all data collected by the CT scanner during past scans using various sensor devices. These sensors may include infrared sensors, laser sensors, electromagnetic sensors, and others. These sensors operate in various scanning scenarios and record a wealth of information related to the scanning process.

[0054] It is necessary to extract sensor positioning features from this massive amount of sensor data. This extraction process is achieved through specific data processing algorithms that can deeply analyze and mine the sensor data. Sensor positioning features mainly include two aspects: sensor type features and position accuracy features.

[0055] Sensing type characteristics specifically involve the unique features of different sensor types. Infrared sensing characteristics include the intensity of the infrared signal, which reflects the amount of infrared energy radiated by the target object received by the infrared sensor; the wavelength range of the infrared signal, as different objects radiate different infrared wavelengths, which helps identify different targets; and the modulation method of the infrared signal. Laser sensing characteristics include the laser emission frequency, which is the number of laser emissions per unit time, which affects the speed and accuracy of scanning; the spot size, which is the size of the spot formed when the laser beam hits the target object and is related to positioning resolution; the laser wavelength, as different wavelengths of laser light have different propagation characteristics in air and reflection characteristics on objects; and the laser pulse width. Electromagnetic sensing characteristics include the frequency of the electromagnetic signal, as different electromagnetic sensors operate in different frequency bands and are used to detect different targets; the intensity distribution of the electromagnetic signal, which indicates the strength distribution of the electromagnetic signal in space; and the phase characteristics of the electromagnetic signal.

[0056] Position accuracy features include coordinate accuracy, which refers to the accuracy of the positioning coordinates in space. This is typically measured by the coordinate error range, for example, whether the coordinate errors on the X, Y, and Z axes are within the allowable range. Scanning range refers to the size of the spatial area that the sensing device can effectively scan, which determines the range of the scanning area that the device can cover. Positioning duration accuracy features involve the stability and accuracy of the positioning process. For example, whether the time required for each positioning is roughly the same, and whether there are large time fluctuations, which will affect the efficiency and real-time performance of the scan.

[0057] After extracting the sensor type signature, the scanning area management module needs to filter out matching coordinates based on these signatures. The scanning area management module stores all coordinate information within the scanning area, with each coordinate associated with a corresponding sensor type signature. The screening process involves checking each coordinate individually to determine if it contains features that match the extracted sensor type signature. For example, if the extracted sensor type signature is a specific wavelength range and signal strength range within the infrared sensor signature, the scanning area management module will filter out all coordinates associated with that wavelength range and signal strength range.

[0058] After selecting the coordinates that meet the criteria, they are output as an initial positioning set. This initial positioning set consists of multiple coordinates whose sensor type characteristics match those in the historical sensor data, providing a basis for subsequent positioning screening. By forming this initial positioning set, the positioning range can be narrowed to coordinates that match the characteristics of the historical sensor data, reducing the amount of data to be processed later and improving the efficiency and specificity of positioning.

[0059] Throughout the implementation process, attention must be paid to data accuracy and integrity. Historical sensor data input must be verified to be authentic and valid, and data processing algorithms must be designed to accurately extract the required sensor positioning features to avoid feature extraction errors. Coordinate information in the scan area management module must also be updated and maintained promptly to ensure that the selected coordinates are current and accurate.

[0060] Furthermore, the output format of the initial positioning set must conform to the requirements of subsequent processing modules to ensure that the coordinate information can be smoothly received and processed in subsequent steps. Furthermore, different processing methods and filtering conditions may be required for different types of sensor data to accommodate the characteristics of different sensor devices and scanning requirements.

[0061] Example 2:

[0062] This embodiment primarily refines step S2. Historical sensor data from the scanning device is acquired. This data records all sensor information generated by the scanning device during previous CT scans, including multi-dimensional data such as the location coordinates, sensor type, and environmental parameters for each scan. The sources of this historical sensor data include various sensors built into the device, such as infrared, laser, and electromagnetic sensors. This data can be stored as structured data in a database or in a log file format to ensure data integrity and traceability.

[0063] Analyze the characteristics of historical positioning coordinates. The characteristics of historical positioning coordinates include coordinate identification characteristics and attribute characteristics. Coordinate identification characteristics are codes or identifiers used to uniquely identify each positioning coordinate, such as hash values ​​or sequential numbers based on spatial coordinates. Their function is to accurately locate specific coordinates in a large amount of data. Attribute characteristics involve the physical properties of the area where the coordinates are located, environmental parameters, and the geometric characteristics of the coordinates themselves. Specifically, they include: material characteristics of the area where the coordinates are located, such as the reflection and absorption characteristics of different materials such as soft tissue, bone, or metal for sensor signals; parameters such as ambient temperature and humidity, which may affect the propagation and detection accuracy of sensor signals; three-dimensional spatial position parameters of the coordinates, such as the coordinate values ​​of the X, Y, and Z axes and their error ranges; and scanning parameter characteristics such as the thickness of the scanning layer and the interlayer spacing corresponding to the coordinates.

[0064] After analyzing the features, the historical positioning coordinates are screened based on the coordinate identification features and the position accuracy features extracted in step S1. The position accuracy features include the accuracy features of coordinate accuracy, scanning range, and positioning duration. During the screening process, the specific coordinates are first located through the coordinate identification features, and then it is determined whether they meet the requirements of the position accuracy features. For example, if the position accuracy features require that the coordinate accuracy is within ±0.5mm, the scanning range needs to cover a specific area, and the positioning time does not exceed 2 seconds, then only the historical positioning coordinates that meet these conditions are retained, and coordinates with insufficient accuracy or excessive duration are excluded to ensure that the screened coordinates meet the basic requirements in terms of position accuracy.

[0065] Obtain the attribute features of the coordinates in the initial positioning set. The initial positioning set is the set of coordinates selected based on the sensor type features in step S1. Each coordinate is associated with a corresponding attribute feature, such as sensor type, area material, and spatial location. These attribute features are obtained by querying the database of the scanning area management module and extracting the corresponding attribute data based on the coordinate identifiers to form a structured attribute feature list.

[0066] Perform attribute matching analysis. The specific operation is to analyze the attribute characteristics of the filtered historical positioning coordinates and the attribute characteristics of the coordinates in the initial positioning set one by one. For example, for each historical positioning coordinate, traverse each item in its attribute characteristics, such as material properties, temperature, coordinate accuracy, etc., and compare them with the corresponding attribute items of each coordinate in the initial positioning set. The comparison rules are set according to the attribute type: for numerical attributes (such as coordinate accuracy error value), determine whether they are consistent within the preset error range; for enumeration attributes (such as sensor type), determine whether they are exactly the same; for text attributes (such as area description), determine whether they are semantically matched.

[0067] The ratio of the number of matching attribute items to the total number of attribute items is calculated as the attribute matching degree. For example, if a historical positioning coordinate has 10 attribute items, and 8 of them match the attribute items of a coordinate in the initial positioning set, the matching degree is 80%. During the statistical process, it is important to pay attention to the weighting of the attribute items. If certain attribute items (such as coordinate accuracy and sensor type) have a greater impact on positioning matching, they can be given a higher weight when calculating the ratio. However, the weighting setting should be based on historical data patterns or domain knowledge to ensure the rationality of the calculation logic.

[0068] After calculating the attribute matching, all historical coordinates are sorted in descending order of their matching with the coordinates in the initial positioning set. This sorting prioritizes coordinates with high matching scores, making subsequent filtering more targeted. The sorting rule uses descending numerical order, ensuring that the coordinates with the highest matching scores are placed first.

[0069] Set the sequence number according to the actual application requirements, filter out the coordinates corresponding to the sequence number, and output them in the form of a second positioning set. For example, if the first 20% of the coordinates are set to be filtered, the first 20% of the coordinates after sorting will be taken to form the second positioning set. The output format must include coordinate identifiers, attribute characteristics, and matching values ​​to facilitate subsequent steps. The role of the second positioning set is to further narrow the scope through attribute matching on the basis of the initial positioning set, so that the remaining coordinates are more consistent with the attribute characteristics of the historical positioning data, providing a more accurate data foundation for the subsequent analysis of the sensing behavior pattern and positioning adaptability of the device.

[0070] Throughout the implementation process, attention must be paid to the accuracy and efficiency of data processing. The acquisition of historical sensor data must ensure that there are no omissions or errors. Data integrity can be verified through data verification algorithms (such as parity check and hash check); the analysis of attribute features must follow unified standards and specifications to avoid errors caused by inconsistent analysis rules; when calculating the matching degree, performance optimization under large data volumes must be considered. Indexing technology or parallel computing frameworks can be used to increase processing speed. In addition, the threshold for setting the serial number needs to be adjusted according to the specific needs of the scanning scenario. For example, in high-precision scanning scenarios, the threshold can be reduced to retain coordinates with higher matching degrees. In fast scanning scenarios, the threshold can be appropriately relaxed to improve processing efficiency.

[0071] Example 3:

[0072] This embodiment primarily refines step S3. It is necessary to extract two key parameters, scanning time and positioning depth, from the filtered historical sensor data. The filtered historical sensor data is the valid data remaining after processing in step S2. This data excludes sensor information corresponding to coordinates with low attribute matching, retaining historical sensor records that closely match the attribute characteristics of the initial positioning set.

[0073] To process scan time, we need to calculate the scan time interval between two adjacent historical sensor data points. Since historical sensor data is recorded in chronological order, each data point contains a specific scan timestamp. Therefore, we can sequentially read the timestamps of two adjacent data points and calculate the time difference between them to obtain the scan time interval. For example, if the scan time of the first data point is t1 and the scan time of the second data point is t2, then the time interval between them is t2 - t1. Similarly, by performing this calculation for all adjacent data pairs, we can obtain multiple scan time intervals.

[0074] To process positioning depth, the corresponding positioning depth value must be extracted from each piece of historical sensor data. Positioning depth refers to the spatial depth of the target position relative to the scanner during positioning operations, typically measured in millimeters. Each piece of historical sensor data records the depth value of that positioning. Extracting these values ​​one by one forms a positioning depth dataset.

[0075] After obtaining multiple scan time intervals and positioning depth values, they need to be averaged. To calculate the average scan time interval, all scan time intervals are added together and then divided by the number of intervals to obtain the average scan time interval. This average value reflects the average time interval between two consecutive scans during the scanning process of the scanning device, thus reflecting the frequency characteristics of the scan. Similarly, to calculate the average positioning depth, all positioning depth values ​​are added together and then divided by the number of depth values ​​to obtain the average positioning depth. This average value represents the average spatial depth position involved in the positioning operation of the scanning device during the historical scan.

[0076] The average scan interval is compared with a preset first and second interval thresholds to determine the scanning device's sensing behavior. These thresholds are pre-set based on the actual CT scanning application scenario and the device's performance parameters. For example, the first interval threshold might be set at 50 milliseconds and the second at 200 milliseconds, but the specific values ​​need to be adjusted based on actual conditions.

[0077] If the average scanning interval is less than or equal to the first interval threshold, it indicates that the interval between two consecutive scans of the scanning device during the historical scanning process was very short, that is, the number of scans and positioning updates per unit time was high. Therefore, it can be determined that the device has a high positioning update frequency. This situation usually occurs in scenarios where rapid real-time data acquisition is required or when scanning dynamic targets, such as scanning moving organs.

[0078] If the average scanning interval is greater than the first interval threshold and less than the second interval threshold, the scanning interval of the scanning device is at a medium level, and the positioning update frequency is neither too high nor too low, which is considered a medium update frequency. This situation may be suitable for general scanning scenarios of static or slowly changing targets.

[0079] If the average scanning interval is greater than or equal to the second interval threshold, the interval between two consecutive scans by the scanning device is long, the number of positioning updates per unit time is small, and the positioning update frequency of the device is determined to be low. This situation may occur in scenarios that require high scanning accuracy but not high real-time performance, such as scanning certain delicate parts.

[0080] After determining the scanning device's sensor behavior pattern, a sensor positioning pattern score is derived based on that pattern. The sensor positioning pattern score is a numerical value that quantifies the device's sensor behavior pattern and is correlated with the location update frequency. For example, a high location update frequency might result in a higher score, such as 80; a medium frequency might result in a score of 50; and a low frequency might result in a score of 20. The specific scoring rules need to be determined based on the device's performance indicators and scanning requirements to ensure that the score accurately reflects the device's sensor behavior pattern.

[0081] Throughout the implementation process, attention must be paid to data accuracy and the rationality of threshold settings. When extracting historical sensor data, data integrity and accuracy must be ensured to avoid biased calculations due to missing or erroneous data. When calculating average scanning interval and average positioning depth, sufficient data must be collected so that the averages truly reflect the overall historical scanning situation. If the data volume is too small, the averages may fluctuate significantly, affecting the accuracy of the judgment.

[0082] The preset time interval thresholds require thorough testing and verification, determined based on actual scanning scenarios and device performance. Improper threshold settings can lead to inaccurate interpretation of sensor behavior patterns, impacting subsequent positioning suitability analysis. Therefore, in practice, the thresholds may need to be adjusted and optimized based on multiple experiments and actual operational data.

[0083] Furthermore, the determination of sensor positioning mode scores must be scientific and rational, with scoring rules that accurately reflect the impact of different sensor behavior patterns on positioning adaptability. The scoring range and specific values ​​must be considered in conjunction with the requirements of positioning adaptability analysis in subsequent steps to ensure that the scores are effective in subsequent calculations.

[0084] Example 4:

[0085] This embodiment mainly refines step S4. It is necessary to obtain the sensing features and position depth of the coordinates in the second positioning set. The second positioning set is a coordinate set formed after processing in step S2, and each coordinate therein has a high degree of matching with the attribute features of the historical positioning coordinates. For each coordinate, the sensing features mainly include specific parameters of its corresponding sensing type (such as infrared, laser, electromagnetic, etc.), such as the wavelength range and signal strength in infrared sensing features, the emission frequency and spot size in laser sensing features, and the frequency and phase in electromagnetic sensing features. These sensing features are extracted based on historical sensing data in step S1 and used to construct the initial positioning set, and are then the key features retained after the attribute matching screening in step S2. Position depth refers to the spatial depth position of the coordinate in the scanning area, usually expressed as the Z-axis coordinate value in three-dimensional coordinates or the vertical distance relative to the scanning device, reflecting the position information of the coordinate in the depth direction.

[0086] The compatibility of the device with the coordinates in the second location set must be analyzed by combining the sensor positioning mode score and the average positioning depth. The sensor positioning mode score is a quantitative value determined in step S3 based on the scanning device's sensing behavior (i.e., high, medium, or low positioning update frequency) and is used to characterize the device's positioning update characteristics. The average positioning depth is obtained by averaging the positioning depths in the historical sensor data in step S3 and reflects the device's average positioning depth position in the historical scans.

[0087] Positioning adaptability analysis mainly includes two aspects: one is the matching degree between the sensor positioning mode score and the coordinate sensing characteristics, and the other is the matching degree between the average positioning depth and the position depth.

[0088] When analyzing the degree of match between the sensor positioning mode score and the coordinate sensor characteristics, it's important to consider the sensor characteristic requirements of different sensor positioning modes. For example, when the sensor positioning mode score is high (corresponding to a high positioning update frequency), the device may require a faster sensor response speed and a higher data acquisition frequency. In this case, coordinate sensor characteristics with characteristics such as high data transmission speed and a short wavelength (to improve resolution) are highly compatible with this mode. Specifically, if the device's sensor positioning mode is high-frequency update, and the sensor characteristic of a coordinate is laser sensing with a high emission frequency and a small spot size, meeting the accuracy and speed requirements of high-frequency positioning, then the coordinate and device will have a high degree of match. Conversely, if the sensor characteristic of the coordinate is infrared sensing with unstable signal strength, the match may be lower. During the analysis process, it's necessary to establish a standard for the correspondence between the sensor positioning mode and the sensor characteristics. This standard is based on the performance of each sensor characteristic under different modes in historical scan data. For example, statistical analysis can be performed to determine which sensor characteristic combinations produce the best positioning results under the high-frequency update mode, thereby determining the basis for determining the degree of match.

[0089] To analyze the degree of agreement between the average positioning depth and the position depth, the proximity of the position depth to the average positioning depth is compared. The average positioning depth reflects the typical operating depth of the device during historical scans. If the position depth at a certain coordinate is close to the average positioning depth, it indicates that the device's mechanical motion parameters, sensor signal propagation characteristics, and other characteristics are closer to historical conditions when positioning at that depth, making it easier to achieve accurate positioning and achieving a higher degree of agreement. For example, if the average positioning depth is 150mm and the position depth at one coordinate is 155mm, a difference of 5mm, compared to the position depth at another coordinate of 180mm, a difference of 30mm, the former indicates a higher degree of agreement. The calculation can be performed by calculating the absolute value of the difference between the position depth and the average positioning depth, with smaller differences indicating higher agreement. Alternatively, the difference can be divided into different ranges corresponding to different levels of agreement, such as a difference of 0-10mm for high agreement, 10-20mm for medium agreement, and 20mm or above for low agreement.

[0090] After comprehensively considering the above two factors, the positioning adaptability of each coordinate is determined. A weighted summation method can be used to weight the matching score of the sensing positioning mode with the coordinate sensing feature and the matching score of the average positioning depth with the position depth to obtain the final positioning adaptability value. Among them, the setting of the weight needs to be determined according to the importance of the sensing mode and positioning depth in the actual application scenario. For example, in a depth-sensitive scanning scenario, the weight of the matching degree of the average positioning depth with the position depth can be set higher, while in a scenario with strict requirements on the sensing type, the weight of the matching degree of the sensing positioning mode with the sensing feature is higher.

[0091] After calculating positioning suitability, you need to sort the coordinates in descending order. The purpose of sorting is to place coordinates with high suitability first, making them easier to filter later. When sorting, arrange the coordinates in descending order of positioning suitability, ensuring that the coordinates with the highest suitability are at the top.

[0092] Finally, a sequence number is set based on actual needs, and the coordinates corresponding to that sequence number are filtered out and output as a third positioning set. For example, if the top 30% of coordinates are filtered out, the top 30% of coordinates after sorting are taken to form the third positioning set. The coordinates in the third positioning set are selected based on the second positioning set through further positioning adaptability analysis. They are more compatible with the sensing behavior pattern and historical positioning depth characteristics of the scanning device, providing better positioning candidates for subsequent scanning processes, thereby improving the positioning accuracy and efficiency of the CT scanner during scanning.

[0093] During the entire implementation process, the following points need to be noted: First, the sensor characteristics and position depth of the coordinates in the obtained second positioning set must be accurate. This requires ensuring that no errors occur during data storage and transmission, and data verification can be performed when necessary; Second, the matching criteria for the established sensor positioning mode and sensor characteristics, as well as the judgment criteria for the fit between the average positioning depth and the position depth, need to be reasonable and should be based on a large amount of historical data and practical application experience to avoid subjective conjectures; Third, when weighted calculation of positioning adaptability, the weight setting should be scientific and able to reflect the importance of different factors in actual positioning. If necessary, the weight can be optimized and adjusted through multiple experiments; Fourth, in the sorting and screening process, the correctness of the algorithm must be ensured to avoid screening out inappropriate coordinates due to sorting errors.

[0094] Example 5:

[0095] This embodiment primarily refines step S5. A real-time CT scan feedback record is obtained. This record contains all real-time data generated by the scanning device during the current scan, such as positioning coordinates, scan time, sensor signal strength, and multi-target positioning status. The data is sourced from the data stream collected in real time by the device's built-in sensors and transmitted to the control system. The data is stored in a real-time, updated cache or log file to ensure real-time and accuracy.

[0096] Analyze whether there are multi-target positioning operations in the scanning device. The specific analysis method is to count the number of times that multiple coordinates are positioned simultaneously in the CT real-time scanning feedback record to the proportion of the total number of scans. Among them, the judgment standard of "simultaneous positioning of multiple coordinates" is that within the same scanning cycle (such as within one second), the device performs positioning operations on two or more different coordinates. The total number of scans is the total number of positioning operations performed by the device during the current scan, regardless of whether it is multi-target positioning. For example, in 100 scans, if 30 times 2 or more coordinates are positioned simultaneously, the number of multi-target positioning times accounts for 30%.

[0097] A preset multi-target positioning threshold is set based on the specific CT scan application scenario, such as 20% for routine scans and 40% for complex lesion scans. If the statistically calculated ratio exceeds the preset threshold, the device is deemed to have performed multi-target positioning; if not, it is deemed not to have performed multi-target positioning. This analysis is implemented using a real-time data processing algorithm that traverses the positioning operation timestamps and coordinate identifiers in the feedback records in real time, identifying and counting multiple coordinate positioning actions within the same time interval.

[0098] If it is determined that the device does not have a multi-target positioning operation, the coordinate information with the highest positioning match in the third positioning set is obtained. The third positioning set is a coordinate set that is adapted to the device's sensing behavior pattern and positioning depth characteristics, as screened in step S4. Each coordinate is associated with a positioning adaptability score (the score is derived from the positioning adaptability analysis in step S4 and reflects the degree of match between the coordinate and the device). When obtaining the coordinate with the highest positioning match, it is necessary to traverse all coordinates in the third positioning set, extract their positioning adaptability scores, and find the coordinate with the highest score. The information of this coordinate includes three-dimensional coordinate values, sensing characteristics, position depth, etc.

[0099] When optimizing positioning during scanning, the device's positioning parameters are adjusted to those of the coordinates. For example, the sensor type is switched to the one corresponding to the coordinate (infrared / laser / electromagnetic), the positioning depth is adjusted to the depth of the coordinate, and the sensor device is controlled according to the sensor characteristic parameters of the coordinate (such as laser emission frequency and infrared signal strength threshold), thereby achieving positioning optimization. This process is executed by the device's control system, which generates control instructions based on the coordinate information, driving the mechanical moving parts and sensor module to adjust to the target state.

[0100] If the determination device has a multi-target positioning operation, the coordinate information corresponding to the set serial number in the third positioning set is obtained. The set serial number is determined according to the actual needs of multi-target positioning. For example, when the number of multi-target positioning times accounts for 35% and the threshold is 20%, the coordinates of the first 5 or first 10% can be set to be obtained (the specific value needs to be set according to the processing capacity of the scanning device and the positioning accuracy requirements). The acquisition method is to sort the coordinates in the third positioning set in descending order according to the positioning adaptability score, and take the first N coordinates after sorting (N is the set serial number). The positioning adaptability of these coordinates is relatively high and can meet the accuracy requirements of multi-target positioning.

[0101] When optimizing positioning during the scanning process, a phased or parallel processing approach is employed to address the unique characteristics of multi-target positioning operations. For example, coordinates within a set sequence are located sequentially, with the positioning parameters for each coordinate individually adjusted based on its sensing characteristics and position depth. Alternatively, the device's multi-sensor module's parallel processing capabilities can be leveraged to simultaneously set positioning parameters for multiple coordinates (e.g., a multi-channel laser sensor simultaneously emits lasers of different frequencies corresponding to the sensing characteristics of different coordinates). The control system must coordinate the operating timing of each sensor module to avoid signal interference and adjust positioning parameters based on real-time feedback to ensure accurate multi-target positioning.

[0102] Throughout the implementation process, attention must be paid to the efficiency and accuracy of real-time data processing. CT real-time scan feedback records are typically acquired at a high frequency (e.g., 10-100 times per second), requiring data processing algorithms with high-speed computing capabilities. A streaming computing framework can be used to process data in real time to avoid data backlogs. The setting of the multi-target positioning threshold must be considered in conjunction with the device's hardware performance, such as the sensor module's concurrent processing capabilities and the positioning speed of mechanical moving parts. If the threshold is set too high, the device may be overloaded during multi-target positioning, affecting positioning accuracy. If the threshold is set too low, the device's multi-target processing capabilities cannot be fully utilized.

[0103] In addition, when obtaining the coordinate information in the third positioning set, it is necessary to ensure the accuracy of the positioning adaptability score, which depends on the calculation result of step S4. Therefore, it is necessary to ensure the accuracy of the analysis of the matching degree between the sensor positioning mode score value and the coordinate sensing feature in step S4, and the matching degree between the average positioning depth and the position depth. In the multi-target positioning scenario, the spatial position relationship between the coordinates must also be considered to avoid multiple coordinates positioned simultaneously being too close in space, causing interference between the sensor signals. After setting the serial number filter, further spatial distance filtering conditions can be added (such as the distance between coordinates must be greater than 5mm), but this operation needs to be determined according to the specific implementation requirements, and non-essential steps can be omitted.

[0104] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0105] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent sensing positioning method for a CT code scanning device, characterized in that: The specific steps include: S1, collect CT scan historical sensor data, extract sensor positioning features, and build an initial positioning set of the scan area; S2. Analyzing the attribute matching between the historical positioning coordinates and the coordinates in the initial positioning set based on the historical CT scanning sensor data, and selecting a second positioning set for the scan area; S3, analyzing the sensor behavior pattern of the scanning device based on the historical sensor data of the CT scan; S4. Filtering a third positioning set of the scanning area based on the positioning compatibility between the sensing behavior pattern analysis device of the scanning device and the coordinates in the second positioning set; S5. Obtain corresponding coordinate information in the third positioning set according to the CT real-time scanning feedback record, and optimize the positioning during the scanning process.

2. The intelligent sensing positioning method for a CT code scanning device according to claim 1, characterized in that: The S1 includes the following specific steps: S101. Inputting historical CT scan sensor data into a sensor data acquisition module, and extracting sensor positioning features from the sensor data, wherein the sensor positioning features include sensor type features and position accuracy features; S102 : Filter out coordinates containing the sensing type features in the scanning area management module according to the sensing type features and output them in the form of an initial positioning set.

3. The intelligent sensing positioning method of a CT code scanning device according to claim 2, characterized in that: The S2 includes the following specific steps: S201. Acquire historical sensor data from a scanning device, analyze features of historical positioning coordinates based on the historical sensor data, wherein the features of the historical positioning coordinates include coordinate identification features and attribute features, select historical positioning coordinates containing position accuracy features based on the coordinate identification features and the position accuracy features, and simultaneously acquire attribute features of the coordinates in the initial positioning set; S202: Analyze the attribute matching degree between the filtered historical positioning coordinates and the coordinates in the initial positioning set based on the attribute characteristics of the filtered historical positioning coordinates and the attribute characteristics of the coordinates in the initial positioning set; S203: Sort the attribute matching degrees in descending order, filter out the coordinates corresponding to the set sequence number, and output them in the form of a second positioning set.

4. The intelligent sensing positioning method of a CT code scanning device according to claim 3, characterized in that: The S3 includes the following specific steps: S301, extracting the scanning time and positioning depth from the filtered historical sensor data, obtaining the scanning time interval between two adjacent historical sensor data, averaging the obtained scanning time intervals to obtain an average scanning time interval, and averaging the obtained positioning depths to obtain an average positioning depth; S302: Compare the average scanning time interval with a preset first time interval threshold and a second time interval threshold, and determine the sensing behavior pattern of the scanning device. If the average scanning time interval is less than or equal to the first time interval threshold, determine that the device has a high positioning update frequency. If the average scanning time interval is greater than the first time interval threshold and the scanning time interval is less than the second time interval threshold, determine that the device has a medium positioning update frequency. If the average scanning time interval is greater than or equal to the second time interval threshold, determine that the device has a low positioning update frequency. S303: Obtain a sensing positioning mode score value according to the sensing behavior mode of the scanning device.

5. The intelligent sensing positioning method of a CT code scanning device according to claim 4, characterized in that: The S4 includes the following specific steps: S401, obtaining the sensing features and location depth of the coordinates in the second positioning set, and analyzing the positioning compatibility of the device and the coordinates in the second positioning set based on the sensing positioning mode score, the average positioning depth, the sensing features and location depth of the coordinates in the second positioning set; S402: Sort the positioning adaptability in descending order, filter out the coordinates corresponding to the set sequence number, and output them in the form of a third positioning set.

6. The intelligent sensing and positioning method of a CT code scanning device according to claim 5, characterized in that: The S5 includes the following specific steps: Obtain CT real-time scanning feedback records to analyze whether the scanning device has multi-target positioning operations. If the device does not have multi-target positioning operations, obtain the coordinate information with the highest positioning match in the third positioning set, and optimize positioning during the scanning process. If the device has multi-target positioning operations, obtain the coordinate information corresponding to the set sequence number in the third positioning set, and optimize positioning during the scanning process.

7. The intelligent sensing and positioning method for a CT code scanning device according to claim 2, characterized in that: The sensing type characteristics include specific sensing characteristics of infrared, laser, and electromagnetic, and the position accuracy characteristics include accuracy characteristics of coordinate accuracy, scanning range, and positioning duration.

8. The intelligent sensing and positioning method for a CT code scanning device according to claim 5, characterized in that: The positioning compatibility analysis between the device and the coordinates in the second positioning set includes the matching degree between the sensing positioning mode score value and the coordinate sensing feature, and the matching degree between the average positioning depth and the position depth.

9. The intelligent sensing and positioning method for a CT code scanning device according to claim 3, characterized in that: The attribute matching degree is analyzed by performing a correspondence analysis on the attribute features of the filtered historical positioning coordinates and the attribute features of the coordinates in the initial positioning set, and counting the ratio of the number of matching attribute items to the total number of attribute items.

10. The intelligent sensing positioning method of a CT code scanning device according to claim 6, characterized in that: The method for analyzing whether the scanning device has a multi-target positioning operation is to count the proportion of the number of times multiple coordinates are simultaneously positioned in the CT real-time scanning feedback record to the total number of scans. If the proportion exceeds a preset multi-target positioning threshold, it is determined that the device has a multi-target positioning operation.

Images