Medical expert online intelligent auxiliary diagnosis system and method based on cloud computing

Abstract

The invention provides a medical expert online intelligent auxiliary diagnosis system and method based on cloud computing and a computer program product, and belongs to the technical field of intelligent medical diagnosis. The diagnosis system groups the plurality of auxiliary diagnosis requests based on the basic diagnosis information contained in the plurality of auxiliary diagnosis requests to obtain a plurality of grouped auxiliary diagnosis requests; the diagnosis system distributes each group auxiliary diagnosis request to a corresponding first sub-data response library and a corresponding second sub-data response library; and when the difference between the two response results is greater than a preset threshold value, sending the first response result, the second response result and the corresponding grouping auxiliary diagnosis request to a cloud expert response library. According to the technical scheme, cloud auxiliary diagnosis is carried out based on the text information and the image information of the patient to obtain different results with large differences, then the expert diagnosis stage is started, data information of different dimensions can be fully utilized, meanwhile, the medical burden can be relieved, and it is ensured that the auxiliary diagnosis result has a higher reference value degree.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent medical diagnosis technology, and in particular relates to a medical expert online intelligent auxiliary diagnosis system and method based on cloud computing, a computer-readable storage medium for implementing the method, a computer program product and an electronic device. Background Art

[0002] With the support of the Internet of Things and mobile communications, cloud computing and artificial intelligence have developed and been applied rapidly in the medical field. Many large companies have launched their cloud medical platforms, such as IBM's smart medical services, Cisco's regional medical remote collaboration platform, and Huawei's health cloud solutions, which have gradually been recognized by enterprises and individuals and widely used in the medical field. The auxiliary diagnosis system based on artificial intelligence can provide personalized diagnosis and treatment suggestions based on the disease information and the treatment experience of famous traditional Chinese medicine practitioners; the imaging-assisted diagnosis method based on artificial intelligence will not be affected by factors such as doctor's fatigue in reading films, and can quickly and accurately detect and mark small lesions, maximizing the accuracy of diagnosis.

[0003] Chinese invention patent application CN202210766671 proposes a cloud-plus-end intelligent assistance system, which digitizes consensus information and programs the diagnostic process, so that "end" doctors can learn it in a very short time. It improves the existing technology in which IoT medical technology still requires doctors to "memorize" the consensus guidelines required for disease diagnosis and treatment, and makes the procedural instructions for assisting in the diagnosis and treatment of specific diseases intelligent, and quickly pushes and feedbacks them, thereby rapidly improving the homogeneous medical level of IoT medical technology.

[0004] However, in actual applications, it is found that the existing auxiliary diagnosis technologies based on cloud computing or artificial intelligence are mostly targeted at individual patient data, and do not take into account the commonalities of individual data of different patients. The server needs to determine diagnostic recommendations for each piece of data of each patient, which puts a lot of pressure on data processing and transmission. At the same time, the auxiliary diagnosis process considers individual data of different dimensions as a whole and uses a unified model and method for identification. The conclusions drawn are single and often not targeted, which makes patients have low trust and reduces the significance of auxiliary diagnosis. In the end, patients still need to seek help from artificial experts in most cases, and the reference value of auxiliary diagnosis results has not been improved. Summary of the invention

[0005] In response to the above technical problems, the technical solution of the present invention performs cloud-assisted diagnosis based on the patient's text information and image information to obtain differential results and enter the expert diagnosis stage. It can make full use of data information of different dimensions while reducing the medical burden and ensuring that the auxiliary diagnosis results have greater reference value.

[0006] In a first aspect of the present invention, a cloud computing-based medical expert online intelligent auxiliary diagnosis system is proposed, wherein the diagnosis system includes a cloud data response library and a cloud expert response library;

[0007] The cloud data response library includes multiple sub-data response libraries;

[0008] After multiple patient terminals access the diagnosis system through the online intelligent auxiliary diagnosis APP, multiple auxiliary diagnosis requests are sent to the diagnosis system, each of which includes basic diagnosis information of the patient;

[0009] The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, each of which includes at least one group identifier;

[0010] According to the pre-configured correspondence between the group identifier and the sub-data response library, the diagnostic system distributes each group auxiliary diagnosis request to the corresponding first sub-data response library and second sub-data response library;

[0011] When the difference between the first response result of the first sub-database response library and the second response result of the second sub-database response library is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library;

[0012] N patient terminals {D 1 ,D 2 ,…,D N After accessing the diagnostic system through the online intelligent auxiliary diagnosis APP, N auxiliary diagnosis requests are sent to the diagnostic system {R 1 ,R 2 ,…,R N}; N>1; where patient terminal D i The auxiliary diagnosis request sent is R i , i=1,2,…,N;

[0013] Request for auxiliary diagnosis i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition.

[0014] The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, specifically including:

[0015] Get patient terminal D i , D j Auxiliary diagnosis request Ri , R j Corresponding text information Tx i 、Tx j ;

[0016] Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ;

[0017] When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx j If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j are divided into the same group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j.

[0018] The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, specifically including:

[0019] Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ;

[0020] If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Divide into the same group, i, j = 1, 2,…, N, i ≠ j.

[0021] The multiple group-assisted diagnosis requests are divided into a text group and an image group, the first sub-data response library is a text information response sub-database, and the second sub-data response library is an image information response sub-database;

[0022] The group-assisted diagnosis request belonging to the text group is sent to the first sub-data response library, and the group-assisted diagnosis request belonging to the image group is sent to the second sub-data response library.

[0023] Based on the diagnostic system described in the first aspect, in the second aspect of the present invention, a cloud computing-based medical expert online intelligent auxiliary diagnosis method is also proposed, the method is implemented based on a cloud computing online intelligent auxiliary diagnosis system system including a cloud data response library and a cloud expert response library, the cloud data response library includes a text information response sub-database and an image information response sub-database;

[0024] The method comprises the following steps:

[0025] S100: Receive N patient terminals {D 1 ,D 2 ,…,D N N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}; N>1; where patient terminal D i The auxiliary diagnosis request sent is R i , i=1,2,…,N; auxiliary diagnosis request R i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition;

[0026] S200: Based on N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}Corresponding text information {Tx 1 ,Tx 2 ,…,Tx N}, for N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N} to obtain K auxiliary diagnosis request groups {Gx 1 ,Gx 2 ,…,Gx K},1<K<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request;

[0027] S300: Based on N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}Corresponding image information {Img 1 ,Img 2 ,…,Img N}, for N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N} to obtain M auxiliary diagnosis request groups {Gimg 1 ,Gimg2 ,…,Gimg M},1<M<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request;

[0028] S400: Group K auxiliary diagnosis requests into groups {Gx 1 ,Gx 2 ,…,Gx K} is sent to the text information response sub-database to obtain a first response result set; M auxiliary diagnosis requests are grouped into {Gimg 1 ,Gimg 2 ,…,Gimg M}Send to the image information response sub-database to obtain a second response result set;

[0029] S500: When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library.

[0030] S600: Receive the diagnosis result of the cloud expert response library to the group-assisted diagnosis request, and feed back the diagnosis result to the patient terminal group corresponding to the group-assisted diagnosis request.

[0031] Specifically, step S500 also includes: when the auxiliary diagnosis request R i When the difference between the first response result and the second response result is less than a preset threshold, the first response result and the second response result are fed back to the patient terminal group corresponding to the grouping auxiliary request;

[0032] The step S200 specifically includes:

[0033] Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding text information Tx i 、Tx j ;

[0034] Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ;

[0035] When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Txj If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j are divided into the same group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j.

[0036] The step S300 specifically includes:

[0037] Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ;

[0038] If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Divide into the same group, i, j = 1, 2, ..., N, i ≠ j;

[0039] Part or all of the steps of a cloud computing-based online intelligent assisted diagnosis method for medical experts described in the second aspect can be automatically implemented through various forms of electronic devices and computer program instructions; the computer program instructions can be stored in different forms of storage media and loaded into computer electronic devices for execution.

[0040] Therefore, in the third aspect of the present invention, a computer-readable storage medium is also provided for storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the cloud computing-based medical expert online intelligent assisted diagnosis method described in the second aspect.

[0041] In the fourth aspect of the present invention, an electronic device is also proposed, which includes a processor and a memory, the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the cloud computing-based medical expert online intelligent assisted diagnosis method described in the second aspect.

[0042] In the fifth aspect of the present invention, a computer program product is also proposed, which includes a computer program. When the computer program is executed, the cloud computing-based online intelligent assisted diagnosis method for medical experts described in the second aspect is implemented.

[0043] Through the technical solution of the present invention, the diagnosis system groups multiple auxiliary diagnosis requests based on the basic diagnosis information contained in the multiple auxiliary diagnosis requests to obtain multiple grouped auxiliary diagnosis requests; the diagnosis system distributes each grouped auxiliary diagnosis request to the corresponding first sub-data response library and second sub-data response library; when the difference in the response results is greater than a preset threshold, the first response result, the second response result and the corresponding grouped auxiliary diagnosis request are sent to the cloud expert response library. The technical solution of the present invention performs cloud-based auxiliary diagnosis based on the patient's text information and image information, and obtains differential results to enter the expert diagnosis stage. It can fully utilize data information of different dimensions while reducing the medical burden and ensuring that the auxiliary diagnosis results have greater reference value.

[0044] Further advantages of the present invention will be further reflected in detail in the specific embodiments section in conjunction with the drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is a schematic diagram of a specific application scenario of the cloud computing-based medical expert online intelligent auxiliary diagnosis system of the present invention.

[0047] Figure 2 This is a schematic diagram of the working principle of a cloud computing-based medical expert online intelligent auxiliary diagnosis system according to an embodiment of the present invention.

[0048] Figure 3 Schematic diagram of the cloud computing-based medical expert online intelligent auxiliary diagnosis system executing text information grouping and image information grouping

[0049] Figure 4 This is a schematic diagram of the main process of a cloud computing-based medical expert online intelligent auxiliary diagnosis method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments that are the same as the present application. Instead, they are only examples of devices and methods that are the same as some aspects of the present application as detailed in the attached claims.

[0051] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0052] At the same time, in the specific implementation of this application, if user-related data is involved, when the embodiment of this application is applied to a specific product or technology, the user's permission or consent must be obtained, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0053] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0054] See also Figure 1 , Figure 1 A schematic diagram showing a specific application scenario of the cloud computing-based medical expert online intelligent auxiliary diagnosis system of the present invention.

[0055] exist Figure 1 In the figure, a medical expert online intelligent auxiliary diagnosis system based on cloud computing is shown, and the diagnosis system includes a cloud data response library and a cloud expert response library.

[0056] The cloud data response library includes multiple sub-data response libraries; the multiple sub-data response libraries can be divided into a text information response database and an image information response database.

[0057] In the embodiments of the present application, the cloud data response library can be referred to as a "robot database", that is, the artificial intelligence engine database of the auxiliary diagnosis system. Based on the received patient auxiliary diagnosis request, the analysis result, that is, the artificial intelligence response result, is obtained with the support of the artificial intelligence engine database; the implementation of this point can refer to various auxiliary diagnosis methods based on artificial intelligence and deep learning in the prior art, and the present invention does not elaborate on this.

[0058] In the embodiment of the present application, the cloud expert response library can be referred to as an "artificial expert database". The cloud expert response library is supported by registered medical experts as a think tank. When the response result of the cloud data response library is not ideal, or the cloud expert response library needs to be activated for other reasons, the corresponding patient auxiliary diagnosis request is sent to the cloud expert response library, and the currently online medical expert performs the diagnosis response, or waits for the corresponding expert to come online and give a diagnosis response.

[0059] Of course, it is worth explaining that, when applying the technical solution of the present invention, whether it is the machine analysis results obtained with the support of the artificial intelligence engine database or the manual analysis results obtained with the support of the end expert response library, they can only be used as intermediate auxiliary results, not the final diagnosis results. The intermediate auxiliary results are only used as auxiliary diagnostic materials for the patient's current illness for reference by the patient or the on-site doctor.

[0060] The cloud-assisted diagnosis, artificial intelligence-assisted diagnosis and other solutions in the prior art generally have similar cloud data response libraries ("robot databases") and cloud expert response libraries ("artificial expert databases") as mentioned above to perform similar assisted diagnosis processes.

[0061] However, in actual applications, it is found that the existing auxiliary diagnosis technologies based on cloud computing or artificial intelligence are mostly targeted at individual patient data, and do not take into account the commonalities of individual data of different patients. The server needs to determine diagnostic recommendations for each piece of data of each patient, which puts a lot of pressure on data processing and transmission. At the same time, the auxiliary diagnosis process considers individual data of different dimensions as a whole and uses a unified model and method for identification. The conclusions drawn are single and often not targeted, which makes patients have low trust and reduces the significance of auxiliary diagnosis. In the end, patients still need to seek help from artificial experts in most cases, and the reference value of auxiliary diagnosis results has not been improved.

[0062] To this end, the embodiments of the present application are improved as follows.

[0063] Reference Figure 2 After multiple patient terminals access the diagnosis system through the online intelligent auxiliary diagnosis APP, they send multiple auxiliary diagnosis requests to the diagnosis system, each of which includes the patient's basic diagnosis information.

[0064] In practical applications, the patient's basic diagnostic information at least includes text information and image information.

[0065] In actual applications, patients can use various mobile terminals as patient terminals, and the mobile terminals are installed with an online intelligent auxiliary diagnosis APP, which uses the cloud data response library and the cloud expert response library as servers;

[0066] Therefore, patients can input basic diagnostic information in a variety of ways, such as age, blood type, height, past medical history, test results, existing diagnostic images, etc. The input methods include text input, photo / scan input, voice input, etc. In any case, after processing by the terminal, this information can be divided into two categories: text information and image information.

[0067] The auxiliary diagnosis in the prior art usually inputs all the basic diagnostic information input by the patient as a whole as diagnostic factors, for example, sending the ARDS interview data, physical examination item inspection data and supplementary identification data to the cloud server; the cloud server determines the ARDS suggestive suggestion instructions or auxiliary diagnosis conclusions based on the ARDS interview data, physical examination item inspection data and supplementary identification data.

[0068] However, in this process, due to the different characteristics of data (text / image) in different dimensions, the artificial intelligence engine's understanding patterns are also different. If a unified model and method are used for identification, the conclusions drawn will be single and often not targeted.

[0069] For this purpose, see Figure 2 The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information contained in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, each of which contains at least one group identifier.

[0070] The grouping identifier may be, for example, a text grouping identifier or an image grouping identifier; other types of identifiers may also be used, which is not limited in this embodiment.

[0071] According to the pre-configured correspondence between the group identifier and the sub-data response library, the diagnostic system distributes each group auxiliary diagnosis request to the corresponding first sub-data response library and second sub-data response library;

[0072] The corresponding relationship here may be that the text group is sent to the first sub-data response library, and the image group is sent to the second sub-data response library.

[0073] When the difference between the first response result of the first sub-database response library and the second response result of the second sub-database response library is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library.

[0074] To better describe the above process, we will parameterize the relevant features and combine them with Figure 3 The schematic diagram of the cloud computing-based medical expert online intelligent auxiliary diagnosis system executing text information grouping and image information grouping further introduces the above process.

[0075] First, N patient terminals {D 1 ,D 2 ,…,D N After accessing the diagnostic system through the online intelligent auxiliary diagnosis APP, N auxiliary diagnosis requests are sent to the diagnostic system {R 1 ,R 2 ,…,R N}; N>1; where patient terminal D i The auxiliary diagnosis request sent is R i , i=1,2,…,N;

[0076] Request for auxiliary diagnosis i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition;

[0077] Next, perform two levels of grouping at the same time:

[0078] (1) Obtain patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding text information Tx i 、Tx j ;

[0079] Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ;

[0080] When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx j If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j into the same text group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j;

[0081] In this process, the premise for text grouping is text information Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j The text keywords here can be the medical keywords (content words) contained in the text after text recognition and text segmentation, excluding various function words (stop words, structural auxiliary words, etc.).

[0082] Only when the number of keywords in the text is close, the reference value of subsequent text similarity comparison will be improved.

[0083] (2) Obtain patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ;

[0084] If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Classify into the same image group, i, j = 1, 2,…, N, i≠j.

[0085] In this process, since what is compared is image information, the similarity comparison of the images can be performed directly without executing a keyword recognition process similar to the aforementioned text segmentation, which is consistent with the actual scenario.

[0086] The operation diagram of (1) and (2) above can be found in Figure 3 .

[0087] Of course, it is understandable that each group (image group or text group) usually contains at least two auxiliary diagnosis requests; if the similarity standard threshold is set high, it is also possible that a certain group (image group or text group) contains only one auxiliary diagnosis request, that is, a certain auxiliary diagnosis request is a separate group, which does not affect the implementation process of the subsequent technical solutions of the present invention. Preferably, by setting a suitable similarity standard value, it can be ensured that each group (image group or text group) usually contains at least two auxiliary diagnosis requests.

[0088] It can be seen that the multiple group-assisted diagnosis requests are divided into a text group and an image group, the first sub-data response library is a text information response sub-database, and the second sub-data response library is an image information response sub-database;

[0089] The group-assisted diagnosis request belonging to the text group is sent to the first sub-data response library, and the group-assisted diagnosis request belonging to the image group is sent to the second sub-data response library.

[0090] When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is less than a preset threshold, the first response result and the second response result are fed back to the patient terminal group corresponding to the grouping auxiliary request.

[0091] When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud-based expert response library, the diagnosis result of the cloud-based expert response library for the group-assisted diagnosis request is received, and the diagnosis result is fed back to the patient terminal group corresponding to the group-assisted diagnosis request.

[0092] It can be seen that according to the improved technical solution of the present invention, the corresponding auxiliary diagnosis process takes into account the common characteristics of multiple individual patient data, and the server processes the data in groups to determine the diagnosis suggestions, which reduces the pressure of data processing and transmission;

[0093] At the same time, the auxiliary diagnosis process is to separate individual data of different dimensions, and use corresponding models and methods for independent identification and diagnosis, which can produce relatively independent results and enable intuitive comparison, thus enhancing the patient's trust. When the comparison results are quite different, it is necessary to seek the help of artificial experts, thus ensuring the reference value of the auxiliary diagnosis results.

[0094] exist Figure 1-Figure 3 On the basis of Figure 4 A cloud computing-based medical expert online intelligent assisted diagnosis method is shown. The method is implemented based on a cloud computing online intelligent assisted diagnosis system including a cloud computing data response library and a cloud computing expert response library. The cloud data response library includes a text information response sub-database and an image information response sub-database.

[0095] As mentioned above, application Figure 4 The diagnostic method, whether it is the machine analysis result obtained with the support of the artificial intelligence engine database or the manual analysis result obtained with the support of the end expert response library, can only be used as an intermediate auxiliary result, not the final diagnosis result. The intermediate auxiliary result is only used as an auxiliary diagnostic material for the patient's current illness for reference by the patient or the on-site doctor.

[0096] Figure 4 The method comprises the following steps: Figure 4 Step numbers omitted):

[0097] S100: Receive N patient terminals {D 1 ,D 2 ,…,D N N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}; N>1; where patient terminal D iThe auxiliary diagnosis request sent is R i , i=1,2,…,N; auxiliary diagnosis request R i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition;

[0098] S200: Based on N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}Corresponding text information {Tx 1 ,Tx 2 ,…,Tx N}, for N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N} to obtain K auxiliary diagnosis request groups {Gx 1 ,Gx 2 ,…,Gx K},1<K<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request;

[0099] S300: Based on N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N}Corresponding image information {Img 1 ,Img 2 ,…,Img N}, for N auxiliary diagnosis requests {R 1 ,R 2 ,…,R N} to obtain M auxiliary diagnosis request groups {Gimg 1 ,Gimg 2 ,…,Gimg M},1<M<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request;

[0100] S400: Group K auxiliary diagnosis requests into groups {Gx 1 ,Gx 2 ,…,Gx K} is sent to the text information response sub-database to obtain a first response result set; M auxiliary diagnosis requests are grouped into {Gimg 1 ,Gimg 2 ,…,Gimg M}Send to the image information response sub-database to obtain a second response result set;

[0101] S500: When belonging to the same auxiliary diagnosis request R iWhen the difference between the first response result and the second response result is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library.

[0102] Combination Figure 4 It can be seen that after step S100, step S200 and step S300 are executed in parallel, and then step S400 is entered;

[0103] The step S500 further includes:

[0104] When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is less than a preset threshold, the first response result and the second response result are fed back to the patient terminal group corresponding to the grouping auxiliary request.

[0105] After step S500, the method further includes:

[0106] S600: Receive the diagnosis result of the cloud expert response library to the group-assisted diagnosis request, and feed back the diagnosis result to the patient terminal group corresponding to the group-assisted diagnosis request.

[0107] The step S200 specifically includes:

[0108] Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding text information Tx i 、Tx j ;

[0109] Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ;

[0110] When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx j If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j are divided into the same group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j.

[0111] The step S300 specifically includes:

[0112] Get patient terminal D i, D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ;

[0113] If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Divide into the same group, i, j = 1, 2,…, N, i ≠ j.

[0114] The pseudo code implementation process of the embodiment of the present application is introduced in the form of a general computer process language. For ease of understanding, specific numerical values ​​are substituted into the above implementation process (for example, N=6, M=3, K=2) to give a specific cloud computing-based medical expert online intelligent auxiliary diagnosis process as follows.

[0115] It is understood that the specific values ​​(N=6, M=3, K=2) here are only examples and are not limitations of the specific technical solution. The embodiment under the specific values ​​can be extended to any other implementation scheme under the value limit.

[0116] When N=6, the corresponding implementation is as follows:

[0117] Step 1: Receive 6 patient terminals {D 1 ,D 2 ,…,D 6}Sent 6 auxiliary diagnosis requests {R 1 ,R 2 ,…,R 6};

[0118] Assume that auxiliary diagnosis request Ri={Txi,Imgi},i=1,2,…,6;

[0119] Step 2: For each i, j = 1, 2, ..., 6, i ≠ j,

[0120] Get Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ;

[0121] When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx jIf the similarity is greater than the first preset standard value (assuming it is 76%), the auxiliary diagnosis request R i , R j into the same text group, where Num is a preset value (assuming it is 4);

[0122] In this way, all six auxiliary diagnosis requests {R 1 ,R 2 ,…,R 6} Grouping is performed according to the text information features. Assume that three text groups (K=3) are finally obtained as follows:

[0123] G x1 = {R 1 ,R 2 ,R 6}

[0124] G x2 = {R 4 ,R 5}

[0125] G x3 ={R3};

[0126] Step 3: Group the three texts 1 ,R 2 ,R 6}, {R 4 ,R 5}, {R3} is sent to the text message response sub-database to obtain a first response result set;

[0127] Assume that for G x1 = {R 1 ,R 2 ,R 6}The first response result is SR1;

[0128] For G x2 = {R 4 ,R 5}The first response result is SR2;

[0129] For G x3 =The first response result of {R3} is SR3;

[0130] Then the first response result set is SR = {SR1, SR2, SR3};

[0131] It can be understood that the first response result is an analysis result obtained based on the received patient auxiliary diagnosis request with the support of the artificial intelligence engine database (text information response sub-database), that is, an artificial intelligence response result, which can be a text description;

[0132] Step 4: For each i, j = 1, 2, ..., 6, i ≠ j,

[0133] Get R i , R j Corresponding image information Img i , Img j ;

[0134] If the image information Img i , Img j If the similarity is greater than a second preset standard value (e.g., 75%), the auxiliary diagnosis request R i , R j Into the same group

[0135] In this way, all six auxiliary diagnosis requests {R 1 ,R 2 ,…,R 6} Grouping is performed according to the image information features. Assume that two image groups (M=2) are finally obtained as follows:

[0136] G img1 = {R 1 ,R 2 ,R 4};

[0137] G img2 = {R 3 ,R 5 ,R 6};

[0138] Step 5: Send the two image groups to the image information response sub-database to obtain a second response result set;

[0139] Assume that for G img1 = {R 1 ,R 2 ,R 4 The second response result of} is TR1;

[0140] For G img2 = {R 3 ,R 5 ,R 6 The second response result of} is TR2;

[0141] Then the second response result set is TR = {TR1, TR2};

[0142] It can be understood that the second response result is the analysis result obtained based on the received patient auxiliary diagnosis request with the support of the artificial intelligence engine database (image information response sub-database), that is, the artificial intelligence response result, which can be a text description.

[0143] In the above process, Step 2-Step 3 and Step 4-Step 5 are two processes that are executed simultaneously in parallel and can be executed through parallel processes of hardware or software to speed up the process.

[0144] Next, analyze the data belonging to the same auxiliary diagnosis request R i The difference between the first response result and the second response result.

[0145] For example, for R 1 For example, the analysis belongs to the same auxiliary diagnosis request R i The difference between the first response result and the second response result is to analyze the difference between TR1 and SR1.

[0146] For R 3 For example, the analysis belongs to the same auxiliary diagnosis request R i The difference between the first response result and the second response result is to analyze the difference between TR2 and SR3.

[0147] For R 6 For example, the analysis belongs to the same auxiliary diagnosis request R i The difference between the first response result and the second response result is to analyze the difference between TR1 and SR2.

[0148] R 1 For example, since TR1 and SR1 are both represented by text descriptions, at this time, the text difference between TR1 and SR1 is calculated as the difference (the value is between 0-100%);

[0149] When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is less than a preset threshold (for example, 30%), the first response result and the second response result are fed back to the patient terminal group corresponding to the grouping auxiliary request;

[0150] {TR1, SR1} will be fed back to the patient terminal group {D 1 ,D 2 ,D 6}.

[0151] If the difference is greater than the preset threshold, it means that the analysis results obtained with the support of different artificial intelligence engine databases are quite different, and it is necessary to seek help from the cloud-based expert response library and send the first response result, the second response result and the corresponding group-assisted diagnosis request to the cloud-based expert response library.

[0152] Receive the diagnosis result of the cloud expert response library to the group-assisted diagnosis request, and feed back the diagnosis result to the patient terminal group corresponding to the group-assisted diagnosis request.

[0153] Obviously, the above embodiment of N=6 can be extended to the case of any number N.

[0154] According to the above description, we can further know that the corresponding auxiliary diagnosis process takes into account the common characteristics of multiple patients' individual data. The server will process the data in groups to determine the diagnosis suggestions, which reduces the pressure of data processing and transmission. At the same time, the auxiliary diagnosis process separates the individual data of different dimensions and uses corresponding models and methods for independent identification and diagnosis. Relatively independent results can be obtained and compared intuitively, which can enhance the patient's trust. When the comparison results are very different, it is necessary to seek the help of artificial experts to ensure the reference value of the auxiliary diagnosis results.

[0155] The present invention provides multiple embodiments, each of which can constitute an independent technical solution and may contribute to the prior art and solve corresponding technical problems. However, it should be pointed out that different embodiments can be combined with each other without violating logic; at the same time, each embodiment can solve at least one technical problem, but it is not required that each individual embodiment solves multiple or all technical problems.

[0156] For other technologies, principles, algorithms or models not elaborated in detail in this application, please refer to the prior art.

[0157] The foregoing has shown and described the method embodiments and system of the present invention, but it is understandable to those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A medical expert online intelligent auxiliary diagnosis system based on cloud computing, the diagnosis system includes a cloud data response library and a cloud expert response library, characterized in that: The cloud data response library includes multiple sub-data response libraries; After multiple patient terminals access the diagnosis system through the online intelligent auxiliary diagnosis APP, multiple auxiliary diagnosis requests are sent to the diagnosis system, each of which includes basic diagnosis information of the patient; The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, each of which includes at least one group identifier; According to the pre-configured correspondence between the group identifier and the sub-data response library, the diagnostic system distributes each group auxiliary diagnosis request to the corresponding first sub-data response library and second sub-data response library; When the difference between the first response result of the first sub-database response library and the second response result of the second sub-database response library is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library.

2. The cloud computing-based online intelligent auxiliary diagnosis system for medical experts according to claim 1, characterized in that: N patient terminals {D1, D2, ..., D N After accessing the diagnostic system through the online intelligent auxiliary diagnosis APP, N auxiliary diagnosis requests {R1, R2, …, R N }; N>1; where patient terminal D i The auxiliary diagnosis request sent is R i , i=1,2,…,N; Request for auxiliary diagnosis i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition.

3. The cloud computing-based online intelligent auxiliary diagnosis system for medical experts as claimed in claim 2, characterized in that: The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, specifically including: Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding text information Tx i 、Tx j ; Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ; When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx j If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j are divided into the same group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j.

4. The cloud computing-based online intelligent auxiliary diagnosis system for medical experts according to claim 2, characterized in that: The diagnostic system groups the multiple auxiliary diagnostic requests based on the basic diagnostic information included in the multiple auxiliary diagnostic requests to obtain multiple grouped auxiliary diagnostic requests, specifically including: Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ; If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Divide into the same group, i, j = 1, 2,…, N, i ≠ j.

5. The cloud computing-based online intelligent auxiliary diagnosis system for medical experts as claimed in claim 2, characterized in that: The multiple group-assisted diagnosis requests are divided into a text group and an image group, the first sub-data response library is a text information response sub-database, and the second sub-data response library is an image information response sub-database; The group-assisted diagnosis request belonging to the text group is sent to the first sub-data response library, and the group-assisted diagnosis request belonging to the image group is sent to the second sub-data response library.

6. A cloud computing-based medical expert online intelligent assisted diagnosis method, the method is implemented based on a cloud computing online intelligent assisted diagnosis system including a cloud data response library and a cloud expert response library, the cloud data response library includes a text information response sub-database and an image information response sub-database; It is characterized in that The method comprises the following steps: S100: Receive N patient terminals {D1, D2, ..., D N } sent by N auxiliary diagnosis requests {R1, R2, …, R N }; N>1; where patient terminal D i The auxiliary diagnosis request sent is R i , i=1,2,…,N; auxiliary diagnosis request R i The basic diagnostic information of the patient is included in the text information Tx i and image information Img i composition; S200: Based on N auxiliary diagnosis requests {R1, R2, ..., R N }Corresponding text information {Tx1,Tx2,…,Tx N }, for N auxiliary diagnosis requests {R1, R2, …, R N } to obtain K auxiliary diagnosis request groups {Gx1, Gx2, …, Gx K },1<K<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request; S300: Based on N auxiliary diagnosis requests {R1, R2, ..., R N } corresponding to the image information {Img1,Img2,…,Img N }, for N auxiliary diagnosis requests {R1, R2, …, R N } to obtain M auxiliary diagnosis request groups {Gimg1, Gimg2,…, Gimg M },1<M<N; Each auxiliary diagnosis request group contains at least one auxiliary diagnosis request; S400: Group K auxiliary diagnosis requests into {Gx1, Gx2, ..., Gx K } is sent to the text information response sub-database to obtain a first response result set; M auxiliary diagnosis requests are grouped into {Gimg1, Gimg2,…, Gimg M }Send to the image information response sub-database to obtain a second response result set; S500: When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is greater than a preset threshold, the first response result, the second response result and the corresponding group-assisted diagnosis request are sent to the cloud expert response library.

7. The cloud computing-based online intelligent auxiliary diagnosis method for medical experts according to claim 6, characterized in that: The step S500 further includes: When belonging to the same auxiliary diagnosis request R i When the difference between the first response result and the second response result is less than a preset threshold, the first response result and the second response result are fed back to the patient terminal group corresponding to the grouping auxiliary request.

8. The cloud computing-based online intelligent auxiliary diagnosis method for medical experts according to claim 6, characterized in that: After step S500, the method further includes: S600: Receive the diagnosis result of the cloud expert response library to the group-assisted diagnosis request, and feed back the diagnosis result to the patient terminal group corresponding to the group-assisted diagnosis request.

9. The cloud computing-based online intelligent auxiliary diagnosis method for medical experts according to claim 6, characterized in that: The step S200 specifically includes: Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding text information Tx i 、Tx j ; Confirm text message Tx i 、Tx j The number of keywords contained NumTx i 、NumTx j ; When |NumTx i -NumTx j |≤Num, if the text message Tx i 、Tx j If the similarity is greater than the first preset standard value, the auxiliary diagnosis request R i , R j are divided into the same group, where Num is a preset value, i, j = 1, 2, ..., N, i ≠ j.

10. The cloud computing-based online intelligent auxiliary diagnosis method for medical experts according to claim 6, characterized in that: The step S300 specifically includes: Get patient terminal D i , D j Auxiliary diagnosis request R i , R j Corresponding image information Img i , Img j ; If the image information Img i , Img j If the similarity is greater than the second preset standard value, the auxiliary diagnosis request R i , R j Divide into the same group, i, j = 1, 2,…, N, i ≠ j.

Images