CN111950235A - Intelligent medical text processing system - Google Patents
Intelligent medical text processing system Download PDFInfo
- Publication number
- CN111950235A CN111950235A CN202010818352.3A CN202010818352A CN111950235A CN 111950235 A CN111950235 A CN 111950235A CN 202010818352 A CN202010818352 A CN 202010818352A CN 111950235 A CN111950235 A CN 111950235A
- Authority
- CN
- China
- Prior art keywords
- data
- type
- terminal equipment
- server
- medical text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Abstract
The application discloses intelligent medical text processing system includes: a first type of terminal device for use by a patient to input patient data; the second type of terminal equipment is used for doctors to input diagnosis and treatment data; the server is used for storing and processing the data sent to the first type of terminal equipment or the second type of terminal equipment; the first type terminal equipment and the second type terminal equipment are respectively in communication connection with the server so that the server can at least send data to the first type terminal equipment and the second type terminal equipment; the server includes: a data module and a processing module; the data module is at least used for storing data uploaded by the first type of terminal equipment or the second type of terminal equipment; the processing module is used for processing the data uploaded by the first type of terminal equipment or the second type of terminal equipment. The intelligent medical text processing system has the beneficial effects that the intelligent medical text processing system can be used for carrying out standardized processing on irregular sentences in medical texts, so that the doctor-patient communication efficiency is improved.
Description
Technical Field
The application relates to an intelligent medical text processing system, and belongs to the field of intelligent medical treatment.
Background
The improvement of medical technology can be positively assisted by analyzing and researching the existing medical data. In recent years, with the rapid development of electronic information technology, the data volume of electronic medical data generated in the medical field is increasing, the difficulty of extracting effective information from the electronic medical data is also increasing, and further, people begin to discuss and learn how to improve the improvement efficiency of the medical industry by using the character recognition technology.
Disclosure of Invention
An intelligent medical text processing system, comprising: a first type of terminal device for use by a patient to input patient data; the second type of terminal equipment is used for doctors to input diagnosis and treatment data; the server is used for storing and processing the data sent to the first type of terminal equipment or the second type of terminal equipment; the first type terminal equipment and the second type terminal equipment are respectively in communication connection with the server so that the server can at least send data to the first type terminal equipment and the second type terminal equipment; the server includes: a data module and a processing module; the data module is at least used for storing the data uploaded by the first type of terminal equipment or the second type of terminal equipment; the processing module is used for processing the data uploaded by the first type of terminal equipment or the second type of terminal equipment; the data module of the server is used for storing the patient data or the medical text in the diagnosis and treatment data; the processing module of the server comprises a neural network module, and the neural network module adopts the neural network trained by artificial indexing to process the medical text so as to acquire the acquired required data.
Further, the data in the medical text in the data module is divided into: native data, semi-native data, and non-native data.
Further, the native data comprises medical statement data, network medical text data, medical knowledge base data and medical literature base data.
Further, the non-native data includes electronic medical record data and health profile data.
Further, the semi-native data includes data automatically generated by the first class of terminal device, the second terminal device or the server, and devices with which they constitute a data interaction.
Further, the data model is generated by the neural network module. (the data pattern is not a module, but a data model formed by a neural network)
Further, the first type of terminal device, the second type of terminal device, or the server inputs data to a neural network module in the server.
Further, when processing the data of the second type of terminal device, the server takes the native data or data model obtained by processing the data of the first type of terminal device by the intelligent medical text processing method as the native data with priority matching.
Further, the server preferentially matches the data and the model which are already structured in the historical data of the first type terminal device when processing the new medical text in the same first type terminal device.
Further, when processing new medical texts in the same first type terminal device, the server preferentially pairs the data and the model of the corresponding disease according to the data and the disease corresponding to the model which are structured in the historical data of the first type terminal device.
The application has the advantages that: the intelligent medical text processing system is used for carrying out standardized processing on irregular sentences in medical texts so as to improve doctor-patient communication efficiency.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic block diagram of an intelligent medical text processing system according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of data interconnections among various portions of an intelligent medical text processing system according to an embodiment of the present application;
FIG. 3 is a schematic diagram of interaction between a first type of terminal device and the rest according to an embodiment of the present application
FIG. 4 is a flow diagram of a medical text recognition processing method according to an embodiment of the present application;
FIG. 5 is a diagram of entity tagging of an instance of text;
fig. 6 is a flow chart diagram of a medical text recognition processing method according to another embodiment of the present application.
The meaning of the reference symbols in the figures:
the system comprises an intelligent medical text processing system 100, a first type terminal device 101, a second type terminal device 102, a server 103, a physical examination device 104, a treatment device 105 and a second type terminal device 106.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, the intelligent medical text processing system includes: the system comprises a first type of terminal equipment, a second type of terminal equipment and a server.
The first type of terminal device is used by a patient to input patient data, and as a specific scheme, the first type of terminal device may include: the system comprises a first type of man-machine interaction device, a first type of processor and a first type of communication module. The first type of human-computer interaction device is used for implementing human-computer interaction, namely, for a patient to input information and feed back information to the patient, and as a more specific scheme, the first type of human-computer interaction device may include: a touch screen, a microphone and a sound box; the first type of processor is used for processing data according to a program, in particular data related to a patient input by the patient through the first type of human-computer interaction device.
Patient-related data is defined herein as patient data. The patient data may include: patient personal data, patient condition data, and other patient data. The patient personal data includes patient identification data (such as sex, age, home address, health care card number), biometric data (face recognition data, fingerprint recognition data), and the like.
Patient condition data includes: the medical health monitoring system comprises active disease data and passive disease data, wherein the active disease data is data actively input by a patient, and the passive disease data is data which is acquired by a first type of terminal equipment or additional physical examination equipment and is transmitted to the first type of terminal equipment and related to the physical condition of the patient.
As a preferred scheme, the first type of terminal device has a detection unit, and the detection unit can detect certain body index data of a patient, and as a further preferred scheme, the detection unit includes an infrared camera, and the infrared camera can take infrared pictures to detect body temperature data of the patient. Therefore, the patient can detect the body temperature before entering a hospital or a heating outpatient service, and upload data through the first type of terminal equipment, and the server can uniformly and collectively stage the patient to the hospital for the treatment according to the body temperature data of the patient and the change of the body temperature data, so that the concentration of a large number of patients is avoided, and epidemic infection is caused.
As an extension scheme, the first Type of terminal device has an extension interface, the extension interface can enable the first Type of terminal device to be externally connected with a physical examination device or a treatment device and interact data with the physical examination device or the treatment device, the extension interface can be a USB interface or a Type-C interface, and the physical examination device can include a blood pressure meter, a blood glucose meter, and the like; the treatment device may include an oxygen machine, a nebulizer, and the like. The first type of terminal equipment can obtain the detection data of the patient and also can obtain the treatment condition of the patient through the expansion interface, so that the disease condition data can be obtained.
As a further alternative, the first type terminal device has a first type communication module, and the first type terminal device may form a communication connection with the outside through the first type communication module, for example, form a communication connection with a server, or form a communication connection with the aforementioned physical examination device or treatment device. As a specific solution, the first type of communication module includes both a communication chip suitable for remote communication to implement long-distance wireless communication, such as remote communication implemented by 2G, 3G, 4G, and 5G communication chips, and a communication chip suitable for near field communication to implement near field wireless communication, such as near field communication implemented by WiFi, bluetooth, LoRa, and UWB communication chips. The first type of terminal equipment and the server adopt remote communication with higher data transmission rate, such as through a 4G or 5G network; the first type of terminal equipment, the physical examination equipment and the treatment equipment form near field communication.
The first-class terminal equipment can realize wireless data interaction with the physical examination equipment and the treatment equipment through the near-field communication chip in the first-class communication module, so that the cost increase and the inconvenience in use caused by the arrangement of the expansion interface are avoided.
As a specific solution, the first type of terminal device includes a first type of processor, and the first type of processor is used for preprocessing patient data. And the first type terminal equipment uploads the data preprocessed by the first type processor to the server. In particular, the first type of processor includes a first language processing unit for converting patient input non-native data into native data. The first processor can complete the structured processing of the data independently, or can realize the conversion of the data by the server through the data interaction with the server, and the whole program or part of the program. In addition, the first type of processor can integrate execution of other programs to process patient data or to provide feedback to the user.
Alternatively, the first type processor includes a first AI processing unit that directs the patient to input data, and the first AI processing unit directs the patient to query the patient for past input history, or to query the characteristics of the disease based on the gender, age, etc. of the user. The first AI processing unit may remember historical inputs and historical input habits of the user to perform intelligent prompting or to perform specialized questioning of the patient according to data received to the server, so as to track the condition of an illness or physical condition of the user to further accurately collect patient data.
As a specific embodiment, the first type of terminal device may be configured as a mobile terminal, such as a smart phone or a smart tablet. Of course, the first type of terminal device may also be a computer device such as a PC device that is not used for movement.
As another aspect of the present application, a second type of terminal device is used by a doctor to input clinical data, which includes medication data, treatment data, and other order data given by the doctor.
As a specific scheme, the second type of terminal device may adopt a configuration scheme similar to that of the first type of terminal device, and specifically, the second type of terminal device may include: the system comprises a second type human-computer interaction device, a second type processor and a second type communication module. The second type of human-computer interaction device is used for realizing human-computer interaction, namely, information is input by a doctor and information is fed back to a patient, and as a more specific scheme, the second type of human-computer interaction device may include: a touch screen, a microphone and a sound box; the second type of processor is used for processing data according to a program, in particular treatment-related data input by a doctor through the second type of human-computer interaction device.
Data related to patient treatment is defined herein as clinical data. The medical data may further include: personal data of doctors and data of hospitals.
As an extension scheme, the second Type of terminal device has an extension interface, the extension interface can enable the second Type of terminal device to be externally connected with the physical examination device or the treatment device and to interact data with the physical examination device or the treatment device, the extension interface can be a USB interface or a Type-C interface, and the physical examination device can include a blood pressure meter, a blood glucose meter, and the like; the treatment device may include an oxygen machine, a nebulizer, and the like. The second type of terminal equipment can obtain the detection data of the patient and the treatment condition of the patient through the expansion interface, so that the disease condition data can be obtained.
As a further alternative, the second type of terminal device has a second type of communication module, and the second type of terminal device may form a communication connection with the outside through the second type of communication module, for example, form a communication connection with a server, or form a communication connection with the aforementioned physical examination device or treatment device. As a specific solution, the second type of communication module includes both a communication chip suitable for remote communication to implement long-distance wireless communication, such as 2G, 3G, 4G, and 5G communication chips, and a communication chip suitable for near field communication to implement near field wireless communication, such as WiFi, bluetooth, LoRa, and UWB communication chips. The second type of terminal equipment and the server adopt remote communication with higher data transmission rate, such as through a 4G or 5G network; the second type of terminal equipment, the physical examination equipment and the treatment equipment form near field communication.
The second type of terminal equipment can realize wireless data interaction with the physical examination equipment and the treatment equipment through the near field communication chip in the second type of communication module, so that the cost increase and the inconvenience in use caused by the arrangement of an expansion interface are avoided.
As a specific solution, the second type of terminal device includes a second type of processor, and the second type of processor is used for preprocessing the patient data. And the second type terminal equipment uploads the data preprocessed by the second type processor to the server. In particular, the second type of processor includes a second language processing unit for converting patient input non-native data into native data. The second type processor can complete the structured processing of the data independently, or can realize the conversion of the data by the server through the data interaction with the server, and the whole program or part of the program. In addition, the second type of processor can integrate the execution of other procedures to process patient data for feedback to the physician.
Alternatively, the second type of processor includes a second AI processing unit, which can help a doctor input data, and the second AI processing unit can assist the doctor in inquiring about the doctor's inquiry by inquiring about the past input history of the patient, or prompt the doctor to inquire about the characteristics of the important disease according to the characteristics of the user's population such as sex and age. The second AI processing unit can remember the patient's anamnesis for intelligent prompting or prompt the doctor for corresponding data and provide the doctor with a corresponding standardized medical record template according to the data received to the server.
As a specific embodiment, the second type of terminal device may be configured as a mobile terminal, such as a smart phone or a smart tablet. Of course, the second type of terminal device may also be a computer device such as a PC device that is not used for movement. Preferably, the second type of terminal is a PC device.
It should be noted that the term "patient" in the present application refers to the patient in the broadest sense, that is, all the persons who have the diagnosis and treatment requirement and use the intelligent diagnosis and treatment system of the present application. The term "doctor" as used herein refers to the doctor in the broadest sense, i.e., all the personnel who participate in the diagnosis, examination, and treatment and use the intelligent review system of the present application.
As an extension scheme of the present application, the present application further includes a second type of terminal device, and the configuration of the third type of terminal device may refer to the first type of terminal device and the second type of terminal device. The third type of terminal device can be partially facing to the patient and partially facing to the medical staff, specifically, the second type of terminal device is constructed as a medical guide platform, a self-service inquiry machine, a payment registration machine and the like. The third type terminal device may also form data interaction with at least one of the first type terminal device, the second type terminal device, and the server.
As a preferred scheme, the first class terminal device may form data interaction with the second class terminal device and the third class terminal device through bluetooth, and after the user finishes pre-diagnosis through the first class terminal device, the user scans the two-dimensional code of the second class terminal device or the third class terminal device through the camera of the first class terminal device, thereby implementing pairing with the second class terminal device or the third class terminal device and acquiring the authority.
Taking pairing with a second type of terminal device as an example, the specific scheme is that after code scanning, a first type of terminal device acquires an address of the first type of terminal device, and sends a request to a server to acquire a key for bluetooth pairing, the server feeds back an instruction to the first type of terminal device to request a user of the first terminal device to perform identity identification, such as password or face identification, if the identification passes, the key for bluetooth pairing is sent to the first type of terminal device to realize bluetooth pairing, and meanwhile, the server sends corresponding information in the first type of terminal device to the second type of terminal device according to pairing information.
Therefore, when a patient makes a diagnosis, a doctor can acquire patient information from the second type of terminal equipment through code scanning, and acquire the right for generating a medical record and a treatment scheme on the server.
Referring to the foregoing scheme, the physical examination device and the treatment device in this application may both be implemented by using a similar scheme, and the physical examination device and the treatment device form a communication connection with at least one of the first type terminal device, the second type terminal device, and the server, so that the physical examination device sends the physical data of the patient to at least one of the first type terminal device, the second type terminal device, and the server.
As an alternative, since the mobile phone cannot be carried in part of treatment, the system for the back-consultation also comprises a bracelet used by the patient, wherein the bracelet comprises two-dimensional code information and can also be constructed to be provided with an RFID tag or an UWB tag to realize positioning. When a patient is treated, physical examination equipment and treatment equipment scan two-dimensional code information of a bracelet, the current patient is identified, then data of detection and treatment are recorded to a server, the patient obtains and sends a data request to the server through scanning the two-dimensional code information on the bracelet when the patient is convenient, the server judges whether a first type of terminal equipment has authority to obtain previous detection and treatment data according to a collection password or other identity authentication data of the first type of terminal equipment, if the server has the authority, all data of the previous corresponding bracelet are synchronized to a storage space of the server corresponding to the first type of terminal equipment to update the data.
The server of the application is used for storing and processing the data sent to the first type of terminal equipment or the second type of terminal equipment, and comprises: a data module and a processing module; the data module is at least used for storing data uploaded by the first type of terminal equipment or the second type of terminal equipment; the processing module is used for processing the data uploaded by the first type of terminal equipment or the second type of terminal equipment. It can be understood that the data module is a storage space, and the storage space may be an entity storage device, and may be a cloud storage space. The processing module is used for realizing a diagnosis function, and specifically comprises a machine processing module and a doctor processing module, wherein the machine processing module obtains diseases and medicines by a built-in diagnosis method according to symptom information input by a patient terminal (which refers to a first type of terminal equipment, the same below), the doctor processing module sends the symptom information input by the patient terminal to one of doctor terminals (which refers to a second type of terminal equipment, the same below), and the diseases and medicines are obtained through the diagnosis information output by the doctor terminal.
The data stored in the server comprises case data, on-line inquiry data, diagnosis and treatment knowledge, a pharmaceutical dictionary and scientific research documents. As a preferred scheme, the server is also provided with a neural network learning module which can learn according to data of the patient terminal, the doctor terminal and other data acquisition equipment in the system, so that intelligent judgment is realized.
The server further comprises: and the pushing module is at least used for pushing data to the first type of terminal equipment or the second type of terminal equipment. Specifically, the pushed data includes: auxiliary diagnosis inquiry strategy, auxiliary diagnosis examination strategy, auxiliary diagnosis strategy, differential diagnosis strategy, personalized treatment scheme, critical serious disease reminding and doctor advice treatment information.
In the specific diagnosis and treatment process, before diagnosis, a patient inputs basic information and diagnosis problems at a system terminal as a pre-inquiry; during diagnosis, a doctor receives the treatment problem of a patient at a system terminal, makes clinical diagnosis on the disease of the patient according to case data, examination data and diagnosis and treatment data, and makes a prescription; after the doctor visits, the academician carries out case quality control and clinic procedure quality control on the diagnosis result and the prescription of the doctor, and for the patient with the chronic disease, the system tracks the illness state of the patient and gives suggestions.
As shown in fig. 4, the medical text recognition processing method includes the following steps:
s1) setting a medical term library, wherein the medical term library stores native data; the native data comprises medical statement data, network medical text data, medical knowledge base data and medical literature base data.
S2) extracting the sentences to be processed in the medical text, carrying out sentence segmentation and syntactic analysis on the sentences to be processed, determining entity marks of the sentences to be processed according to the neural network training model and forming an entity mark sequence; the entity tag sequence is represented as (entity word 1, entity word 2, entity relationship), and the entity relationship represents the relationship between entity word 1 and entity word 2.
S3) screening the entities in the sentence to be processed according to the preset syntactic analysis screening rule, and determining the candidate standardized terms in the sentence to be processed. The syntactic analysis screening rule is as follows: screening entities in the sentence to be processed, determining candidate standardized terms in the sentence to be processed, and determining the types of the candidate standardized terms according to the entity types, wherein the steps of judging whether the sentence to be processed meets a preset syntax structure or not and discarding the entities in the sentence to be processed when the sentence to be processed meets the preset syntax structure are included.
S4) matching the candidate standardized terms in the sentence to be processed with the medical term library, and if the matching is successful, determining the candidate standardized terms in the sentence to be processed as standardized terms; if the matching is unsuccessful, the candidate standardized terms are corrected by a deletion method, and the re-matching is carried out.
The medical texts comprise outpatient prescription lists, physical examination lists, case books, hospitalized medical advice data, medicine enterprise medicine data, medicine enterprise sales data, medical knowledge base and literature base data, medicine specification data and the like.
The entity types comprise medicine specification entities, package entities, medicine name entities, body part entities, health condition entities and the like which are acquired according to a predetermined medicine specification database, a packaging specification database, a medicine name database, a physical examination specification database, a case database and the like, and preset entity marking rules can be manually set according to different entity types.
In a specific embodiment, an outpatient prescription is taken as a medical text to be identified, and the prescription records an oral medicine amoxicillin capsule, and then the oral medicine amoxicillin capsule is subjected to sentence segmentation to obtain the following single character sequences of oral taking, medicine taking, A, M, xi, forest, glue and capsule. And identifying the single character sequence according to a CRF model to identify the medical terms in the single character sequence. According to a preset medical term library, the oral amoxicillin capsule comprises an entity amoxicillin and an entity capsule, wherein the entity type corresponding to the amoxicillin is a medicine name entity, the entity type corresponding to the capsule is a medicine shape entity, and the capsule corresponds to the rear position of the amoxicillin, so that an entity marking sequence of the amoxicillin capsule is determined, and the standardized term of the amoxicillin capsule is determined to be the amoxicillin capsule through matching with the medical term library.
As further shown in fig. 5, medical records are extracted: "the patient finds the urethral orifice phyma in 1 year, is bright red, has the size of about 0.5 x 1cm, has smooth surface, does not have discomfort such as macroscopic hematuria and dysuria, the patient does not pay attention to the method, the urethral orifice phyma does not increase obviously in 1 year, the patient has no obvious inducement to the lower urethral hemorrhage before 6 months, has small amount and no discomfort such as fever and aversion to cold, the patient comes from the outpatient service of our hospital for further diagnosis and treatment, and the 'urethral caruncle' is planned to be admitted to the hospital; "since the disease, the spirit is clear, the spirit is good, the stomach is good, the sleep is normal, the stool is not very good, the urine is as above, and the weight is not obviously reduced".
The medical records are physically extracted to obtain clinical manifestations including time, size, modification and negative and general description, specifically, time before "1 year", clinical manifestations of "urethral orifice mass", modification of "bright red color", size of "0.5 x 1 cm", modification of "smooth surface", negative "no macroscopic hematuria", negative "no difficulty in urination", time after "1 year", clinical manifestations of "no obvious enlargement of urethral orifice mass", time before "6 months", inducement of "no obvious inducement", clinical manifestations of "urethral hemorrhage", modification of "small amount", negative "no fever and aversion to cold", possible disease name of "urethral caruncle", and other general description. The original data, namely the entity marker sequence (metformin hydrochloride sustained release tablets, diabetes and treatment) is obtained by the method of extracting the model through the entity relationship.
As a specific scheme, the first class terminal device, the second class terminal device or the server is used for executing the intelligent medical text processing method. As a preferred scheme, the first class terminal device and the second class terminal device may complete text preprocessing, i.e. steps of entity tagging, and the server may complete remaining matching steps, or the server may completely perform the method of the present application.
When the data of the second type of terminal equipment is processed, the native data or the model obtained after the data of the first type of terminal equipment is processed by the intelligent medical text processing method is used as the preset native data in a priority matching mode. This may reduce the time taken to execute the program.
When processing new medical texts in the same first type terminal device, the data and the model which are already structured in the historical data of the first type terminal device are preferentially matched. Therefore, not only can the quick text processing be carried out according to the historical data of the user, but also a personalized database can be arranged in the first terminal device, when the patient inputs the text, the medical text processing is preferentially carried out on the local machine, and when the text which does not appear is detected, the text is uploaded to the server to be processed by the server.
When processing new medical texts in the same first type terminal equipment, preferentially pairing data and models corresponding to the symptoms according to data and models which are already structured in historical data of the first type terminal equipment. This has the advantage that the data entered by the physician can be quickly mapped to standard data that has already been screened for patient-entered data.
As a further preferred solution, the first terminal device may obtain the stored native data and the model in the first terminal device through the bluetooth pairing with the second terminal device as described earlier. The data transmission can be realized through Bluetooth, and can also be called from a server after Bluetooth pairing.
As another embodiment of the present application, an intelligent medical text processing method of the present application includes:
step 1: a neural network is trained with the data to obtain raw data and a data model.
Step 2: acquiring medical texts in the patient data or the diagnosis and treatment data.
And step 3: the neural network is caused to process the medical text to obtain the required data that has been obtained.
As a specific scheme, in order to implement the intelligent medical text processing method of the present application, a neural network may be trained in an artificial indexing manner on a server to obtain corresponding data and a corresponding relationship between models, and then the medical text may be intelligently processed through the artificial neural network.
The neural network is not suitable for arranging a first class terminal and a second class terminal due to the operation requirement, as a preferred scheme, the server can process the medical text by adopting the neural network (hereinafter referred to as intelligent matching), the first class terminal and the second class terminal adopt the matching method (hereinafter referred to as machine matching) for processing, then data comparison is carried out in the server, if the matching rate of the comparison result exceeds a first preset value, the comparison result is input into the neural network again for processing, the result is matched with the machine matching result again, if the matching rate exceeds an expected value and the matching rate is compared with the last matching rate, the difference value of the matching rate is larger than zero, intelligent matching is carried out again until the matching rate exceeds a second preset value, if the difference value of the matching rate is larger than zero, whether the current matching is larger than the first preset value or not is judged, and if the current matching is larger than the first preset value, and then, carrying out the operation of the intelligent matching and the difference value of the matching rate again, if the intelligent matching and the difference value of the matching rate are smaller than the first preset value, judging the calculation times of the current matching rate, and if the calculation times are larger than or equal to the preset value, feeding the result back to manual processing to enable the data to be used as the material for the neural network processing.
As an extension, the first preset value is a dynamic value, which is a sum of a reference value and a correction value, wherein the correction value is related to the current number of matching rate calculations, and specifically, the correction value is in a linear relationship with the number of matching rate calculations.
Preferably, the feedback manual processing is fed back to the second type terminal for correction by a doctor, or is fed back to the first type terminal for correction.
As another preferred scheme, an active interaction mode is adopted at the first type terminal and the second type terminal to actively prompt and collect data, and the data is subjected to structured processing, so that the data processing difficulty is reduced. As a more specific solution, the problem of active prompting is that only matching can be performed according to user input, and active prompts or voices are derived from neural network learning, except that native data and models are output, and prompts aiming at the native data are output at the same time.
In order to implement the above solution, the present application also provides an intelligent medical text processing system, including: a first type of terminal device for use by a patient to input patient data; the second type of terminal equipment is used for doctors to input diagnosis and treatment data; the server is used for storing and processing the data sent to the first type of terminal equipment or the second type of terminal equipment; the first type terminal equipment and the second type terminal equipment are respectively in communication connection with the server so that the server can at least send data to the first type terminal equipment and the second type terminal equipment; the server includes: a data module and a processing module; the data module is at least used for storing data uploaded by the first type of terminal equipment or the second type of terminal equipment; the processing module is used for processing data uploaded by the first type of terminal equipment or the second type of terminal equipment; the data module of the server is used for storing medical texts in patient data or diagnosis and treatment data; the processing module of the server comprises a neural network module, and the neural network module adopts the neural network which is trained by artificial indexing to process the medical text so as to obtain the acquired required data.
Specifically, the data in the medical text in the data module is divided into: native data, semi-native data, and non-native data. The native data comprises medical statement data, network medical text data, medical knowledge base data and medical literature base data. The non-native data includes electronic medical record data and health profile data. Semi-native data includes data automatically generated by a first class of terminal device, a second terminal device or server, and the devices with which they constitute a data interaction. The data model is generated by a neural network module. The first type of terminal equipment, the second type of terminal equipment or the server inputs data to a neural network module in the server. When processing the data of the second type of terminal equipment, the server takes the native data or the data model obtained after the data of the first type of terminal equipment is processed by the intelligent medical text processing method as the native data which is matched preferentially. When processing new medical texts in the same first type terminal equipment, the server preferentially matches the data and the model which are already structured in the historical data of the first type terminal equipment. When the server processes a new medical text in the same first type terminal device, the server preferentially pairs the data and the model of the corresponding disease according to the disease corresponding to the data and the model which are already structured in the historical data of the first type terminal device.
As an extension scheme, patient's bracelet is equipped with a UWB label, and as the alternative, patient's bracelet is the disposable bracelet of making by macromolecular material that the hospital was distributed, and at the inside built-in UWB label device of disposable bracelet, also can independently encapsulate UWB label device after certainly, combine it to the bracelet body again, and as another kind of scheme, patient's bracelet also is constructed as an intelligent equipment, makes it have more functions, for example makes patient's bracelet have: the device comprises a display screen, a UWB tag device, a controller and a communication module; the display screen can be used for showing image information such as two-dimensional code, and communication module is used for realizing wireless communication, and the controller is used for controlling display screen, UWB label device and communication module.
For other devices of the present application, the patient bracelet needs to have a configuration of two-dimensional code and UWB tag devices to enable a specific control process.
The system of the present application further comprises: the UWB positioning base station is used for positioning the position of the patient bracelet or the first type of terminal equipment. The UWB positioning base station transmits the position data of the patient to the server, which can verify the dwell time of the user's treatment process based on the patient's position. When a user carries out various treatment links, the server activates the corresponding UWB positioning base station, if a correct UWB patient bracelet is detected, medical staff is informed through the second type of terminal equipment, the treatment equipment and the physical examination equipment, the patient is in place, then the medical staff scans the two-dimensional code of the patient bracelet again through the camera arranged on the second type of terminal equipment, the treatment equipment and the physical examination equipment, so that the identity of the patient is confirmed again, and when the link carries out treatment, the server predicts the waiting time of the queuing patient through UWB positioning base station data, so that the patient plans the time of self-examination or treatment according to the time predicted by the server.
As an extension, the system of the present application includes: millimeter wave detection device, millimeter precious detection device are used for detecting inherent attributes such as patient's height to record patient's gait data, then will pass through the combination of data and UWB location basic station data that millimeter detection device detected, even under the condition that the patient can not wear patient's bracelet at some, still can obtain patient's positional information through millimeter wave detection device.
The server takes the data of the UWB positioning base station and the data of the millimeter wave detection device as the basis for text processing, because the data are standardized when the positioning base station and the millimeter wave detection device are set. The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An intelligent medical text processing system, characterized by:
the intelligent medical text processing system comprises:
a first type of terminal device for use by a patient to input patient data;
the second type of terminal equipment is used for doctors to input diagnosis and treatment data;
the server is used for storing and processing the data sent to the first type of terminal equipment or the second type of terminal equipment;
the first type terminal equipment and the second type terminal equipment are respectively in communication connection with the server so that the server can at least send data to the first type terminal equipment and the second type terminal equipment;
the server includes: a data module and a processing module; the data module is at least used for storing the data uploaded by the first type of terminal equipment or the second type of terminal equipment; the processing module is used for processing the data uploaded by the first type of terminal equipment or the second type of terminal equipment;
the data module of the server is used for storing the patient data or the medical text in the diagnosis and treatment data;
the processing module of the server comprises a neural network module, and the neural network module adopts the neural network trained by artificial indexing to process the medical text so as to acquire the acquired required data.
2. The intelligent medical text processing system of claim 1, wherein:
the data in the medical text in the data module is divided into: native data, semi-native data, and non-native data.
3. The intelligent medical text processing system of claim 2, wherein:
the native data comprises medical statement data, network medical text data, medical knowledge base data and medical literature base data.
4. The intelligent medical text processing system of claim 3, wherein:
the non-native data includes electronic medical record data and health profile data.
5. The intelligent medical text processing system of claim 4, wherein:
the semi-native data includes data automatically generated by a first class of terminal device, a second class of terminal device or server, and devices with which they constitute a data interaction.
6. The intelligent medical text processing system of claim 5, wherein:
the data model is generated by the neural network module.
7. The intelligent medical text processing system of claim 6, wherein:
and the first type terminal equipment, the second type terminal equipment or the server inputs data to a neural network module in the server.
8. The intelligent medical text processing system of claim 7, wherein:
and when processing the data of the second type of terminal equipment, the server takes the original data or data model obtained after the data of the first type of terminal equipment is processed by the intelligent medical text processing method as the original data which is matched preferentially.
9. The intelligent medical text processing system of claim 8, wherein:
when processing new medical texts in the same first-class terminal equipment, the server preferentially matches the data and the model which are already structured in the historical data of the first-class terminal equipment.
10. The intelligent medical text processing system of claim 9, wherein:
when processing a new medical text in the same first type terminal device, the server preferentially pairs the data and the model of the corresponding disease according to the data which are structured in the historical data of the first type terminal device and the disease corresponding to the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010818352.3A CN111950235A (en) | 2020-08-14 | 2020-08-14 | Intelligent medical text processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010818352.3A CN111950235A (en) | 2020-08-14 | 2020-08-14 | Intelligent medical text processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111950235A true CN111950235A (en) | 2020-11-17 |
Family
ID=73342327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010818352.3A Pending CN111950235A (en) | 2020-08-14 | 2020-08-14 | Intelligent medical text processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950235A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114743693A (en) * | 2022-03-21 | 2022-07-12 | 北京左医科技有限公司 | Doctor-patient dialogue based center quality control method and center quality control device |
-
2020
- 2020-08-14 CN CN202010818352.3A patent/CN111950235A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114743693A (en) * | 2022-03-21 | 2022-07-12 | 北京左医科技有限公司 | Doctor-patient dialogue based center quality control method and center quality control device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105260588B (en) | A kind of health guards robot system and its data processing method | |
| US8392216B2 (en) | Association of data entries with patient records, customized hospital discharge instructions, and charting by exception for a computerized medical record system | |
| AU2003262725B8 (en) | Diagnostic instrument workstation | |
| CN111613291B (en) | Medicine management, classification and medical staff and patient association system | |
| WO2022267678A1 (en) | Video consultation method and apparatus, device and storage medium | |
| US11901059B2 (en) | System and device for remote monitoring | |
| US20220246299A1 (en) | Electronic patient advisor and healthcare system for remote management of chronic conditions | |
| CN111950235A (en) | Intelligent medical text processing system | |
| CN110544522A (en) | mobile nursing information system based on traditional Chinese medicine nursing program | |
| CN111950234A (en) | Processing method based on intelligent medical text processing system | |
| CN113724895A (en) | Day operation postoperative health monitoring system and method and health management platform | |
| CN105654406A (en) | Family health service platform system | |
| CN111863166A (en) | Face recognition management method for hospital | |
| JP2004030257A (en) | Medical information input system using electronic pen and program to be used for this | |
| US20140358583A1 (en) | System and method for confirming the identity of a patient | |
| CN111951984B (en) | Intelligent auxiliary diagnosis system | |
| CN112002381B (en) | Intelligent medical record data management system | |
| US8668138B1 (en) | System and method for inputting medical information | |
| US20230268039A1 (en) | Methods, systems, and computer-readable media for decreasing patient processing time in a clinical setting | |
| CN113990468B (en) | Mobile nursing system integrating breast milk and blood transfusion closed-loop management | |
| KR102596492B1 (en) | A Drug Dispenser Capable of Measuring non-contact Biometric Information | |
| KR20110000014U (en) | How to provide personal health information through mobile devices and system | |
| CN117253622A (en) | Disease data management system | |
| Lopez | DiAbVi: IoT-based Recommender System for Diabetic Patients | |
| KR20230050595A (en) | Server for integrated management of personal health records into global big data, method, and recording media thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |