Diagnosis and treatment system and diagnosis and treatment method based on RPA technology

Abstract

The invention relates to a diagnosis and treatment system and method based on an RPA technology, and relates to the technical field of medical information. Comprising a first diagnosis and treatment system and at least one second diagnosis and treatment system, the writing system comprises a pre-inquiry subsystem and a face diagnosis subsystem; the pre-inquiry subsystem is configured to perform pre-inquiry on a patient and generate pre-inquiry information; the face diagnosis subsystem is configured to respectively obtain face diagnosis questions of doctors and face diagnosis replies of patients and generate face diagnosis information; the diagnosis system is configured to obtain a diagnosis result based on medical information in the pre-inquiry information and the face diagnosis information and an inspection result of the patient; any second diagnosis and treatment system is configured to acquire preset information content from at least one of the pre-inquiry information, the face diagnosis information and the diagnosis result based on at least one RPA robot and input the preset information content. The complexity of using a software system by a doctor is reduced, and the diagnosis and treatment efficiency of the doctor is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a diagnosis and treatment system and a diagnosis and treatment method based on RPA technology. Background Art

[0002] With the continuous growth in the number of patients treated in hospitals, doctors' diagnosis and treatment work has become increasingly busy. At present, various medical institutions are constantly adding various information software systems, and some hospitals even have more than 50 information software systems. With the continuous increase in information software systems, two problems have emerged. One is that each information software system is relatively complex, but for doctors, there are only a few high-frequency functional modules, but doctors need to learn more functional modules of more software systems, which greatly increases the daily workload of doctors. Second, in the case of multiple information software systems, doctors need to constantly switch between multiple software systems to achieve a patient's complete diagnosis and treatment process, which reduces the efficiency of doctors' daily diagnosis and treatment work. Therefore, there is an urgent need for a method to reduce the complexity of doctors' use of software systems and improve the efficiency of doctors' diagnosis and treatment work. Summary of the invention

[0003] The technical problem to be solved by this application is to provide a diagnosis and treatment system and a diagnosis and treatment method based on RPA technology, which has the characteristics of reducing the complexity of doctors using the software system and improving the efficiency of doctors' diagnosis and treatment work.

[0004] In a first aspect, an embodiment provides a diagnosis and treatment system based on RPA technology, including a first diagnosis and treatment system and at least one second diagnosis and treatment system, wherein the first diagnosis and treatment system includes a writing system and a diagnosis system; The writing system includes a pre-questioning subsystem and a face-to-face consultation subsystem; the pre-questioning subsystem is configured to conduct a pre-questioning of the patient and generate pre-questioning information; the face-to-face consultation subsystem is configured to obtain the doctor's face-to-face consultation questions and the patient's face-to-face consultation replies, respectively, and generate face-to-face consultation information; The diagnostic system is configured to obtain a diagnostic result based on the medical information in the pre-diagnosis information and the face-to-face consultation information, and the patient's test results; Among the at least one second diagnosis and treatment system, any one of the second diagnosis and treatment systems is configured to obtain and enter preset information content from at least one of the pre-consultation information, face-to-face consultation information and diagnosis results based on at least one RPA robot.

[0005] In one embodiment, the pre-consultation subsystem includes a first service terminal and a first user terminal, the first user terminal is a terminal where the patient is located, and the first service terminal is a terminal where the patient is treated in a hospital; the first service terminal is configured to send a pre-consultation request to the first user terminal in response to a received user's medical request, and in response to the pre-consultation request confirmation information returned by the first user terminal, send pre-consultation content to the first user terminal, and in response to the pre-consultation reply content confirmation instruction sent by the first user terminal, extract the pre-consultation reply content and generate pre-consultation information; The first user terminal is configured to display the pre-consultation request confirmation interface in response to the received pre-consultation request, and send pre-consultation request confirmation information to the first service terminal in response to the received pre-consultation request confirmation instruction, display the pre-consultation content in response to the received pre-consultation content, and send the pre-consultation reply content confirmation instruction to the first service terminal in response to the received pre-consultation reply content confirmation instruction.

[0006] In one embodiment, the consultation subsystem is configured to collect and record the consultation content in response to a recording instruction of the consultation questions, collect and record the consultation reply content in response to a recording instruction of the consultation reply, and extract the consultation questions and consultation reply content and generate consultation information in response to the recorded consultation questions and consultation replies.

[0007] In one embodiment, the writing system also includes a historical data extraction subsystem, which is configured to query whether the patient is a historical patient in response to the patient's registration information. If so, the patient's personal basic information and historical medical information are automatically extracted and sent to a second user terminal where the patient's doctor is located; if not, the patient's personal basic information is obtained and sent to a second user terminal where the patient's doctor is located.

[0008] In one embodiment, the first diagnosis and treatment system further includes a query system, and the query system is configured to acquire and display corresponding query information in response to the acquired query conditions.

[0009] In a second aspect, an embodiment provides a diagnosis and treatment method, which can be used in a diagnosis system in a diagnosis and treatment system described in any one of the above embodiments to obtain a diagnosis result, the method comprising: obtaining a diagnosis result based on medical information in pre-consultation information and face-to-face consultation information, and the patient's test results.

[0010] In one embodiment, the step of obtaining a diagnosis result based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results, includes: Obtaining first diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results; Vectorizing the first diagnosis and treatment information to obtain first vector data; Calculating the similarity between the first vector data and each second vector data in a vector database to obtain the second vector data with the highest similarity; the vector database is obtained based on the medical record data of multiple historically diagnosed and treated patients; The first diagnosis result of the patient is obtained based on the diagnosis result corresponding to the second vector data with the highest similarity.

[0011] In one embodiment, the step of obtaining a diagnosis result based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results, includes: Obtaining second diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results; In response to the acquired second diagnosis and treatment information, the input of the large model is identified based on the diagnosis result to obtain the large model diagnosis result; the large model obtained by the diagnosis result is a neural network model obtained by training in combination with the loss function.

[0012] In one embodiment, a final diagnosis result is obtained based on the first diagnosis result and the large model diagnosis result.

[0013] In one embodiment, the large model diagnosis result includes a second diagnosis result and a third diagnosis result, and the second diagnosis information is used as an input of the diagnosis result identification large model to obtain the large model diagnosis result, including: In response to the acquired second diagnosis and treatment information, a large model is identified based on the second diagnosis result to obtain a second diagnosis result; the large model for obtaining the second diagnosis result is a neural network model for identifying diagnosis results obtained by training based on the medical record data of multiple historical diagnosis and treatment patients in the hospital where the patient was treated, combined with the first loss function; In response to the acquired second diagnosis and treatment information, a third diagnosis result is obtained based on a large model for identifying the third diagnosis result; the large model for identifying the third diagnosis result is a neural network model for identifying diagnosis results based on medical record data of multiple historical diagnosis and treatment patients in multiple hospitals, combined with training using the second loss function.

[0014] The beneficial effects of the present invention are: The second diagnosis and treatment system obtains and enters the preset information based on the various information obtained by the RPA robot through the first diagnosis and treatment system. In this way, for doctors, the patient's information only needs to be obtained and entered once, and there is no need to frequently switch between systems due to the existence of multiple diagnosis and treatment systems (or multiple information software systems), which reduces the complexity of doctors using software systems and improves the efficiency of doctors' diagnosis and treatment work. Secondly, the setting of the pre-questioning subsystem in the first diagnosis and treatment system means that doctors no longer need to repeatedly ask and enter some basic questions during consultations, which further reduces the complexity of doctors using software systems and improves the efficiency of doctors' diagnosis and treatment work. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a structural diagram of a diagnosis and treatment system based on RPA technology according to an embodiment of the present application; Figure 2 is a schematic diagram of the structure of a writing system according to an embodiment of the present application; Figure 3 is a schematic diagram of interaction between a first service terminal and a second service terminal according to an embodiment of the present application; Figure 4 is a structural schematic diagram of a writing system in another embodiment of the present application; Figure 5 is a structural diagram of a diagnosis and treatment system based on RPA technology in another embodiment of the present application; Figure 6 It is a flowchart of a method for obtaining a first diagnostic result according to an embodiment of the present application.

[0016] In the diagram: 01, the first diagnosis and treatment system, 02, the second diagnosis and treatment system, 011, the writing system, 012, the diagnosis system, 0111, the consultation subsystem, 0112, the face-to-face consultation subsystem, 0113, the historical data extraction subsystem, 013, the query system. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0018] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0019] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0020] To facilitate the description of the inventive concept of this application, a brief description of medical information technology is given below.

[0021] Based on the two problems highlighted by the continuous increase of information software systems in medical institutions, some medical structures, in order to improve the efficiency of doctors, currently have a method of arranging doctor assistants to specifically operate the information software system to solve these two problems. However, this still requires a lot of manpower and material resources. Therefore, how to solve these two problems based on advanced technology has become a major problem currently faced.

[0022] In view of this, a diagnosis and treatment system and a diagnosis and treatment method based on RPA technology are provided in an embodiment of the present application. In this scheme, a first diagnosis and treatment system and at least one second diagnosis and treatment system are included. The first diagnosis and treatment system is used to collect various information of the patient. The second diagnosis and treatment system obtains and enters the preset information to be obtained based on the various information obtained by the RPA robot through the first diagnosis and treatment system. In this way, for doctors, the patient's information only needs to be obtained and entered once, and there is no need to frequently switch between systems due to the existence of multiple diagnosis and treatment systems (or multiple information software systems), which reduces the complexity of doctors using software systems and improves the efficiency of doctors' diagnosis and treatment work. Secondly, the setting of the pre-questioning subsystem in the first diagnosis and treatment system makes it no longer necessary for doctors to repeatedly ask and enter some basic questions when they ask questions, which further reduces the complexity of doctors using software systems and improves the efficiency of doctors' diagnosis and treatment work.

[0023] In one embodiment of the present application, a diagnosis and treatment system based on RPA technology is provided. Figure 1 , including a first diagnosis and treatment system 01 and at least one second diagnosis and treatment system 02, wherein the first diagnosis and treatment system includes a writing system 011 and a diagnosis system 012.

[0024] Please refer to Figure 2The writing system 011 includes a pre-questioning subsystem 0111 and a face-to-face consultation subsystem 0112. The pre-questioning subsystem 0111 is configured to conduct a pre-questioning of the patient and generate pre-questioning information. The face-to-face consultation subsystem 0112 is configured to obtain the doctor's question and the patient's reply, respectively, and generate face-to-face consultation information.

[0025] In one embodiment, the pre-consultation subsystem 0111 includes a first service terminal and a first user terminal, the first user terminal is the terminal where the patient is located, and the first service terminal is the terminal where the patient is treated in the hospital. Figure 3 , the interaction between the first service terminal and the second service terminal is configured as follows: Step S100: the first service terminal sends a pre-consultation request to the first user terminal in response to a received user's consultation request.

[0026] The user's medical consultation request may be generated in response to the user's successful registration information or in response to the user's medical consultation check-in information. If the user's successful registration information is generated, the patient may start to enter the pre-consultation information after the registration is successful. If the user's medical consultation check-in information is generated, the patient may enter the pre-consultation information during the waiting time period after successfully checking in at the hospital.

[0027] The content of the pre-consultation can be set based on needs. In one embodiment, the content of the pre-consultation may include the patient's chief complaint (the patient's active description of the condition), current medical history (which may include the occurrence, development, evolution and treatment of the condition), past medical history (which may include past health conditions and diseases suffered in the past. Past health conditions may include eating habits, etc.) and allergy history, etc.

[0028] Step S200: The first user terminal displays the pre-consultation request confirmation interface in response to the received pre-consultation request.

[0029] In one embodiment, the pre-consultation request interface may be a link pop-up window, which may be switched to the pre-consultation page in response to a confirmation command in the link pop-up window selected by the user. The pre-consultation request confirmation interface may be specifically configured according to requirements.

[0030] Step S300: the first user terminal sends pre-consultation request confirmation information to the first service terminal in response to the received pre-consultation request confirmation instruction.

[0031] In one embodiment, the pre-consultation request interface based on the link pop-up window may display a "confirmation" button, and the user may select the confirmation button so that the first user terminal receives the pre-consultation request confirmation instruction and sends the pre-consultation request confirmation information to the first service terminal.

[0032] Step S400: the first service terminal sends pre-consultation content to the first user terminal in response to the pre-consultation request confirmation information returned by the first user terminal.

[0033] Step S500: The first user terminal displays the pre-consultation content in response to the received pre-consultation content, and sends the pre-consultation reply content confirmation instruction to the first service terminal in response to the received pre-consultation reply content confirmation instruction.

[0034] The user can enter the reply content based on the pre-consultation content displayed on the first user terminal. In one embodiment, the user can enter the pre-consultation reply content based on text and / or voice. The display of the pre-consultation content can be based on one round of displaying all the pre-consultation content, or it can be based on the patient's condition, The pre-consultation content can be displayed in multiple rounds. In one embodiment, after the user enters a certain item, a part, or all of the pre-consultation content, the pre-consultation reply content entered can be confirmed through the pre-consultation reply content confirmation interface.

[0035] Step S600: The first service terminal extracts the pre-consultation reply content and generates pre-consultation information in response to the pre-consultation reply content confirmation instruction sent by the first user terminal.

[0036] In one embodiment, based on RPA technology and an RPA robot, in response to a pre-consultation reply content confirmation instruction, the pre-consultation reply content can be automatically extracted and pre-consultation information can be generated.

[0037] In one embodiment, the pre-consultation information may exist in the form of a pre-consultation information table. Based on the RPA robot, in response to the pre-consultation reply content confirmation instruction, the pre-consultation reply content is automatically extracted and the pre-consultation information table is filled in.

[0038] The pre-consultation subsystem based on any of the above embodiments can effectively reduce the doctor's repetitive questions about the content of the previous pre-consultation during face-to-face consultations, reduce the patient's repetitive answers, and thus improve the efficiency of the doctor's diagnosis and treatment work.

[0039] In one embodiment, the consultation subsystem 0112 is configured to collect and record consultation content in response to a recording instruction of consultation questions, collect and record consultation reply content in response to a recording instruction of consultation replies, and extract the consultation questions and consultation reply content and generate consultation information in response to the recorded consultation questions and consultation reply content.

[0040] In one embodiment, the recording instruction of the face-to-face consultation questions and / or the recording instruction of the face-to-face consultation replies may be a keyword trigger instruction, and the keyword may be a collected text keyword or a keyword obtained based on voice recognition. In one embodiment, the recording instruction of the face-to-face consultation questions and / or the recording instruction of the face-to-face consultation replies may be an interface trigger instruction. For example, by selecting the recording interface of the face-to-face consultation questions, the recording instruction of the face-to-face consultation questions may be obtained; by selecting the recording interface of the face-to-face consultation replies, the recording instruction of the face-to-face consultation replies may be obtained.

[0041] In one embodiment, based on RPA technology and RPA robots, in response to recorded consultation questions and consultation reply contents, consultation questions and consultation reply contents can be extracted and consultation information can be generated. In which, in response to recorded consultation questions and consultation reply contents, the following can be included: in response to the completion of recording of a content, for example, starting the recording of the next content, which indicates that the recording of the current content is completed, or the submission of the recorded content, which indicates that the recording is completed.

[0042] In one embodiment, the records of consultation questions and / or consultation responses may be recorded using voice recognition, text input, or a combination of voice recognition and text input to improve the efficiency of the doctor's diagnosis and treatment work.

[0043] In one embodiment, the consultation information may exist in the form of a consultation information table. Based on the RPA robot, in response to the recorded consultation questions and consultation response contents, the consultation questions and consultation response contents are automatically extracted and the consultation information table is filled in.

[0044] In one embodiment, please refer to Figure 4 The writing system 011 also includes a historical data extraction subsystem 0113, which is configured to query whether the patient is a historical patient in response to the patient's registration information. If so, the patient's personal basic information and historical medical information are automatically extracted and sent to the second user terminal where the patient's doctor is located; if not, the patient's personal basic information is obtained and sent to the second user terminal where the patient's doctor is located.

[0045] After the patient registers, based on the patient's registration information, such as the ID number, it can be queried whether the patient is seeking medical treatment for the first time in the current hospital, that is, whether he is a historical patient. If it is not the first time to seek medical treatment, it means that the patient is a historical patient of the current hospital, and the patient's personal basic information (such as gender, age, address, occupation, contact information, etc.) and historical diagnosis and treatment information in the hospital's medical record system can be automatically extracted, and the patient's personal basic information and historical diagnosis and treatment information are automatically filled into the corresponding position of the electronic medical record page for the patient to see the doctor. In this way, this information is no longer repeatedly asked and repeatedly entered during the face-to-face consultation between the doctor and the patient, effectively improving the doctor's diagnosis and treatment efficiency and writing efficiency. If the patient is seeking medical treatment for the first time, a personal basic information collection link is automatically sent to the first user terminal where the patient is located, and the patient enters the personal basic information, thereby realizing the automatic collection of the patient's personal basic information, and the collected patient's personal basic information is filled into the corresponding position of the electronic medical record page for the patient to see the doctor. In this way, this information is no longer repeatedly asked and repeatedly entered during the face-to-face consultation between the doctor and the patient, effectively improving the doctor's diagnosis and treatment efficiency and writing efficiency.

[0046] In one embodiment, the patient's basic personal information and / or historical medical information is automatically extracted based on an RPA robot.

[0047] In one embodiment, please refer to Figure 5 The first diagnosis and treatment system 01 also includes a query system 013, which is configured to obtain and display corresponding query information in response to the obtained query conditions.

[0048] In one embodiment, the query conditions may be obtained by text input, voice collection, etc.

[0049] In one embodiment, any item of entered information may be used as a query condition.

[0050] In one embodiment, the query condition may be a single condition query or a combined condition query (a logical combination of at least two query conditions (may include logical AND, logical OR, logical NOT, etc.)).

[0051] The diagnosis system 012 is configured to obtain a diagnosis result based on the medical information in the pre-consultation information and the consultation information, and the patient's test results.

[0052] In one embodiment of the present application, a diagnosis and treatment method is provided, which can be applied to the above-mentioned diagnosis system to obtain a diagnosis result, including: obtaining a diagnosis result based on medical information in pre-consultation information and face-to-face consultation information, and the patient's test results.

[0053] In one embodiment, the diagnosis result includes a first diagnosis result, see Figure 6, the method for obtaining the first diagnosis result includes: Step S10, obtaining first diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results.

[0054] Collect information from the pre-consultation information and the face-to-face consultation information that is helpful for disease diagnosis, such as historical symptoms, complications, course of disease, and clinical manifestations, as collected medical information. Combine the collected medical information with the patient's test results (which may include imaging test results, blood routine test results, etc.) to obtain the first diagnosis and treatment information.

[0055] Step S20, vectorizing the first diagnosis and treatment information to obtain first vector data.

[0056] The first diagnosis and treatment information is vectorized to obtain first vector data. The diagnosis and treatment information can be vectorized using the processing method of the prior art, which will not be described in detail here.

[0057] Step S30, calculating the similarity between the first vector data and each second vector data in the vector database, and obtaining the second vector data with the highest similarity. The vector database is obtained based on the medical record data of multiple historically diagnosed and treated patients.

[0058] In one embodiment, the diagnosis and treatment information of multiple historically treated patients can be vectorized to obtain multiple corresponding second vector data, and the obtained multiple second vector data can be included in the vector database, so as to calculate the similarity between the first vector data and each second vector data in the vector database, and obtain the second vector data with the highest similarity. The calculation method of the similarity of the vector data adopts the calculation method of the prior art, which will not be repeated here.

[0059] Step S40, obtaining a first diagnosis result of the patient based on the diagnosis result corresponding to the second vector data with the highest similarity.

[0060] In one embodiment, the diagnosis result corresponding to the second vector data with the highest similarity can be directly used as the first diagnosis result. In one embodiment, the diagnosis result corresponding to the second vector data with the highest similarity can be adjusted by expert experience to obtain the first diagnosis result.

[0061] In one embodiment, the diagnosis result includes a large model diagnosis result, and a method for obtaining the large model diagnosis result may include: Step S1000, obtaining second diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results.

[0062] In one embodiment, information that is useful for disease diagnosis in the pre-diagnosis information and the face-to-face consultation information, such as historical symptoms, complications, course of disease, and clinical manifestations, is collected as the collected medical information. The collected medical information is combined with the patient's test results (which may include imaging test results, blood routine test results, etc.) to obtain the second diagnosis and treatment information.

[0063] Step S2000: In response to the acquired second diagnosis and treatment information, a large model is identified based on the diagnosis result to obtain a large model diagnosis result. The large model obtained by the diagnosis result is a neural network model obtained by training in combination with a loss function.

[0064] In one embodiment, a final diagnosis result is obtained based on the first diagnosis result and the large model diagnosis result. When the first diagnosis result and the large model diagnosis result are consistent, the first diagnosis result or the large model diagnosis result can be directly used as the final diagnosis result. When the first diagnosis result and the large model diagnosis result are consistent, the final diagnosis result is obtained based on comprehensive judgment based on expert experience.

[0065] In one embodiment, the large model diagnosis result includes a second diagnosis result and a third diagnosis result, and a method for obtaining the large model diagnosis result includes: Step S2001, in response to the acquired second diagnosis and treatment information, a large model is identified based on the second diagnosis result to obtain a second diagnosis result. The large model for identifying the second diagnosis result is a neural network model for identifying diagnosis results obtained by training based on the medical records of multiple historical diagnosis and treatment patients in the hospital where the patient was treated, combined with the first loss function.

[0066] In one embodiment, the medical record data of multiple historical patients treated in the hospital where the patient was treated can be collected, and expert experience annotation can be performed to clarify the various disease diagnosis results (which may include disease type, cause and severity of the disease) of each medical record data as labels. The annotated data is preprocessed and converted into a format suitable for the input of the Hua Tuo model to obtain a data set. The data set is divided into a training set, a validation set and a test set. Among them, the training set is used for model training, the validation set is used to evaluate the performance of the model and adjust the hyperparameters during the training process, and the test set is used to finally evaluate the generalization ability of the model. Based on the preset training parameters, the training set is used as the input of the Hua Tuo model for training, the performance of the Hua Tuo model is evaluated and the hyperparameters are adjusted based on the validation set during the training process, and the generalization ability of the Hua Tuo model is evaluated based on the test set, thereby obtaining a trained improved Hua Tuo model. The trained improved Hua Tuo model is used as the second diagnosis result recognition model.

[0067] In one embodiment, a second diagnosis result recognition model corresponding to each treatment department may be trained based on the medical record data of the patients treated in the treatment department, so as to obtain a more accurate diagnosis result recognition model.

[0068] Based on the above embodiments, a diagnosis result recognition model that is more suitable for local patients can be obtained based on the characteristics of local patients.

[0069] Step S2002, in response to the acquired second diagnosis and treatment information, a third diagnosis result is obtained by identifying a large model based on the third diagnosis result; the large model for identifying the third diagnosis result is a neural network model for identifying diagnosis results obtained by training based on the medical record data of multiple historical diagnosis and treatment patients in multiple hospitals and the second loss function.

[0070] In one embodiment, the third diagnostic result acquisition model can adopt the existing Hua Tuo model. The Hua Tuo model, also known as Hua Tuo GPT, is an open source medical model of the existing ChatGPT, which has good natural language understanding of medical information. Patients can interact with Hua Tuo GPT in a conversational manner to realize department triage, auxiliary diagnosis and other functions, and provide assistance to doctors.

[0071] In at least one second diagnosis and treatment system 02, any one of the second diagnosis and treatment systems 02 is configured to obtain and enter preset information content from at least one of pre-consultation information, face-to-face consultation information and diagnosis results based on at least one RPA robot.

[0072] For each second diagnosis and treatment system, since the content and format to be filled in may be different, if the doctor fills it out manually, it is necessary to frequently convert between the various second diagnosis and treatment systems, which increases the complexity of the doctor's use of the software system and reduces the efficiency of the doctor's diagnosis and treatment work. Based on this, on the basis of the pre-consultation information, face-to-face information and diagnosis results obtained by the first diagnosis and treatment system, for any second diagnosis and treatment system, its RPA robot can be customized so that the customized RPA robot can automatically extract the required information from at least one of the pre-consultation information, face-to-face information and diagnosis results, and enter it. In this way, the complexity of the doctor's use of the software system can be greatly reduced, and the efficiency of the doctor's diagnosis and treatment work can be improved.

[0073] Based on the diagnosis and treatment system of any of the above embodiments, for doctors, the patient's information only needs to be obtained and entered once, and there is no need to frequently switch between systems due to the existence of multiple diagnosis and treatment systems (or multiple information software systems), which reduces the complexity of doctors using the software system and improves the efficiency of doctors' diagnosis and treatment work. Secondly, the setting of the pre-questioning subsystem in the first diagnosis and treatment system makes it unnecessary for doctors to repeatedly ask and enter some basic questions during the consultation, which further reduces the complexity of doctors using the software system and improves the efficiency of doctors' diagnosis and treatment work.

[0074] In one embodiment of the present application, a computer-readable storage medium is provided, on which a program is stored. The stored program includes a method that can be loaded by a processor and process any of the above embodiments.

[0075] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0076] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A diagnosis and treatment system based on RPA technology, characterized in that: comprising a first diagnosis and treatment system and at least one second diagnosis and treatment system, wherein the first diagnosis and treatment system comprises a writing system and a diagnosis system; The writing system includes a pre-questioning subsystem and a face-to-face consultation subsystem; the pre-questioning subsystem is configured to conduct a pre-questioning of the patient and generate pre-questioning information; the face-to-face consultation subsystem is configured to obtain the doctor's face-to-face consultation questions and the patient's face-to-face consultation replies, respectively, and generate face-to-face consultation information; The diagnostic system is configured to obtain a diagnostic result based on the medical information in the pre-diagnosis information and the face-to-face consultation information, and the patient's test results; Among the at least one second diagnosis and treatment system, any one of the second diagnosis and treatment systems is configured to obtain and enter preset information content from at least one of the pre-consultation information, face-to-face consultation information and diagnosis results based on at least one RPA robot.

2. The diagnosis and treatment system according to claim 1, characterized in that: The pre-consultation subsystem includes a first service terminal and a first user terminal, the first user terminal is a terminal where the patient is located, and the first service terminal is a terminal where the patient is treated in a hospital; the first service terminal is configured to send a pre-consultation request to the first user terminal in response to a received user's medical request, and in response to the pre-consultation request confirmation information returned by the first user terminal, send pre-consultation content to the first user terminal, and in response to the pre-consultation reply content confirmation instruction sent by the first user terminal, extract the pre-consultation reply content and generate pre-consultation information; The first user terminal is configured to display the pre-consultation request confirmation interface in response to the received pre-consultation request, and send pre-consultation request confirmation information to the first service terminal in response to the received pre-consultation request confirmation instruction, display the pre-consultation content in response to the received pre-consultation content, and send the pre-consultation reply content confirmation instruction to the first service terminal in response to the received pre-consultation reply content confirmation instruction.

3. The diagnosis and treatment system according to claim 1, characterized in that: The consultation subsystem is configured to collect and record the consultation content in response to a recording instruction of the consultation questions, collect and record the consultation reply content in response to a recording instruction of the consultation reply, and extract the consultation questions and consultation reply content and generate consultation information in response to the recorded consultation questions and consultation replies.

4. The diagnosis and treatment system according to claim 1, characterized in that: The writing system also includes a historical data extraction subsystem, which is configured to query whether the patient is a historical patient in response to the patient's registration information. If so, the patient's personal basic information and historical medical information are automatically extracted and sent to the second user terminal where the patient's doctor is located; if not, the patient's personal basic information is obtained and sent to the second user terminal where the patient's doctor is located.

5. The diagnosis and treatment system according to claim 1, characterized in that: The first diagnosis and treatment system also includes a query system, which is configured to obtain and display corresponding query information in response to the obtained query conditions.

6. A diagnosis and treatment method, characterized in that: A diagnostic system that can be used in a diagnosis and treatment system as described in any one of claims 1 to 5 to obtain a diagnosis result, the method comprising: obtaining a diagnosis result based on medical information in pre-consultation information and face-to-face consultation information, and the patient's test results.

7. The diagnosis and treatment method according to claim 6, characterized in that: The method of obtaining the diagnosis result based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results, includes: Obtaining first diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results; Vectorizing the first diagnosis and treatment information to obtain first vector data; Calculating the similarity between the first vector data and each second vector data in a vector database to obtain the second vector data with the highest similarity; the vector database is obtained based on the medical record data of multiple historically diagnosed and treated patients; The first diagnosis result of the patient is obtained based on the diagnosis result corresponding to the second vector data with the highest similarity.

8. The diagnosis and treatment method according to claim 7, characterized in that: The method of obtaining the diagnosis result based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results, includes: Obtaining second diagnosis and treatment information based on the medical information in the pre-consultation information and the face-to-face consultation information, and the patient's test results; In response to the acquired second diagnosis and treatment information, the input of the large model is identified based on the diagnosis result to obtain the large model diagnosis result; the large model obtained by the diagnosis result is a neural network model obtained by training in combination with the loss function.

9. The diagnosis and treatment method according to claim 8, characterized in that: Based on the first diagnosis result and the large model diagnosis result, a final diagnosis result is obtained.

10. The diagnosis and treatment method according to claim 8 or 9, characterized in that: The large model diagnosis result includes a second diagnosis result and a third diagnosis result. The second diagnosis information is used as an input of the diagnosis result identification large model to obtain the large model diagnosis result, including: In response to the acquired second diagnosis and treatment information, a large model is identified based on the second diagnosis result to obtain a second diagnosis result; the large model for obtaining the second diagnosis result is a neural network model for identifying diagnosis results obtained by training based on the medical record data of multiple historical diagnosis and treatment patients in the hospital where the patient was treated, combined with the first loss function; In response to the acquired second diagnosis and treatment information, a third diagnosis result is obtained based on a large model for identifying the third diagnosis result; the large model for identifying the third diagnosis result is a neural network model for identifying diagnosis results obtained based on medical record data of multiple historical diagnosis and treatment patients in multiple hospitals, combined with training using the second loss function.

Images