Intelligent cognitive method and intelligent cognitive system for bacterial dysentery based on ICP algorithm

Abstract

The application discloses a kind of bacterial dysentery intelligent cognitive method and intelligent cognitive system based on ICP algorithm, belong to auxiliary diagnosis technical field, intelligent cognitive method includes: obtaining the relevant diagnosis basis of professional medical institutions about bacterial dysentery, establishes bacterial dysentery diagnosis basis standard information base;The relevant diagnosis basis of bacterial dysentery in bacterial dysentery diagnosis basis standard information base is normalized, and the feature information set of bacterial dysentery clinical classification is obtained;According to the feature information set of bacterial dysentery clinical classification, extract relevant diagnosis basis rule, establish bacterial dysentery diagnosis rule base;Using improved ICP algorithm, bacterial dysentery automatic registration model is established;According to bacterial dysentery automatic registration model, the information and data provided by target bacterial dysentery patient are registered and cognitively analyzed, and the corresponding cognitive report of bacterial dysentery case is generated, and diagnostic conclusion is given.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of auxiliary diagnosis, and particularly relates to a bacterial dysentery intelligent cognition method based on an ICP algorithm and an intelligent cognition system. BACKGROUND

[0002] Bacterial dysentery (bacillary dysentery) is also called shigellosis, which is an intestinal infectious disease caused by Shigella. After Shigella infects the human body through the digestive tract, it causes inflammation and ulceration of the colon mucosa and releases toxins into the blood. The clinical manifestations mainly include fever, abdominal pain, diarrhea, tenesmus, mucopurulent bloody stool, and systemic toxemia symptoms. Severe cases can cause septic shock and / or toxic encephalopathy. Bacterial dysentery is a common and frequently-occurring disease in China, which is often sporadic and more common in summer and autumn. Children and young adults are high-risk groups.

[0003] Traditional bacterial dysentery is mainly diagnosed based on epidemiological history, symptoms, signs and laboratory examination. If a definite diagnosis is to be made, it also depends on the etiological examination, that is, the fecal culture of Shigella dysenteriae, which can only be used to diagnose bacterial dysentery. Because the types of Shigella dysenteriae entering the human body are different, the number is different, and the resistance of each person is different, the clinical symptoms of bacterial dysentery are also different. Because the traditional method relies more on the experience of doctors, especially some ambiguous, seemingly correct characteristic information and data, sometimes it is difficult to judge or make correct decisions, resulting in false negatives and false positives. Clinical work still faces great pressure, so it is more meaningful to explore new, safe and efficient rapid and accurate cognitive diagnosis methods for bacterial dysentery in clinical application. Therefore, an intelligent bacterial dysentery cognition system is urgently needed to quickly and intelligently accurately judge bacterial dysentery. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a bacterial dysentery intelligent cognition method and system based on an ICP (Iterative Closest Point) algorithm, which can solve the technical problem that the current traditional bacterial dysentery diagnosis relies more on the experience of doctors, which is easy to cause false negatives and false positives.

[0005] In order to solve the above technical problems, the present application is implemented as follows:

[0006] In a first aspect, the embodiments of the present application provide a bacterial dysentery intelligent cognition method based on an ICP algorithm, comprising:

[0007] S101: Obtain relevant diagnosis basis of bacterial dysentery of a professional medical institution, and establish a bacterial dysentery diagnosis basis standard information base;

[0008] S102: normalizing the relevant diagnostic basis of the bacterial dysentery in the bacterial dysentery diagnosis basis information base to obtain a feature information set of bacterial dysentery clinical typing;

[0009] S103: extracting a relevant diagnostic basis rule according to the feature information set of bacterial dysentery clinical typing, and establishing a bacterial dysentery diagnosis rule base;

[0010] S104: establishing an automatic registration model of bacterial dysentery by using an improved ICP algorithm;

[0011] S105: registering and cognitively analyzing information and data provided by a target bacterial dysentery patient according to the automatic registration model of bacterial dysentery, generating a cognitive report of the corresponding bacterial dysentery case, and giving a diagnosis conclusion.

[0012] Optionally, the relevant diagnostic basis of the bacterial dysentery includes epidemiological history information, clinical manifestation information and laboratory detection data.

[0013] Optionally, the bacterial dysentery clinical typing includes acute ordinary type, acute mild type, acute toxic type and chronic type.

[0014] Optionally, the S104 specifically includes:

[0015] S1041: taking the multi-source feature information set of the target bacterial dysentery patient as a target point cloud P, and selecting a target point p i from the target point cloud P, wherein p i ∈P;

[0016] S1042: taking the bacterial dysentery diagnosis basis standard information set as a source point cloud Q, and finding a corresponding point q i from the source point cloud Q, wherein q i ∈Q, so that the distance between the corresponding point q i and the target point p i is the smallest, that is, ||q i -p i ||=min;

[0017] S1043: calculating a rotation matrix R and a translation matrix t according to the error function calculation formula shown in formula 1, so that the error function value is the smallest;

[0018]

[0019] wherein n is the number of the nearest point pairs, R is the rotation matrix, and t is the translation vector;

[0020] S1044: According to formula 2, the target point p i performing rotation and translation transformation to obtain the transformed target point p i ’;

[0021] p i ’=R p i +t Formula 2

[0022] S1045: According to formula 3, calculate the average distance d between the transformed target point p i ’ and the corresponding point q i ’;

[0023]

[0024] S1046: When the average distance d is less than the preset threshold or the iteration number is greater than the preset iteration number, stop the iterative calculation; otherwise, return to S1042 until the convergence condition is met.

[0025] Optionally, the diagnostic conclusion includes confirming the target bacterial dysentery patient as a suspected case, a clinically diagnosed case or a confirmed case.

[0026] In a second aspect, an embodiment of the present application provides a bacterial dysentery intelligent cognitive system based on an ICP algorithm, comprising:

[0027] A diagnosis basis module is configured to obtain relevant diagnosis basis of bacterial dysentery from professional medical institutions, and establish a bacterial dysentery diagnosis basis standard information base.

[0028] A data processing module is configured to normalize the relevant diagnosis basis of bacterial dysentery in the bacterial dysentery diagnosis basis standard information base, and obtain a feature information set of bacterial dysentery clinical classification.

[0029] A rule establishment module is configured to extract relevant diagnosis basis rules according to the feature information set of bacterial dysentery clinical classification, and establish a bacterial dysentery diagnosis rule base.

[0030] A cognitive model module is configured to establish an automatic registration model of bacterial dysentery by using an improved ICP algorithm.

[0031] An auxiliary diagnosis module is configured to register and cognitively analyze information and data provided by a target bacterial dysentery patient according to the automatic registration model of bacterial dysentery, generate a corresponding cognitive report of the bacterial dysentery case, and give a diagnostic conclusion.

[0032] Optionally, the relevant diagnosis basis of bacterial dysentery includes epidemiological history information, clinical manifestation information and laboratory test data.

[0033] Optionally, the bacterial dysentery clinical classification includes acute ordinary type, acute mild type, acute toxic type and chronic type.

[0034] Optionally, the cognitive model module specifically comprises:

[0035] a target point selection sub-module, configured to take the multi-source feature information set of the target bacillary dysentery patient as a target point cloud P, and select a target point p i from the target point cloud P; i ∈P;

[0036] a corresponding point calculation sub-module, configured to take the bacillary dysentery diagnosis basis standard information set as a source point cloud Q, and find a corresponding point q i from the source point cloud Q; i ∈Q, such that the distance between the corresponding point q i and the target point p i is minimum, i.e., ||q i -p i ||=min;

[0037] a matrix calculation sub-module, configured to calculate a rotation matrix R and a translation matrix t according to an error function calculation formula shown in Formula 1, such that the error function value is minimum;

[0038]

[0039] wherein n is the number of the nearest point pairs, R is the rotation matrix, and t is the translation vector;

[0040] a transformation sub-module, configured to perform rotation and translation transformation on the target point p i according to Formula 2, to obtain a transformed target point p

[0041] i’; i ’=R p i +t Formula 2

[0042] a distance calculation sub-module, configured to calculate the average distance d between the transformed target point p i’ and the corresponding point q

[0043] i according to Formula 3;

[0044] a stop iteration sub-module, configured to stop the iteration calculation when the average distance d is less than a preset threshold value or the iteration number is greater than a preset iteration number; otherwise, return to S1042 until the convergence condition is met.

[0045] Optionally, the diagnosis conclusion comprises confirming the target bacillary dysentery patient as a suspected case, a clinically diagnosed case or a definitely diagnosed case.

[0046] In the embodiment of the present application, the improved ICP algorithm is used to establish an automatic registration model of bacillary dysentery, and the information and data provided by the target bacillary dysentery patient are registered and cognitively analyzed according to the automatic registration model of bacillary dysentery, and a diagnosis conclusion is given. Not only can the speed of bacillary dysentery cognition and diagnosis be improved, but also the experience factor of relying too much on doctors can be avoided, the accuracy of bacillary dysentery cognition and diagnosis can be improved, and the workload of medical workers can be reduced and the work efficiency can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a flowchart of a bacillary dysentery intelligent cognition method based on an ICP algorithm provided by the embodiment of the present application.

[0048] Figure 2 is a structural schematic diagram of a bacillary dysentery intelligent cognition system based on an ICP algorithm provided by the embodiment of the present application.

[0049] The implementation of the object, functional characteristics and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0050] In order to make the object, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be described clearly and completely in combination with the drawings in the embodiment of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0051] The terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" and the like are generally a class, and are not limited to the number of objects, for example, the first object can be one or more.

[0052] The bacillary dysentery intelligent cognition method based on the ICP algorithm provided by the embodiment of the present application will be described in detail in combination with the drawings and specific embodiments and application scenarios.

[0053] Embodiment one

[0054] Reference Figure 1 is a flowchart of a bacillary dysentery intelligent cognition method based on an ICP algorithm provided by the embodiment of the present application. is a flowchart of a bacillary dysentery intelligent cognition method based on an ICP algorithm provided by the embodiment of the present application.

[0055] The application provides an intelligent cognitive method for bacterial dysentery based on an ICP algorithm, and the method comprises the following steps:

[0056] S101: Obtain relevant diagnosis bases of bacterial dysentery of professional medical institutions, and establish a standard information base of bacterial dysentery diagnosis bases.

[0057] The relevant diagnosis bases of bacterial dysentery comprise epidemiological history information, clinical manifestation information and laboratory detection data. The laboratory detection data can be detection data such as routine fecal examination and pathogen examination.

[0058] For example, the standard information of clinical symptoms and signs of the incubation period of bacterial dysentery is as follows: sudden onset, chills, chill and high fever, followed by abdominal pain, diarrhea and tenesmus, 10-20 times of defecation per day, but not much, and the stool is purulent and bloody, and moderate systemic toxic symptoms; severe patients are accompanied by convulsions, headache, and systemic muscle soreness, and can also cause dehydration and electrolyte disturbance, and can have left lower abdominal tenderness and hyperactive bowel sounds. The above clinical symptoms and sign standard information can be recorded as the relevant diagnosis bases of bacterial dysentery in the standard information base of bacterial dysentery diagnosis bases.

[0059] S102: Normalize the relevant diagnosis bases of bacterial dysentery in the standard information base of bacterial dysentery diagnosis bases, and obtain a feature information set of clinical classification of bacterial dysentery.

[0060] The clinical classification of bacterial dysentery comprises acute ordinary type, acute mild type, acute toxic type and chronic.

[0061] It should be noted that the diagnosis bases recorded in the standard information base of bacterial dysentery diagnosis bases are associated with the clinical classification of bacterial dysentery. For example, part of the diagnosis bases are classified as the diagnosis bases of acute ordinary type, and another part of the diagnosis bases are classified as the diagnosis bases of acute mild type.

[0062] For example, the clinical symptoms and signs of acute ordinary type (typical) mainly include: sudden onset, chills, fever, and can be accompanied by anemic symptoms such as fatigue, headache, poor appetite, diarrhea, abdominal pain, tenesmus, purulent and bloody stool or mucous stool, and left lower abdominal tenderness, and at this time, the part of the diagnosis bases is associated with the acute ordinary type (typical). The clinical symptoms and signs of acute mild type (atypical) mainly include: mild symptoms, and can only have diarrhea and loose stool, and at this time, the part of the diagnosis bases is associated with the acute mild type (atypical).

[0063] S103: According to the feature information set of the clinical classification of bacterial dysentery, relevant diagnosis basis rules are extracted, and a bacterial dysentery diagnosis rule base is established.

[0064] It should be noted that the diagnostic rule should be some conditions that must be met to make a correct diagnosis.

[0065] For example, no matter what the clinical classification of bacterial dysentery is, the patient has a history of unclean diet and / or contact with dysentery patients. At this time, the history of unclean diet and / or contact with dysentery patients can be used as a diagnostic rule for diagnosing bacterial dysentery.

[0066] For example, to make a final diagnosis of bacterial dysentery, it is necessary to rely on etiological examination, etc. At this time, it can also be used as a diagnostic rule for diagnosing bacterial dysentery.

[0067] S104: An automatic registration model for bacterial dysentery is established by using an improved ICP (Iterative Closest Point) algorithm.

[0068] It should be noted that the automatic registration technology of the ICP algorithm is to calculate the misalignment between two point clouds by using a certain algorithm or statistical rule through a computer, so as to achieve the effect of automatic registration of the two point clouds. In fact, the essence is to transform the data point clouds obtained in different coordinate systems to obtain an overall data model. The key problem is how to obtain the rotation matrix R and the translation vector t of the coordinate transformation, so that the distance between the three-dimensional data measured in two perspectives after coordinate transformation is minimized.

[0069] In one possible implementation, step S104 can be completed by sub-step S1041 to sub-step S1046:

[0070] S1041: A multi-source feature information set of a target bacterial dysentery patient is taken as a target point cloud P, and a target point p is selected in the target point cloud P i , wherein p i ∈P.

[0071] S1042: A bacterial dysentery diagnosis basis standard information set is taken as a source point cloud Q, and a corresponding point q is searched in the source point cloud Q i , wherein q i ∈Q, so that the distance between the corresponding point q i and the target point p i is minimized, that is, ||q i -p i ||=min.

[0072] S1043: The rotation matrix R and the translation matrix t are calculated according to the error function calculation formula shown in formula 1, so that the error function value is minimized.

[0073]

[0074] wherein n is the number of the nearest point pairs, R is a rotation matrix, and t is a translation vector.

[0075] S1044: Rotates and translates the target point p i to obtain the transformed target point p i'according to Formula 2.

[0076] p i ' = R p i + t Formula 2

[0077] S1045: Calculates the average distance d between the transformed target point p i'and the corresponding point q i according to Formula 3.

[0078]

[0079] S1046: When the average distance d is less than a preset threshold or the number of iterations is greater than a preset number of iterations, the iterative calculation is stopped. Otherwise, returns to S1042 until the convergence condition is met.

[0080] Specifically, in the overlapping region of the two sets of point cloud data to be matched, two point sets are selected to represent the source point set and the target point set, respectively, wherein P = {p i | p i ∈ R3, i = 1, 2, … n} is the source point set, Q = {q j | q j ∈ R3, j = 1, 2, … m} is the target point set, and m and n are the sizes of the two point sets, respectively. Let R be the rotation matrix and t be the translation matrix, and f(R, t) represent the error between the source point set P and the target point set Q under the transformation matrix (R, t). Then the problem of solving the optimal transformation matrix can be converted into solving the optimal solution (R, t) that satisfies min(f(R, t)). Wherein,

[0081]

[0082] S105: According to the automatic registration model of bacillary dysentery, the information and data provided by the target bacillary dysentery patient are registered and cognitively analyzed, a cognitive report of the corresponding bacillary dysentery case is generated, and a diagnosis conclusion is given.

[0083] Wherein, the diagnosis conclusion includes confirming the target bacillary dysentery patient as a suspected case, a clinically diagnosed case or a confirmed case.

[0084] For example, if the patient has diarrhea, bloody or mucous stool or watery stool or loose stool, accompanied by symptoms such as tenesmus, etc., and has not yet been determined to be caused by other reasons, the diagnosis conclusion of a suspected case can be made.

[0085] For example, if a patient meets the following conditions 3.1, 3.2 and 3.3.1 simultaneously and is excluded from diarrhea caused by other reasons, the diagnosis of a clinical diagnosis case can be made.

[0086] Among them, 3.1 epidemiological history: the patient has a history of unclean diet and / or contact with dysentery patients;

[0087] 3.2 clinical manifestations: 3.2.1 incubation period: several hours to 7 days, usually 1-3 days; 3.2.2 clinical symptoms and signs: sudden onset, chills, fever, followed by abdominal pain, diarrhea and tenesmus, 10-20 times a day, but the amount is not much, and the stool is bloody and purulent, and there are moderate systemic symptoms. Severe patients have convulsions, headache, muscle soreness, and can cause dehydration and electrolyte imbalance, and can have left lower abdominal pain and increased bowel sounds.

[0088] 3.3 laboratory examination: 3.3.1 fecal routine examination, white blood cells or pus cells ≥ 15 / HPE (400 times), red blood cells, phagocytes, etc. can be seen; 3.3.2 etiology examination, fecal culture of Shigella positive.

[0089] For example, if a patient meets the following conditions 3.1, 3.2 and 3.3 simultaneously, the diagnosis of a confirmed case can be made.

[0090] In the embodiment of the application, the improved ICP algorithm is used to establish an automatic registration model of bacterial dysentery, and the information and data provided by the target bacterial dysentery patient are registered and cognitively analyzed by the automatic registration model of bacterial dysentery, and a diagnosis conclusion is given. Not only can the speed of bacterial dysentery cognition and diagnosis be improved, but also the dependence on the experience of doctors can be avoided, the accuracy of bacterial dysentery cognition and diagnosis can be improved, and the workload of medical workers can be reduced and the work efficiency can be improved.

[0091] Example two

[0092] Reference Figure 2 Fig. 1 shows a structural schematic diagram of an intelligent bacterial dysentery cognition system 20 provided by the embodiment of the application.

[0093] The intelligent cognition system 20 comprises:

[0094] The diagnosis basis module 201 is configured to acquire relevant diagnosis basis of bacterial dysentery from professional medical institutions, and establish a bacterial dysentery diagnosis basis standard information database.

[0095] The data processing module 202 is configured to normalize the relevant diagnosis basis of the bacillary dysentery in the bacillary dysentery diagnosis basis standard information base to obtain a feature information set of the clinical classification of the bacillary dysentery.

[0096] The rule establishing module 203 is configured to extract the relevant diagnosis basis rules according to the feature information set of the clinical classification of the bacillary dysentery, and establish a bacillary dysentery diagnosis rule base.

[0097] The cognitive model module 204 is configured to establish an automatic registration model of the bacillary dysentery by using the improved ICP algorithm.

[0098] The auxiliary diagnosis module 205 is configured to register and cognitively analyze the information and data provided by a target bacillary dysentery patient according to the automatic registration model of the bacillary dysentery, generate a cognitive report of the corresponding bacillary dysentery case, and give a diagnosis conclusion.

[0099] Optionally, the relevant diagnosis basis of the bacillary dysentery includes epidemiological history information, clinical manifestation information and laboratory detection data.

[0100] Optionally, the clinical classification of the bacillary dysentery includes acute ordinary type, acute mild type, acute toxic type and chronic type.

[0101] Optionally, the cognitive model module 204 specifically includes:

[0102] The target point selection sub-module 2041 is configured to take the multi-source feature information set of the target bacillary dysentery patient as a target point cloud P, and select a target point p i from the target point cloud P, where p i ∈P.

[0103] The corresponding point calculation sub-module 2042 is configured to take the bacillary dysentery diagnosis basis standard information set as a source point cloud Q, and find a corresponding point q i from the source point cloud Q, where q i ∈Q, so that the distance between the corresponding point q i and the target point p i is the smallest, that is, ||q i -p i ||=min.

[0104] The matrix calculation sub-module 2043 is configured to calculate a rotation matrix R and a translation matrix t according to an error function calculation formula shown in formula 1, so that the error function value is the smallest.

[0105]

[0106] where n is the number of the nearest neighbor point pairs, R is the rotation matrix, and t is the translation vector.

[0107] Transformation submodule 2044 is used to transform the target point p according to formula 2. i Perform rotation and translation transformations to obtain the transformed target point pi';

[0108] p i '=R p i +t Formula 2

[0109] The distance calculation submodule 2045 is used to calculate the average distance d between the transformed target point pi' and the corresponding point qi according to formula 3.

[0110]

[0111] The Stop Iteration submodule 2046 is used to stop the iterative calculation when the average distance d is less than a preset threshold or the number of iterations is greater than a preset number of iterations; otherwise, it returns to S1042 until the convergence condition is met.

[0112] Optionally, the diagnostic conclusion may include identifying the target bacterial dysentery patient as a suspected case, a clinically diagnosed case, or a confirmed case.

[0113] The intelligent cognitive system 20 provided in this embodiment of the invention can realize the various processes implemented in the above method embodiments, and will not be repeated here to avoid repetition.

[0114] In this embodiment of the invention, an improved ICP algorithm is used to establish an automatic registration model for bacterial dysentery. This model is then used to register and analyze information and data provided by target bacterial dysentery patients, and to provide a diagnostic conclusion. This not only improves the speed of bacterial dysentery recognition and diagnosis but also avoids over-reliance on doctors' experience, thus improving the accuracy of bacterial dysentery recognition and diagnosis. Simultaneously, it reduces the workload of medical staff and improves work efficiency.

[0115] The virtual system in this embodiment of the invention may be a device, or a component, integrated circuit, or chip in a terminal.

[0116] Furthermore, it should be noted that the device embodiments described above are merely illustrative and do not constitute a limitation on the scope of protection of the present invention. In practical applications, those skilled in the art can select some or all of the modules to achieve the purpose of the embodiment according to actual needs, and no restrictions are imposed here.

[0117] In addition, for technical details not described in detail in this embodiment, please refer to the intelligent cognitive method and system provided in any embodiment of the present invention, which will not be repeated here.

[0118] The above merely provides the preferred embodiment of the present application, and is not used to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for intelligent cognition of bacterial dysentery based on the ICP algorithm, characterized in that, include: S101: Obtain relevant diagnostic evidence for bacterial dysentery from professional medical institutions and establish a database of diagnostic criteria for bacterial dysentery. S102: Normalize the relevant diagnostic criteria for bacterial dysentery in the bacterial dysentery diagnostic criteria information database to obtain a set of characteristic information for clinical classification of bacterial dysentery; the relevant diagnostic criteria for bacterial dysentery include epidemiological history information, clinical manifestation information and laboratory test data; the clinical classification of bacterial dysentery includes acute common type, acute mild type, acute toxic type and chronic type; S103: Based on the characteristic information set of the clinical classification of bacterial dysentery, extract relevant diagnostic rules and establish a bacterial dysentery diagnostic rule base; S104: An automatic registration model for bacterial dysentery is established using an improved ICP algorithm, including: S1041: The multi-source feature information set of the target bacterial dysentery patient is used as the target point cloud P, and a target point p is selected in the target point cloud P. i , where p i ∈P; S1042: Using the set of diagnostic criteria information for bacterial dysentery as the source point cloud Q, find a corresponding point q in the source point cloud Q. i , where q i ∈Q, such that the corresponding point q i With target point p i The distance between them is minimized, i.e., ||q i -p i ||=min; S1043: Calculate the rotation matrix R and translation matrix t according to the error function calculation formula shown in Formula 1, so as to minimize the error function value; Formula 1 Where n is the number of nearest neighbor pairs, R is the rotation matrix, and t is the translation vector; S1044: Apply Formula 2 to the target point p i Perform rotation and translation transformations to obtain the transformed target point pi'; p i '=R p i + t Formula 2 S1045: Calculate the average distance d between the transformed target point pi' and the corresponding point qi according to Formula 3; Formula 3 S1046: Stop the iterative calculation when the average distance d is less than the preset threshold or the number of iterations is greater than the preset number of iterations; otherwise, return to S1042 until the convergence condition is met. S105: Based on the bacterial dysentery automatic registration model, register and perform cognitive analysis on the information and data provided by the target bacterial dysentery patient, generate a corresponding cognitive report of the bacterial dysentery case, and give a diagnostic conclusion, the diagnostic conclusion including confirming the target bacterial dysentery patient as a suspected case, a clinically diagnosed case, or a confirmed case.

2. A bacterial dysentery intelligent cognitive system based on the ICP algorithm, characterized in that, include: The diagnostic criteria module is used to obtain relevant diagnostic criteria for bacterial dysentery from professional medical institutions and to establish a database of diagnostic criteria standards for bacterial dysentery. The data processing module is used to normalize the relevant diagnostic criteria for bacterial dysentery in the bacterial dysentery diagnostic criteria standard information database to obtain a set of characteristic information for the clinical classification of bacterial dysentery; the relevant diagnostic criteria for bacterial dysentery include epidemiological history information, clinical manifestation information and laboratory test data; the clinical classification of bacterial dysentery includes acute common type, acute mild type, acute toxic type and chronic type; The rule establishment module is used to extract relevant diagnostic rules based on the characteristic information set of the clinical classification of bacterial dysentery and establish a bacterial dysentery diagnosis rule base. The cognitive model module is used to build an automatic registration model for bacterial dysentery using an improved ICP algorithm. The cognitive model module specifically includes: The target point selection submodule is used to select a target point p from the multi-source feature information set of the target bacterial dysentery patient as the target point cloud P. i , where p i ∈P; The corresponding point calculation submodule is used to take the set of diagnostic criteria information for bacterial dysentery as the source point cloud Q, and find a corresponding point q in the source point cloud Q. i , where q i ∈Q, such that the corresponding point q i With target point p i The distance between them is minimized, i.e., ||q i -p i ||=min; The matrix calculation submodule is used to calculate the rotation matrix R and translation matrix t according to the error function calculation formula shown in Formula 1, so as to minimize the error function value. Formula 1 Where n is the number of nearest neighbor pairs, R is the rotation matrix, and t is the translation vector; The transformation submodule is used to transform the target point p according to formula 2. i Perform rotation and translation transformations to obtain the transformed target point pi'; p i '=R p i + t Formula 2 The distance calculation submodule is used to calculate the average distance d between the transformed target point pi' and the corresponding point qi according to Formula 3. Formula 3 The Stop Iteration submodule is used to stop the iterative calculation when the average distance d is less than a preset threshold or the number of iterations is greater than a preset number of iterations; otherwise, return to S1042 until the convergence condition is met. The auxiliary diagnostic module is used to register and perform cognitive analysis on the information and data provided by the target bacterial dysentery patient according to the bacterial dysentery automatic registration model, generate a corresponding cognitive report of the bacterial dysentery case, and give a diagnostic conclusion, which includes confirming the target bacterial dysentery patient as a suspected case, a clinically diagnosed case, or a confirmed case.

Images