Medical information data query method and system based on artificial intelligence

Abstract

The invention provides a medical information data query method and system based on artificial intelligence, and relates to the field of data processing.The system comprises a data acquisition module used for acquiring medical data; the data processing module is used for preprocessing the medical data; the data encryption module is used for encrypting the preprocessed medical data; the data storage module is used for storing the encrypted medical data; the data query module is used for receiving a data query request of the patient end or the medical care end, performing permission verification on the patient end or the medical care end based on the data query request, determining target medical data corresponding to the data query request through artificial intelligence after the permission verification, and feeding back the target medical data to the patient end or the medical care end; the method has the advantage of improving the intelligence of medical data query.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a medical information data query method and system based on artificial intelligence. Background Art

[0002] Medical data is becoming increasingly centralized. In accessing massive medical data, there are services for large-scale data statistics and calculations, and the fastest possible query response time is required. Due to the large scale of medical data and the strong correlation between medical data, different types of users have different perspectives on the same data, which places high demands on the storage model of medical data to cope with flexible and changeable data requests. There are also a large number of known or unknown data analysis requirements on large-scale data, and there are many types of queries, which need to support various customized queries. It can be seen that due to the high requirements of users for querying medical data, the existing medical data storage system simply uses traditional databases, commercial parallel databases or SQL databases to perform online query analysis on massive medical data and then return the results. The method can no longer meet the actual situation and needs.

[0003] Therefore, there is a need to provide an artificial intelligence-based medical information query method and system to improve the intelligence of medical data query. Summary of the invention

[0004] The present invention provides a medical information data query system based on artificial intelligence, comprising: a data acquisition module, used to acquire medical data; a data processing module, used to preprocess the medical data; a data encryption module, used to encrypt the preprocessed medical data; a data storage module, used to store the encrypted medical data; a data query module, used to receive a data query request from a patient end or a medical end, perform authority verification on the patient end or the medical end based on the data query request, and after the authority verification, determine the target medical data corresponding to the data query request through artificial intelligence, and feed back the target medical data to the patient end or the medical end.

[0005] Furthermore, the data processing module includes a first cluster, wherein the first cluster includes a first scheduling node and a plurality of first cluster nodes, the first scheduling node is used to allocate a first cluster node to the medical data, and the first cluster node is used to pre-process the medical data.

[0006] Further, the medical data includes medical treatment data of multiple patients, wherein the medical treatment data of the patients includes basic patient data, medical process data, clinical diagnosis and treatment data and / or health management data: the data processing module preprocesses the medical data, including: the first cluster node divides the basic patient data to generate multiple basic patient data fragments; the first cluster node divides the medical process data to generate multiple medical process data fragments; the first cluster node divides the clinical diagnosis and treatment data to generate multiple clinical diagnosis and treatment data fragments; the first cluster node divides the health management data to generate multiple health management data fragments; the first cluster node repeatedly performs sampling of the multiple basic patient data fragments, sampling of the multiple medical process data fragments, sampling of the multiple clinical diagnosis and treatment data fragments, sampling of the multiple health management data fragments, generates spliced ​​data, and records the splicing identifier of the spliced ​​data until each of the basic patient data fragments, medical process data fragments, clinical diagnosis and treatment data fragments and health management data fragments are sampled.

[0007] Furthermore, the first cluster node records the splicing identifier of the spliced ​​data, including: calculating the hash value of each of the patient's basic data fragments, the hash value of each of the medical process data fragments, the hash value of each of the clinical diagnosis and treatment data fragments, and the hash value of each of the health management data fragments included in the spliced ​​data; determining the splicing position of each of the patient's basic data fragments, the splicing position of each of the medical process data fragments, the splicing position of each of the clinical diagnosis and treatment data fragments, and the splicing position of each of the health management data fragments included in the spliced ​​data; based on the splicing position and hash value of each of the patient's basic data fragments, the splicing position and hash value of each of the medical process data fragments, the splicing position and hash value of each of the clinical diagnosis and treatment data fragments, and the splicing position and hash value of each of the health management data fragments included in the spliced ​​data, generate and record the splicing identifier of the spliced ​​data.

[0008] Furthermore, the data encryption module includes a second cluster, wherein the second cluster includes a second scheduling node and multiple second cluster nodes, the second scheduling node is used to allocate a second cluster node to the medical data, and the second cluster node is used to encrypt the splicing data; the second cluster node encrypts the splicing data, including: calculating the hash value corresponding to the splicing identifier; encrypting the splicing data based on the hash value corresponding to the splicing identifier; encrypting the splicing identifier based on the public key corresponding to the second cluster node.

[0009] Furthermore, the data storage module includes a third cluster, wherein the third cluster includes a third scheduling node and multiple third cluster nodes, the third scheduling node is used to allocate a third cluster node to the encrypted medical data, and the third cluster node is used to store the encrypted medical data.

[0010] Furthermore, the third scheduling node allocates a third cluster node to the encrypted medical data, including: determining similar medical data to the medical data, and obtaining historical query information of the similar medical data; determining an optimal distributed storage quantity based on the historical query information of the similar medical data; and allocating a third cluster node to the encrypted medical data based on the optimal distributed storage quantity.

[0011] Furthermore, the data query module includes a fourth cluster, wherein the fourth cluster includes a fourth scheduling node and multiple fourth cluster nodes, the fourth scheduling node is used to allocate a fourth cluster node to the data query request, and the fourth cluster node is used to perform authority verification on the patient side or the medical side based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient side or the medical side.

[0012] Furthermore, the fourth cluster node performs authority verification on the patient side or medical side based on the data query request, including: obtaining historical data query requests from the patient side or medical side that initiated the data query request; obtaining historical data query requests from the device where the patient side or medical side that initiated the data query request is located; determining abnormal parameters of the data query request based on the historical data query requests from the patient side or medical side that initiated the data query request and the historical data query requests from the device where the patient side or medical side that initiated the data query request is located; when the abnormal parameter is less than a preset abnormal parameter threshold, obtaining authority verification information from the patient side or medical side; and performing authority verification on the patient side or medical side based on the authority verification information.

[0013] The present invention provides a medical information data query method based on artificial intelligence, comprising: acquiring medical data; preprocessing the medical data; encrypting the preprocessed medical data; storing the encrypted medical data; receiving a data query request from a patient end or a medical end, and performing authority verification on the patient end or the medical end based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient end or the medical end.

[0014] Compared with the prior art, the medical information data query method and system based on artificial intelligence provided by the present invention have at least the following beneficial effects:

[0015] 1. Encrypting medical data can greatly improve data security, prevent unauthorized access or tampering during storage or transmission, and protect patient privacy and hospital sensitive information. Performing permission verification before data query ensures that only patients, medical staff or systems with corresponding permissions can access specific data, further enhancing data security. Using artificial intelligence technology (such as natural language processing, machine learning, etc.) to automatically parse and identify data query requests, quickly locate and extract target medical data, greatly improves the efficiency of data processing and query. Through automated data processing and query processes, patients can obtain their medical information faster, and medical staff can obtain the required data more efficiently, thereby improving patient satisfaction and work efficiency.

[0016] 2. The larger the mean value of the historical medical data processing volume corresponding to the current query time period and the smaller the variance of the historical medical data processing volume, the higher the demand for medical data processing volume in the current query time period may be. By determining the optimal number of nodes based on the mean value of the historical medical data processing volume and the variance of the historical medical data processing volume corresponding to the current query time period, more first cluster nodes can be allocated to medical data to improve the data processing efficiency of medical data. When the demand for medical data processing volume in the current query time period is low, fewer first cluster nodes are allocated to medical data to reduce the overhead of network transmission and data migration.

[0017] 3. By splitting and reassembling data, the original structure and content of the data can be obfuscated, making it difficult for unauthorized users to directly understand or use the data, reducing the risk of single-point leakage. Even if a part of the data is leaked, the attacker needs additional information to reconstruct the complete original data, which improves the security of medical data storage and access. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0019] Figure 1 It is a module diagram of a medical information data query system based on artificial intelligence according to some embodiments of this specification;

[0020] Figure 2 It is a flowchart of a medical information data query method based on artificial intelligence as shown in some embodiments of this specification. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0022] Figure 1 is a module diagram of a medical information data query system based on artificial intelligence according to some embodiments of this specification, such as Figure 1 As shown, an artificial intelligence-based medical information data query system may include a data acquisition module, a data processing module, a data encryption module, a data storage module and a data query module.

[0023] The data acquisition module can be used to acquire medical data.

[0024] In some embodiments, the medical data includes the medical data of multiple patients, wherein the medical data of the patients includes basic patient data, medical process data, clinical diagnosis and treatment data and / or health management data. The basic information of the patient includes name, age, gender, contact information, address, etc., which is the basis for patient identification and medical records. The medical process data includes the department, doctor, diagnosis results, treatment plan, etc. where the patient is treated. Clinical diagnosis and treatment data includes electronic medical record data: detailed records of the patient's medical history, condition, diagnosis, treatment, medication, examination and other medical information throughout the process, which is an important basis for doctors to make clinical decisions. Clinical diagnosis and treatment data also includes medical imaging data: such as medical imaging images such as X-rays, CT scans, and MRI. Clinical diagnosis and treatment data also includes laboratory test data: including test results of blood, urine, tissue samples, etc. Health management data includes vital signs data: such as physiological parameters such as blood pressure, heart rate, body temperature, etc. of the patient, which are monitored and recorded in real time through medical equipment. Health management data also includes health management files: including the patient's physical examination results, health consultation records, vaccination records, etc., which are used to assess the patient's overall health status.

[0025] In some embodiments, the medical data may also include medical resource data, such as the number of hospital beds, the number of health technicians, the number of medical equipment, etc.

[0026] The data processing module can be used to pre-process medical data.

[0027] In some embodiments, the data processing module includes a first cluster, wherein the first cluster includes a first scheduling node and a plurality of first cluster nodes, the first scheduling node is used to allocate the first cluster node to the medical data, and the first cluster node is used to pre-process the medical data.

[0028] Specifically, the first scheduling node may allocate the first cluster node to the medical data based on the following process:

[0029] Obtain the historical medical data processing volume corresponding to the current query time period, wherein the historical medical data processing volume includes the medical data processing volume of the current query time period in multiple historical cycles. For example, if the current query time period is 09:00-10:00, the medical data processing volume of 09:00-10:00 every day in the past year can be obtained;

[0030] Determine the mean value and variance of the historical medical data processing volume corresponding to the current query time period based on the historical medical data processing volume corresponding to the current query time period;

[0031] Determine the optimal number of nodes based on the mean value and variance of the historical medical data processing volume corresponding to the current query time period;

[0032] Obtaining the current load of each first cluster node and calculating the current node load difference parameter;

[0033] When the current node load difference parameter is greater than the preset current node load difference parameter, the first cluster nodes are sorted from small to large according to the current load, and the first cluster nodes are allocated to the medical data based on the sorting result and the optimal number of nodes. For example, if the optimal number of nodes is 3, the top three first cluster nodes are selected as the first cluster nodes allocated to the medical data;

[0034] When the current node load difference parameter is less than or equal to the preset current node load difference parameter, a first cluster node with an optimal number of nodes is randomly selected as the first cluster node allocated to the medical data.

[0035] For example, the mean value and variance of the historical medical data processing volume corresponding to the current query time period can be calculated based on the following formula:

[0036]

[0037]

[0038] in, is the average value of historical medical data processing volume corresponding to the current query time period, is the amount of medical data processed in the i-th historical period during the current query period, is the total number of historical cycles, is the variance of historical medical data processing volume corresponding to the current query time period.

[0039] The optimal number of nodes can be calculated based on the following formula:

[0040]

[0041] in, The optimal number of nodes, and is the preset parameter, and and All are greater than 0, and [ ] is a rounding down operation.

[0042] The current node load difference parameter can be calculated based on the following formula:

[0043]

[0044] in, is the current node load difference parameter, is the current load of the jth first cluster node, is the number of nodes in the first cluster.

[0045] It can be understood that the larger the mean value of the historical medical data processing volume corresponding to the current query time period and the smaller the variance of the historical medical data processing volume, the higher the demand for medical data processing volume in the current query time period may be. By determining the optimal number of nodes based on the mean value of the historical medical data processing volume and the variance of the historical medical data processing volume corresponding to the current query time period, more first cluster nodes can be allocated to the medical data to improve the data processing efficiency of the medical data. When the demand for medical data processing volume in the current query time period is low, fewer first cluster nodes are allocated to the medical data to reduce the overhead of network transmission and data migration.

[0046] In some embodiments, the data processing module pre-processes the medical data, including:

[0047] The first cluster node divides the patient's basic data to generate multiple patient basic data fragments;

[0048] The first cluster node divides the medical process data to generate multiple medical process data fragments;

[0049] The first cluster node segments the clinical diagnosis and treatment data to generate multiple clinical diagnosis and treatment data segments;

[0050] The first cluster node segments the health management data to generate multiple health management data segments;

[0051] The first cluster node repeatedly performs sampling of multiple patient basic data fragments, sampling of multiple medical process data fragments, sampling of multiple clinical diagnosis and treatment data fragments, sampling of multiple health management data fragments, generates spliced ​​data, and records the splicing identifier of the spliced ​​data until each patient basic data fragment, medical process data fragment, clinical diagnosis and treatment data fragment, and health management data fragment is sampled.

[0052] Specifically, the number of basic patient data segments, the number of medical process data segments, the number of clinical diagnosis and treatment data segments, and the number of health management data segments are consistent.

[0053] Patient basic data, medical process data, clinical diagnosis and treatment data, and health management data can be segmented based on the following processes:

[0054] Calculate the mean data volume of basic patient data, medical process data, clinical diagnosis and treatment data, and health management data;

[0055] Determine the optimal number of fragments based on the mean data volume;

[0056] Based on the optimal number of fragments, patient basic data, medical process data, clinical diagnosis and treatment data, and health management data are segmented.

[0057] For example, the optimal number of fragments can be calculated based on the following formula:

[0058]

[0059] in, is the optimal number of fragments, is the preset number of clips, is the average of the patient's basic data, medical process data, clinical diagnosis and treatment data, and health management data. is the preset data volume mean.

[0060] As an example only, the first cluster node segments the patient's basic data to generate patient basic data segment 1 and patient basic data segment 2, segments the medical process data to generate medical process data segment 1 and medical process data segment 2, segments the clinical diagnosis and treatment data to generate clinical diagnosis and treatment data segment 1 and clinical diagnosis and treatment data segment 2, segments the health management data to generate health management data segment 1 and health management data segment 2, samples patient basic data segment 1, medical process data segment 2, clinical diagnosis and treatment data segment 1 and health management data segment 2 to generate spliced ​​data 1, samples patient basic data segment 2, medical process data segment 1, clinical diagnosis and treatment data segment 2 and health management data segment 1 to generate spliced ​​data 2.

[0061] It is understandable that by splitting and reassembling the data, the original structure and content of the data can be obfuscated, making it difficult for unauthorized users to directly understand or use the data, reducing the risk of single point leakage. Even if a part of the data is leaked, the attacker needs additional information to reconstruct the complete original data, which improves the security of medical data storage and access.

[0062] In some embodiments, the first cluster node records the splicing identifier of the spliced ​​data, including:

[0063] Calculate the hash value of each patient basic data fragment, the hash value of each medical process data fragment, the hash value of each clinical diagnosis and treatment data fragment, and the hash value of each health management data fragment included in the spliced ​​data;

[0064] Determine the splicing position of each patient basic data fragment, each medical process data fragment, each clinical diagnosis and treatment data fragment, and each health management data fragment included in the splicing data;

[0065] Based on the splicing position and hash value of each patient basic data fragment, the splicing position and hash value of each medical process data fragment, the splicing position and hash value of each clinical diagnosis and treatment data fragment, and the splicing position and hash value of each health management data fragment included in the splicing data, the splicing identifier of the spliced ​​data is generated and recorded.

[0066] As an example only, for the spliced ​​data 1, its splicing identifier is: the hash value of the health management data segment 1, the hash value of the medical process data segment 2, the hash value of the clinical diagnosis and treatment data segment 1 and the hash value of the health management data segment 2.

[0067] The data encryption module can be used to encrypt the pre-processed medical data.

[0068] In some embodiments, the data encryption module includes a second cluster, wherein the second cluster includes a second scheduling node and multiple second cluster nodes, the second scheduling node is used to allocate second cluster nodes to medical data, and the second cluster nodes are used to encrypt the spliced ​​data.

[0069] Specifically, the second scheduling node allocates the second cluster node to the medical data in a similar manner as the first scheduling node allocates the first cluster node to the medical data, which will not be described in detail here.

[0070] In some embodiments, the second cluster node encrypts the spliced ​​data, including:

[0071] Calculate the hash value corresponding to the splicing identifier;

[0072] Encrypting the spliced ​​data based on the hash value corresponding to the splicing identifier;

[0073] The splicing identifier is encrypted based on the public key corresponding to the second cluster node.

[0074] Specifically, the hash value of each patient basic data fragment, the hash value of each medical process data fragment, the hash value of each clinical treatment data fragment, and the hash value of each health management data fragment included in the splicing identifier can be combined into a new string according to the splicing position, and the hash value of the string can be calculated for encrypting the spliced ​​data.

[0075] The data storage module can be used to store encrypted medical data.

[0076] In some embodiments, the data storage module includes a third cluster, wherein the third cluster includes a third scheduling node and multiple third cluster nodes, the third scheduling node is used to allocate third cluster nodes to the encrypted medical data, and the third cluster node is used to store the encrypted medical data.

[0077] Specifically, the way in which the third scheduling node allocates the third cluster node to the encrypted medical data is similar to the way in which the first scheduling node allocates the first cluster node to the medical data, which will not be described in detail here.

[0078] In some embodiments, the third scheduling node allocates a third cluster node for the encrypted medical data, including:

[0079] Determine similar medical data to the medical data, and obtain historical query information of the similar medical data;

[0080] Determine the optimal number of distributed storage based on historical query information of similar medical data;

[0081] Based on the optimal distributed storage quantity, a third cluster node is allocated for the encrypted medical data.

[0082] Specifically, the similarity of the two medical data can be calculated based on the patient's basic data, medical process data, clinical diagnosis and treatment data and / or health management data included in the two medical data through a similarity determination model, wherein the similarity determination model can be a convolutional neural network (CNN) model. If the similarity of the two medical data is greater than a preset similarity threshold, the two medical data are similar medical data to each other. Based on the historical query information of similar medical data, the query frequency of similar medical data is determined, the average query frequency of similar medical data is calculated, and the optimal distributed storage quantity is determined.

[0083] The optimal amount of distributed storage can be calculated based on the following formula:

[0084]

[0085] in, is the optimal number of distributed storage, To preset the number of distributed storage, is the preset query frequency mean, is the mean query frequency of similar medical data.

[0086] As an example only, the optimal distributed storage quantity is 3, and the third scheduling node divides the multiple spliced ​​data into three parts and stores them in three third cluster nodes respectively.

[0087] The data query module can be used to receive data query requests from the patient side or the medical side, and perform authority verification on the patient side or the medical side based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient side or the medical side.

[0088] In some embodiments, the data query module includes a fourth cluster, wherein the fourth cluster includes a fourth scheduling node and multiple fourth cluster nodes, the fourth scheduling node is used to allocate a fourth cluster node to the data query request, and the fourth cluster node is used to perform authority verification on the patient side or the medical side based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient side or the medical side.

[0089] In some embodiments, the fourth cluster node performs permission verification on the patient end or the medical end based on the data query request, including:

[0090] Obtain historical data query requests from patients or medical staff who initiate data query requests;

[0091] Obtain the historical data query request of the device where the patient or medical staff initiates the data query request;

[0092] Determine abnormal parameters of the data query request based on historical data query requests of the patient end or medical end that initiated the data query request and historical data query requests of the device where the patient end or medical end that initiated the data query request is located;

[0093] When the abnormal parameter is less than the preset abnormal parameter threshold, the authority verification information is obtained from the patient or medical staff, where the authority verification information can be face information, fingerprint information, etc.;

[0094] Based on the permission verification information, the permission verification is performed on the patient side or the medical staff side.

[0095] Specifically, the similarity between the medical data corresponding to the two historical data query requests of the device where the patient or medical end initiating the data query request is located can be determined through a similarity determination model, and the historical data query requests of the patient or medical end initiating the data query request and the historical data query requests of the device where the patient or medical end initiating the data query request are located can be determined. The user terminal switching frequency of the historical data query requests of the patient or medical end initiating the data query request and the device where the patient or medical end initiating the data query request are located in the current cycle can be determined, and the abnormality parameters of the data query request can be determined based on the historical data query requests of the patient or medical end initiating the data query request and the historical data query requests of the device where the patient or medical end initiating the data query request is located through an abnormality determination model, wherein the abnormality determination model can be a convolutional neural network (CNN, Convolutional Neural Network) model. It can be understood that when the similarity between the medical data corresponding to the two historical data query requests is smaller, the historical data query requests of the patient or medical end initiating the data query request and the user terminal switching frequency of the device where the patient or medical end initiating the data query request is higher in the current cycle, and the abnormality parameter is larger.

[0096] Artificial intelligence technologies (such as natural language processing, machine learning, etc.) can be used to automatically parse and identify data query requests, determine the target medical data corresponding to the data query requests, and feed back the target medical data to the patient or medical staff.

[0097] Figure 2 is a flowchart of a medical information data query method based on artificial intelligence according to some embodiments of this specification, such as Figure 2 As shown, a medical information data query method based on artificial intelligence may include the following process.

[0098] Step 210, obtaining medical data;

[0099] Step 220, preprocessing medical data;

[0100] Step 230, encrypting the pre-processed medical data;

[0101] Step 240, storing the encrypted medical data;

[0102] Step 250, receiving a data query request from the patient or medical staff, performing authority verification on the patient or medical staff based on the data query request, and after authority verification, determining the target medical data corresponding to the data query request through artificial intelligence, and feeding back the target medical data to the patient or medical staff.

[0103] An artificial intelligence-based medical information data query method can be executed by an artificial intelligence-based medical information data query system. For more descriptions of an artificial intelligence-based medical information data query method, please refer to the relevant descriptions of an artificial intelligence-based medical information data query system, which will not be repeated here.

[0104] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A medical information data query system based on artificial intelligence, characterized in that: include: A data acquisition module, used for acquiring medical data; A data processing module, used for preprocessing the medical data; A data encryption module, used for encrypting the pre-processed medical data; A data storage module, used for storing encrypted medical data; The data query module is used to receive data query requests from the patient side or the medical side, and perform authority verification on the patient side or the medical side based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient side or the medical side.

2. According to claim 1, a medical information data query system based on artificial intelligence is characterized in that: The data processing module includes a first cluster, wherein the first cluster includes a first scheduling node and a plurality of first cluster nodes, the first scheduling node is used to allocate a first cluster node to the medical data, and the first cluster node is used to pre-process the medical data.

3. The medical information data query system based on artificial intelligence according to claim 2 is characterized in that: The medical data includes the medical treatment data of multiple patients, wherein the medical treatment data of the patients includes basic patient data, medical treatment process data, clinical diagnosis and treatment data and / or health management data: The data processing module pre-processes the medical data, including: The first cluster node divides the patient basic data to generate multiple patient basic data segments; The first cluster node segments the medical process data to generate multiple medical process data fragments; The first cluster node segments the clinical diagnosis and treatment data to generate a plurality of clinical diagnosis and treatment data segments; The first cluster node segments the health management data to generate a plurality of health management data segments; The first cluster node repeatedly performs sampling of the multiple patient basic data fragments, sampling of the multiple medical process data fragments, sampling of the multiple clinical diagnosis and treatment data fragments, sampling of the multiple health management data fragments, generates spliced ​​data, and records the splicing identifier of the spliced ​​data until each of the patient basic data fragment, medical process data fragment, clinical diagnosis and treatment data fragment, and health management data fragment is sampled.

4. The medical information data query system based on artificial intelligence according to claim 3 is characterized in that: The first cluster node records the splicing identifier of the splicing data, including: Calculate the hash value of each of the patient's basic data fragments, the hash value of each of the medical process data fragments, the hash value of each of the clinical diagnosis and treatment data fragments, and the hash value of each of the health management data fragments included in the spliced ​​data; Determine the splicing position of each of the patient basic data segments, the splicing position of each of the medical process data segments, the splicing position of each of the clinical diagnosis and treatment data segments, and the splicing position of each of the health management data segments included in the splicing data; Based on the splicing position and hash value of each patient basic data fragment, the splicing position and hash value of each medical process data fragment, the splicing position and hash value of each clinical treatment data fragment, and the splicing position and hash value of each health management data fragment included in the splicing data, the splicing identifier of the spliced ​​data is generated and recorded.

5. The medical information data query system based on artificial intelligence according to claim 4 is characterized in that: The data encryption module includes a second cluster, wherein the second cluster includes a second scheduling node and a plurality of second cluster nodes, the second scheduling node is used to allocate a second cluster node to the medical data, and the second cluster node is used to encrypt the spliced ​​data; The second cluster node encrypts the spliced ​​data, including: Calculate the hash value corresponding to the splicing identifier; Encrypting the splicing data based on the hash value corresponding to the splicing identifier; The splicing identifier is encrypted based on a public key corresponding to the second cluster node.

6. A medical information data query system based on artificial intelligence according to any one of claims 1 to 5, characterized in that: The data storage module includes a third cluster, wherein the third cluster includes a third scheduling node and multiple third cluster nodes, the third scheduling node is used to allocate a third cluster node to the encrypted medical data, and the third cluster node is used to store the encrypted medical data.

7. The medical information data query system based on artificial intelligence according to claim 6, characterized in that: The third scheduling node allocates a third cluster node to the encrypted medical data, including: Determine similar medical data to the medical data, and obtain historical query information of the similar medical data; Determining an optimal distributed storage quantity based on historical query information of the similar medical data; Based on the optimal distributed storage quantity, a third cluster node is allocated to the encrypted medical data.

8. The medical information data query system based on artificial intelligence according to any one of claims 1 to 5, characterized in that: The data query module includes a fourth cluster, wherein the fourth cluster includes a fourth scheduling node and multiple fourth cluster nodes, the fourth scheduling node is used to allocate a fourth cluster node to the data query request, and the fourth cluster node is used to perform authority verification on the patient side or the medical side based on the data query request. After the authority verification, the target medical data corresponding to the data query request is determined through artificial intelligence, and the target medical data is fed back to the patient side or the medical side.

9. The medical information data query system based on artificial intelligence according to claim 8, characterized in that: The fourth cluster node performs authority verification on the patient end or the medical end based on the data query request, including: Obtain a historical data query request from a patient or medical staff that initiates the data query request; Obtain a historical data query request from the device where the patient end or medical end that initiated the data query request is located; Determine abnormal parameters of the data query request based on historical data query requests of the patient end or the medical end that initiated the data query request and historical data query requests of the device where the patient end or the medical end that initiated the data query request is located; When the abnormal parameter is less than a preset abnormal parameter threshold, obtaining authority verification information from the patient end or the medical end; Based on the authority verification information, the patient end or the medical care end is verified for authority.

10. A medical information data query method based on artificial intelligence, characterized in that: include: Access to medical data; preprocessing the medical data; Encrypt the pre-processed medical data; Store encrypted medical data; Receive a data query request from the patient or medical staff, perform authority verification on the patient or medical staff based on the data query request, and after authority verification, determine the target medical data corresponding to the data query request through artificial intelligence, and feed back the target medical data to the patient or medical staff.

Images