Multi-modal blood data fusion method and system
Through the multimodal blood data fusion method, combined with blood attribute data and identification information, the problem of incomplete diagnosis of a single data source is solved, the accuracy and comprehensiveness of blood disease diagnosis are improved, and clinical decision-making is supported.
Patent Information
- Application Number
- CN202510582832.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2025-09-26
AI Technical Summary
In the existing technology, blood diagnosis methods based on a single data source are difficult to fully reveal the patient's blood diseases, especially occult blood diseases, resulting in low diagnostic accuracy.
A multimodal blood data fusion method is used to obtain blood attribute data and identification information, calculate abnormal indication information, select patient state vectors, determine whether they meet pre-configured requirements, and obtain multimodal blood data fusion results.
It improves the accuracy and comprehensiveness of blood disease diagnosis, provides data support in more dimensions, and provides a more reliable basis for clinical decision-making.
Smart Images
Figure CN120705790A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data fusion technology, and in particular to a multimodal blood data fusion method and system. Background Art
[0002] With the continuous deepening of medical research, the early diagnosis and precise treatment of blood diseases have become important challenges in modern medicine. The diagnosis of blood diseases has traditionally relied on a single data source, such as blood images or biochemical indicators. However, a single data source may have incomplete information and it is difficult to accurately reveal the patient's full picture, especially some hidden blood diseases. In order to improve the accuracy of diagnosis and provide more dimensional data support for clinical decision-making, the use of multimodal data fusion technology has become an effective solution. Currently, blood images, patients' biochemical indicators and clinical data can all serve as important reference information for the diagnosis of blood diseases. How to effectively fuse these heterogeneous data and automatically identify and analyze blood diseases through advanced technical means is the main goal of this project. Summary of the Invention
[0003] In view of this, the present application provides a multimodal blood data fusion method and system.
[0004] In a first aspect, a multimodal blood data fusion method is provided, the method comprising: Obtaining blood attribute data of target multimodal blood data identified at a real-time time node and collected identification information, wherein the identification information at least includes: an identification factor and a blood image sequence number of the target multimodal blood data and a patient's biochemical index; Calculating abnormality indication information by combining the characteristic content of the blood attribute data and the identification information; When at least one description mode of the characteristic content in the blood attribute data matches the abnormality indication information, determining that the target multimodal blood data contains multimodal blood data with abnormal information; When it is determined that the multimodal blood data containing the abnormal information exists in the target multimodal blood data, acquiring blood attribute data of the target multimodal blood data identified after the real-time time node; selecting the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determining whether the patient state vector meets a first pre-configured requirement; When the patient state vector meets the first pre-configured requirement, a multimodal blood data fusion result of the target multimodal blood data is obtained.
[0005] Furthermore, the step of calculating abnormal indication information by combining the characteristic content of the blood attribute data and the identification information includes: Calculating characteristic contents of the auxiliary information of the blood attribute data by combining characteristic contents of each description mode in the blood attribute data; Calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index; A sharing coefficient judgment is performed on the information anomaly rate and a pre-configured error indication, and a judgment result of the sharing coefficient judgment is spliced with the characteristic content of the auxiliary information to obtain the anomaly indication information.
[0006] Furthermore, the step of calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index includes: A thread parsing method for calculating the real-time time node in combination with the patient's biochemical indicators, wherein the patient's biochemical indicators include at least: data interference, temperature error, and time error; Archiving the thread parsing method and the blood image serial number, and using the archiving result as a coefficient of a calculation network for calculating the information abnormality rate; The information anomaly rate is obtained by calculation through the computing network.
[0007] Furthermore, the patient state vector of the multimodal blood data of the abnormal information includes at least one coefficient selected from the following: a constraint of the multimodal blood data of the abnormal information, a characteristic content change of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information. Under the premise that the patient state vector of the multimodal blood data of the abnormal information includes the plurality of coefficients, the step of determining whether the patient state vector meets the first pre-configured requirement includes: In the blood attribute data, the patient state vector is determined to meet the first pre-configured requirement when one or two of the patient state vectors meet the following: a constraint on the multimodal blood data of the abnormal information in the blood attribute data is a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0008] Furthermore, the patient state vector of the multimodal blood data of the abnormal information includes: the constraints of the multimodal blood data of the abnormal information, changes in characteristic content of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information, wherein the step of determining whether the patient state vector meets the first pre-configured requirement includes: determining that the patient state vector meets the first pre-configured requirement when at least one of the patient state vectors in the blood attribute data meets the following: the constraints of the multimodal blood data of the abnormal information in the blood attribute data are a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0009] In a second aspect, a multimodal blood data fusion system is provided, comprising a solar energy collection device and a terminal server, wherein the solar energy collection device and the terminal server are communicatively connected, and the terminal server is specifically configured to: Obtaining blood attribute data of target multimodal blood data identified at a real-time time node and collected identification information, wherein the identification information at least includes: an identification factor and a blood image sequence number of the target multimodal blood data and a patient's biochemical index; Calculating abnormality indication information by combining the characteristic content of the blood attribute data and the identification information; When at least one description mode of the characteristic content in the blood attribute data matches the abnormality indication information, determining that the target multimodal blood data contains multimodal blood data with abnormal information; When it is determined that the multimodal blood data containing the abnormal information exists in the target multimodal blood data, acquiring blood attribute data of the target multimodal blood data identified after the real-time time node; selecting the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determining whether the patient state vector meets a first pre-configured requirement; When the patient state vector meets the first pre-configured requirement, a multimodal blood data fusion result of the target multimodal blood data is obtained.
[0010] Furthermore, the terminal server is specifically used for: Calculating characteristic contents of the auxiliary information of the blood attribute data by combining characteristic contents of each description mode in the blood attribute data; Calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index; A sharing coefficient judgment is performed on the information anomaly rate and a pre-configured error indication, and a judgment result of the sharing coefficient judgment is spliced with the characteristic content of the auxiliary information to obtain the anomaly indication information.
[0011] Furthermore, the terminal server is specifically used for: A thread parsing method for calculating the real-time time node in combination with the patient's biochemical indicators, wherein the patient's biochemical indicators include at least: data interference, temperature error, and time error; Archiving the thread parsing method and the blood image serial number, and using the archiving result as a coefficient of a calculation network for calculating the information abnormality rate; The information anomaly rate is obtained by calculation through the computing network.
[0012] Furthermore, the terminal server is specifically used for: In the blood attribute data, when one or two of the patient state vectors meet the following, it is determined that the patient state vector meets the first pre-configured requirement: the constraint of the multimodal blood data of the abnormal information in the blood attribute data is a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0013] Furthermore, the terminal server is specifically used for: the constraints of the multimodal blood data of the abnormal information, changes in characteristic content of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information, wherein the step of determining whether the patient state vector meets the first pre-configured requirement includes: determining that the patient state vector meets the first pre-configured requirement when at least one of the patient state vectors in the blood attribute data meets the following: the constraints of the multimodal blood data of the abnormal information in the blood attribute data are a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0014] The embodiment of the present application provides a multimodal blood data fusion method and system, which obtains blood attribute data of target multimodal blood data identified at a real-time time node, and the collected identification information, wherein the identification information at least includes: an identification factor and a blood image sequence number of the target multimodal blood data and a patient's biochemical index; calculates abnormal indication information based on the characteristic content of the blood attribute data and the identification information; determines that the target multimodal blood data contains abnormal information when at least one description method of the blood attribute data contains characteristic content that meets the fire source standard; and determines that the target multimodal blood data contains abnormal information when it is determined that the target multimodal blood data contains abnormal information. When the multimodal blood data of the target multimodal blood data is obtained, the blood attribute data of the target multimodal blood data identified after the real-time time node is obtained; the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data of abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node is selected, and it is determined whether the patient state vector meets the first pre-configured requirement; when the patient state vector meets the first pre-configured requirement, the content of the multimodal blood data fusion result in the target multimodal blood data is determined, so as to ensure the readiness of the recognition control and thus ensure the stability of the temperature throughout the day. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.
[0016] Figure 1 This is a flowchart of a multimodal blood data fusion method provided in an embodiment of the present application.
[0017] Figure 2 This is a block diagram of a multimodal blood data fusion device provided in an embodiment of the present application.
[0018] Figure 3 This is an architectural diagram of a multimodal blood data fusion system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0019] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.
[0020] See also Figure 1 , shows a multimodal blood data fusion method, which may include the technical solutions described in the following steps 100-600.
[0021] Step 100: Acquire blood attribute data of target multimodal blood data identified at a real-time time node and the collected identification information.
[0022] For example, the identification information at least includes: an identification factor, a blood image serial number of the target multimodal blood data, and a patient's biochemical index.
[0023] Step 200: Abnormal indication information is calculated by combining the characteristic content of the blood attribute data and the identification information.
[0024] For example, the abnormal indication information is used to indicate the presence of inaccurate information in the multimodal blood data fusion result.
[0025] Step 300: When at least one description mode of the characteristic content in the blood attribute data matches the abnormality indication information, it is determined that there is multimodal blood data with abnormal information in the target multimodal blood data.
[0026] Step 400 : When it is determined that the multimodal blood data containing the abnormal information exists in the target multimodal blood data, blood attribute data of the target multimodal blood data identified after the real-time time node is acquired.
[0027] Step 500: Select the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data of the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determine whether the patient state vector meets the first pre-configured requirement.
[0028] Step 600: When the patient state vector meets the first pre-configured requirement, a multimodal blood data fusion result of the target multimodal blood data is obtained.
[0029] It can be understood that when executing the technical solution described in the above steps 100 to 600, the blood attribute data of the target multimodal blood data identified at the real-time time node and the collected identification information are obtained, wherein the identification information at least includes: the identification factor and the blood image serial number of the target multimodal blood data and the patient's biochemical index; the abnormal indication information is calculated based on the characteristic content of the blood attribute data and the identification information; when the characteristic content of at least one description method in the blood attribute data meets the fire source standard, it is determined that the target multimodal blood data contains abnormal information; when it is determined that the target multimodal blood data contains abnormal information, the target multimodal blood data is detected as the target multimodal blood data. When multimodal blood data with normal information is obtained, blood attribute data of the target multimodal blood data identified after the real-time time node is obtained; the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data with abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node is selected, and it is determined whether the patient state vector meets the first pre-configured requirement; when the patient state vector meets the first pre-configured requirement, the content of the multimodal blood data fusion result in the target multimodal blood data is determined, so as to ensure the readiness of the recognition control and thus ensure the stability of the temperature throughout the day.
[0030] In an independently implemented embodiment, the inventors found that when combining the characteristic content of the blood attribute data and the identification information, there is a problem of inaccurate characteristic content of the auxiliary information of the blood attribute data, making it difficult to accurately calculate the abnormal indication information. In order to improve the above technical problem, the step of combining the characteristic content of the blood attribute data and the identification information to calculate the abnormal indication information described in step 200 can specifically include the technical solutions described in the following steps 210-230.
[0031] Step 210 : Calculate the feature content of the auxiliary information of the blood attribute data by combining the feature content of each description mode in the blood attribute data.
[0032] Step 220 , calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index.
[0033] Step 230 , performing a sharing coefficient judgment on the information anomaly rate and a pre-configured error indication, and concatenating the judgment result of the sharing coefficient judgment with the characteristic content of the auxiliary information to obtain the anomaly indication information.
[0034] It can be understood that when executing the technical solution described in the above steps 210-230, when combining the characteristic content of the blood attribute data and the identification information, the problem of inaccurate calculation of the characteristic content of the auxiliary information of the blood attribute data is avoided as much as possible, so that the abnormal indication information can be accurately calculated.
[0035] In an independently implemented embodiment, the inventors found that when combining the identification factor with the blood image serial number of the target multimodal blood data and the patient's biochemical indicators, there is a problem of inaccurate thread parsing method, which makes it difficult to accurately calculate the information anomaly rate of the real-time time node. In order to improve the above technical problem, the step described in step 220 of combining the identification factor with the blood image serial number of the target multimodal blood data and the patient's biochemical indicators to calculate the information anomaly rate of the real-time time node can specifically include the technical solutions described in the following steps 221-223.
[0036] Step 221 : Calculate the thread parsing mode of the real-time time node in combination with the patient's biochemical indexes, wherein the patient's biochemical indexes at least include: data interference, temperature error, and time error.
[0037] Step 222: Archiving the thread parsing method and the blood image serial number, and using the archiving result as a coefficient of a calculation network for calculating the information abnormality rate.
[0038] Step 223: Calculate the information anomaly rate through the computing network.
[0039] It can be understood that when executing the technical solution described in steps 221 to 223 above, when combining the identification factor with the blood image serial number of the target multimodal blood data and the patient's biochemical indicators, the problem of inaccurate thread parsing method is improved, so that the information anomaly rate of the real-time time node can be accurately calculated.
[0040] In an independently implemented embodiment, the inventors discovered that the patient state vector of the multimodal blood data of the abnormal information includes at least one of the following coefficients: a constraint on the multimodal blood data of the abnormal information, a characteristic content change of the multimodal blood data of the abnormal information, an allowable error range for the multimodal blood data of the abnormal information, and an allowable error value for the multimodal blood data of the abnormal information. If the patient state vector of the multimodal blood data of the abnormal information includes multiple coefficients, the patient state vector may be inaccurate, making it difficult to accurately determine whether the patient state vector meets the first pre-configured requirement. To improve the above technical problem, the patient state vector of the multimodal blood data of the abnormal information described in step 500 includes at least one of the following coefficients: a constraint on the multimodal blood data of the abnormal information, a characteristic content change of the multimodal blood data of the abnormal information, an allowable error range for the multimodal blood data of the abnormal information, and an allowable error value for the multimodal blood data of the abnormal information. If the patient state vector of the multimodal blood data of the abnormal information includes multiple coefficients, the step of determining whether the patient state vector meets the first pre-configured requirement may specifically include the technical solutions described in steps 510 through 540.
[0041] Step 510, in the blood attribute data, when one or two of the patient state vectors meet the following content, determine that the patient state vector meets the first pre-configured requirement: the constraint of the multimodal blood data of the abnormal information in the blood attribute data is a non-standard list.
[0042] Step 520 : The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes to decrease from bottom to top.
[0043] Step 530 : The error tolerance ranges of the multimodal blood data of the abnormal information in the blood attribute data are the same.
[0044] Step 540: The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0045] It can be understood that when executing the technical solution described in steps 510 to 540 above, the patient state vector of the multimodal blood data of the abnormal information includes at least one coefficient among the following: the constraint of the multimodal blood data of the abnormal information, the characteristic content change of the multimodal blood data of the abnormal information, the error allowable range of the multimodal blood data of the abnormal information, and the error allowable value of the multimodal blood data of the abnormal information. Under the premise that the patient state vector of the multimodal blood data of the abnormal information includes multiple coefficients, the problem of inaccuracy of the patient state vector is improved, so that it is possible to accurately judge whether the patient state vector meets the first pre-configured requirement.
[0046] In an independently implemented embodiment, the inventors found that when determining the patient state vector of the multimodal blood data of abnormal information, there is a problem of inaccurate changes in the characteristic content of the multimodal blood data, making it difficult to accurately determine the patient state vector of the multimodal blood data of abnormal information. In order to improve the above technical problem, the step of determining the patient state vector of the multimodal blood data of abnormal information described in step 500 can specifically include the technical solutions described in the following steps q1 to q4.
[0047] Step q1, the constraints of the multimodal blood data of the abnormal information, the characteristic content changes of the multimodal blood data of the abnormal information, the allowable error range of the multimodal blood data of the abnormal information, and the allowable error value of the multimodal blood data of the abnormal information, wherein the step of judging whether the patient state vector meets the first pre-configured requirement includes: in the blood attribute data, when at least one of the patient state vectors meets the following content, determining that the patient state vector meets the first pre-configured requirement: the constraints of the multimodal blood data of the abnormal information in the blood attribute data are a non-standard list.
[0048] Step q2: the characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes to decrease from bottom to top.
[0049] Step q3: The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range.
[0050] In step q4, the error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
[0051] It can be understood that when executing the technical solution described in steps q1 to q4 above, the patient state vector of the multimodal blood data of the abnormal information is improved, and the problem of inaccurate changes in the characteristic content of the multimodal blood data is improved, so that the patient state vector of the multimodal blood data of the abnormal information can be accurately determined.
[0052] In a possible embodiment, the inventors found that when the characteristic content of at least one description method in the blood attribute data meets the abnormal indication information, there is a problem of inaccurate projection points, which makes it difficult to accurately determine the multimodal blood data containing abnormal information in the target multimodal blood data. In order to improve the above technical problem, the step described in step 300 of determining the multimodal blood data containing abnormal information in the target multimodal blood data when the characteristic content of at least one description method in the blood attribute data meets the abnormal indication information can specifically include the technical solutions described in the following steps w1 to w5.
[0053] Step w1: Acquire first blood attribute data, where the first blood attribute data includes a plurality of blood data fusion directories, each of which includes a projection point of a list, and the list is a projection node including a plurality of projection points.
[0054] Step w2: Obtain confidence association indications of two adjacent projection points of a first projection point, where the first projection point is any projection point in the list.
[0055] Step w3: In combination with the confidence association indication of the two adjacent projection points in the first blood attribute data, the first projection point is switched from the first blood data fusion directory to the blood data fusion directory where one of the two adjacent projection points is located, to obtain second blood attribute data. The first blood data fusion directory is the blood data fusion directory where the first projection point is located.
[0056] Step w4: obtaining a confidence association indicator of each adjacent projection point of a second projection point, where the second projection point is any projection point in the list.
[0057] Step w5: When the maximum confidence association indication among the confidence association indications corresponding to each adjacent projection point exceeds a preset standard, the second projection point is switched from the second blood data fusion directory to the blood data fusion directory where the adjacent projection point corresponding to the maximum confidence association indication is located in the second blood attribute data, to obtain third blood attribute data. The second blood data fusion directory is the blood data fusion directory where the second projection point is located.
[0058] It can be understood that when executing the technical solution described in the above steps w1 to w5, when there is at least one characteristic content of the description method in the blood attribute data that meets the abnormal indication information, the problem of inaccurate projection points is improved, so that the multimodal blood data containing abnormal information in the target multimodal blood data can be accurately determined.
[0059] In a possible embodiment, the inventors found that when obtaining the confidence association indication of two adjacent projection points of the first projection point, there is a problem of inaccurate confidence association indication, making it difficult to accurately obtain the confidence association indication of two adjacent projection points of the first projection point. In order to improve the above technical problem, the step of obtaining the confidence association indication of two adjacent projection points of the first projection point described in step w2 can specifically include the technical solutions described in the following steps w21 and w22.
[0060] Step w21: Switch the first projection point from the first blood data fusion directory to the blood data fusion directory where the first adjacent projection point is located and obtain a first confidence association indication of all blood data fusion directories in real time, where the first confidence association indication is a confidence association indication of the first adjacent projection point, and the first adjacent projection point is any adjacent projection point of the first projection point.
[0061] Step w22: Switch the first projection point from the blood data fusion directory where the first adjacent projection point is located to the blood data fusion directory where the second adjacent projection point is located, and obtain a second confidence association indication of all blood data fusion directories in real time. The second confidence association indication is a confidence association indication of the second adjacent projection point, which is another adjacent projection point of the first projection point.
[0062] It can be understood that when executing the technical solutions described in the above steps w21 and w22, when obtaining the confidence association indication of two adjacent projection points of the first projection point, the problem of inaccurate confidence association indication is improved, so that the confidence association indication of two adjacent projection points of the first projection point can be accurately obtained.
[0063] In a possible embodiment, the inventors discovered that when adding the first projection point to the blood data fusion directory where one of the two adjacent projection points is located in combination with the confidence association indication of the two adjacent projection points, there is a problem of inaccurate indication judgment, making it difficult to accurately add the first projection point to the blood data fusion directory where one of the two adjacent projection points is located. In order to improve the above technical problem, the step described in step w3 of adding the first projection point to the blood data fusion directory where one of the two adjacent projection points is located in combination with the confidence association indication of the two adjacent projection points can specifically include the technical solutions described in the following steps w31 and w32.
[0064] Step w31: Select a maximum confidence association indication from the first confidence association indication and the second confidence association indication.
[0065] Step w32: when the maximum confidence correlation indicator is greater than zero, switching the first projection point from the blood data fusion directory where the second adjacent projection point is located to the blood data fusion directory where the adjacent projection point corresponding to the maximum confidence correlation indicator is located.
[0066] It can be understood that when executing the technical solutions described in the above steps w31 and w32, when adding the first projection point to the blood data fusion directory where one of the two adjacent projection points is located in combination with the confidence association indication of the two adjacent projection points, the problem of inaccurate indication judgment is improved, so that the first projection point can be accurately added to the blood data fusion directory where one of the two adjacent projection points is located.
[0067] Based on the above, please refer to Figure 2 , provides a multimodal blood data fusion device 200, applied to a terminal server, the device comprising: An information identification module 210 is configured to obtain blood attribute data of target multimodal blood data identified at a real-time time node, as well as collected identification information, wherein the identification information includes at least an identification factor and a blood image sequence number of the target multimodal blood data, and a patient's biochemical index; An information calculation module 220 is configured to calculate abnormality indication information by combining the characteristic content of the blood attribute data and the identification information; an information determining module 230 for determining that the target multimodal blood data contains multimodal blood data with abnormal information when at least one characteristic content of the description mode in the blood attribute data matches the abnormality indication information; An information acquisition module 240 is configured to, when it is determined that the target multimodal blood data contains the multimodal blood data with the abnormal information, acquire blood attribute data of the target multimodal blood data identified after the real-time time node; a requirement determination module 250 for selecting the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determining whether the patient state vector meets a first pre-configured requirement; The result fusion module 260 is configured to obtain a multimodal blood data fusion result of the target multimodal blood data when the patient state vector meets the first pre-configured requirement.
[0068] Based on the above, please refer to Figure 3, shows a multimodal blood data fusion system 300, including a processor 310 and a memory 320 communicating with each other, the processor 310 is used to obtain and execute a computer program from the memory 320 to implement the above method.
[0069] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.
[0070] In summary, based on the above scheme, the blood attribute data of the target multimodal blood data identified at the real-time time node and the collected identification information are obtained, wherein the identification information at least includes: the identification factor and the blood image serial number of the target multimodal blood data and the patient's biochemical index; the abnormal indication information is calculated based on the characteristic content of the blood attribute data and the identification information; when the characteristic content of at least one description method in the blood attribute data meets the fire source standard, it is determined that the target multimodal blood data contains multimodal blood data with abnormal information; when it is determined that the target multimodal blood data contains multimodal blood data with abnormal information When the target multimodal blood data is detected, blood attribute data of the target multimodal blood data identified after the real-time time node is obtained; the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node is selected, and it is determined whether the patient state vector meets the first pre-configured requirement; when the patient state vector meets the first pre-configured requirement, the content of the multimodal blood data fusion result in the target multimodal blood data is determined, so as to ensure the readiness of the recognition control and thus ensure the stability of the temperature throughout the day.
[0071] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of the present application. Not only can hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, they can also be implemented using software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).
[0072] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.
[0073] The basic concepts have been described above. It will be apparent to those skilled in the art that the detailed disclosure above is merely illustrative and does not limit the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to the present application. Such modifications, improvements, and amendments are suggested in the present application and remain within the spirit and scope of the exemplary embodiments of the present application.
[0074] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic associated with at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in at least one embodiment of this application may be appropriately combined.
[0075] In addition, it will be understood by those skilled in the art that various aspects of the present application can be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application can be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in no less than one computer-readable medium, which includes computer-readable program code.
[0076] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.
[0077] The computer program code required for the operation of the various parts of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. The program code can be executed entirely on the user's computer, or as a stand-alone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).
[0078] In addition, unless expressly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.
[0079] Similarly, it should be noted that, in order to simplify the presentation of this application and thereby facilitate understanding of at least one embodiment of the invention, the foregoing descriptions of the embodiments of this application sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this application requires more features than those recited in the claims. In practice, an embodiment may have fewer features than the totality of the features of a single embodiment disclosed above.
[0080] In some embodiments, numbers are used to describe the number of components and factors. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical coefficients used in the description and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical coefficients should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and coefficients used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values are as accurate as possible within the feasible range.
[0081] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflict with the content of this application, documents that limit the broadest scope of the claims of this application (in real time or subsequently attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the accompanying materials of this application are inconsistent or conflicting with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.
[0082] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this application may be considered consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.
[0083] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.
Claims
1. A multimodal blood data fusion method, characterized in that: The method comprises: Obtaining blood attribute data of target multimodal blood data identified at a real-time time node and collected identification information, wherein the identification information at least includes: an identification factor and a blood image sequence number of the target multimodal blood data and a patient's biochemical index; Calculating abnormality indication information by combining the characteristic content of the blood attribute data and the identification information; When at least one description mode of the characteristic content in the blood attribute data matches the abnormality indication information, determining that the target multimodal blood data contains multimodal blood data with abnormal information; When it is determined that the multimodal blood data containing the abnormal information exists in the target multimodal blood data, acquiring blood attribute data of the target multimodal blood data identified after the real-time time node; selecting the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determining whether the patient state vector meets a first pre-configured requirement; When the patient state vector meets the first pre-configured requirement, a multimodal blood data fusion result of the target multimodal blood data is obtained.
2. The method according to claim 1, characterized in that The step of calculating abnormal indication information by combining the characteristic content of the blood attribute data and the identification information includes: Calculating characteristic contents of the auxiliary information of the blood attribute data by combining characteristic contents of each description mode in the blood attribute data; Calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index; A sharing coefficient judgment is performed on the information anomaly rate and a pre-configured error indication, and a judgment result of the sharing coefficient judgment is spliced with the characteristic content of the auxiliary information to obtain the anomaly indication information.
3. The method according to claim 2, characterized in that The step of calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index includes: A thread parsing method for calculating the real-time time node in combination with the patient's biochemical indicators, wherein the patient's biochemical indicators include at least: data interference, temperature error, and time error; Archiving the thread parsing method and the blood image serial number, and using the archiving result as a coefficient of a calculation network for calculating the information abnormality rate; The information anomaly rate is obtained by calculation through the computing network.
4. The method according to claim 1, wherein The patient state vector of the multimodal blood data of the abnormal information includes at least one coefficient selected from the following: a constraint of the multimodal blood data of the abnormal information, a characteristic content change of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information. Under the premise that the patient state vector of the multimodal blood data of the abnormal information includes the plurality of coefficients, the step of determining whether the patient state vector meets a first pre-configured requirement includes: In the blood attribute data, the patient state vector is determined to meet the first pre-configured requirement when one or two of the patient state vectors meet the following: a constraint on the multimodal blood data of the abnormal information in the blood attribute data is a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
5. The method according to claim 1, wherein The patient state vector of the multimodal blood data of the abnormal information includes: the constraints of the multimodal blood data of the abnormal information, changes in characteristic content of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information, wherein the step of determining whether the patient state vector meets the first pre-configured requirement includes: determining that the patient state vector meets the first pre-configured requirement when at least one of the patient state vectors in the blood attribute data meets the following: the constraints of the multimodal blood data of the abnormal information in the blood attribute data are a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
6. A multimodal blood data fusion system, characterized in that: The solar energy collection device and the terminal server are connected in communication with each other, and the terminal server is specifically used for: Obtaining blood attribute data of target multimodal blood data identified at a real-time time node and collected identification information, wherein the identification information at least includes: an identification factor and a blood image sequence number of the target multimodal blood data and a patient's biochemical index; Calculating abnormality indication information by combining the characteristic content of the blood attribute data and the identification information; When at least one description mode of the characteristic content in the blood attribute data matches the abnormality indication information, determining that the target multimodal blood data contains multimodal blood data with abnormal information; When it is determined that the multimodal blood data containing the abnormal information exists in the target multimodal blood data, acquiring blood attribute data of the target multimodal blood data identified after the real-time time node; selecting the blood attribute data of the target multimodal blood data identified at the real-time time node, or the patient state vector of the multimodal blood data containing the abnormal information in the blood attribute data of the target multimodal blood data identified after the real-time time node, and determining whether the patient state vector meets a first pre-configured requirement; When the patient state vector meets the first pre-configured requirement, a multimodal blood data fusion result of the target multimodal blood data is obtained.
7. The system according to claim 6, characterized in that The terminal server is specifically used for: Calculating characteristic contents of the auxiliary information of the blood attribute data by combining characteristic contents of each description mode in the blood attribute data; Calculating the information abnormality rate of the real-time time node by combining the identification factor with the blood image sequence number of the target multimodal blood data and the patient's biochemical index; A sharing coefficient judgment is performed on the information anomaly rate and a pre-configured error indication, and a judgment result of the sharing coefficient judgment is spliced with the characteristic content of the auxiliary information to obtain the anomaly indication information.
8. The system according to claim 7, characterized in that The terminal server is specifically used for: A thread parsing method for calculating the real-time time node in combination with the patient's biochemical indicators, wherein the patient's biochemical indicators include at least: data interference, temperature error, and time error; Archiving the thread parsing method and the blood image serial number, and using the archiving result as a coefficient of a calculation network for calculating the information abnormality rate; The information anomaly rate is obtained by calculation through the computing network.
9. The system according to claim 6, wherein: The terminal server is specifically used for: In the blood attribute data, when one or two of the patient state vectors meet the following, it is determined that the patient state vector meets the first pre-configured requirement: the constraint of the multimodal blood data of the abnormal information in the blood attribute data is a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.
10. The system according to claim 6, wherein: The terminal server is specifically used for: the constraints of the multimodal blood data of the abnormal information, changes in characteristic content of the multimodal blood data of the abnormal information, an allowable error range of the multimodal blood data of the abnormal information, and an allowable error value of the multimodal blood data of the abnormal information, wherein the step of determining whether the patient state vector meets the first pre-configured requirement includes: determining that the patient state vector meets the first pre-configured requirement when at least one of the patient state vectors in the blood attribute data meets the following: the constraints of the multimodal blood data of the abnormal information in the blood attribute data are a non-standard list; The characteristic content of the multimodal blood data of the abnormal information in the blood attribute data changes in a manner that decreases from bottom to top; The error tolerance range of the multimodal blood data of the abnormal information in the blood attribute data is the same range; The error tolerance value of the multimodal blood data of the abnormal information in the blood attribute data reaches a pre-configured value range.