A method, device and system for generating electronic medical record information

Abstract

Embodiments of the present invention provide a method, apparatus, and system for generating electronic medical record information, which relate to the field of digital medical technology and can simplify the consultation process and improve the consultation efficiency. The method includes: retrieving a corpus of a target object from a pre-stored database; obtaining voice information of the conversation between a user and a doctor, where the voice information includes real-time voice information and / or recorded voice information; performing voice recognition on the voice information according to the corpus to obtain a voice recognition result; performing semantic analysis on the voice recognition result to generate object status information of the target object in the electronic medical record. This method can be applied to the process of generating electronic medical records.

Description

Technical Field

[0001] The present invention relates to the field of digital medical technologies, and particularly to a method, apparatus, and system for generating electronic medical record information. Background Art

[0002] With the popularization of medical electronic informatization, electronic medical records have become an essential way for major hospitals to record medical information.

[0003] Existing electronic medical record generation solutions require doctors to start the installed electronic medical record program on the computer. Then, during the consultation process, manually input the medical record content using an electronic medical record template and store it as the patient's electronic medical record. However, this operation method will bring additional burdens to doctors and affect the consultation efficiency. Summary of the Invention

[0004] Embodiments of the present invention provide a method, apparatus, and system for generating electronic medical record information, which can simplify the consultation process and improve the consultation efficiency.

[0005] To achieve the above object, embodiments of the present invention adopt the following technical solutions:

[0006] On the one hand, embodiments of the present invention provide a method for generating electronic medical record information, including: retrieving a corpus of a target object from a pre-stored database; obtaining voice information of the conversation between a user and a doctor, where the voice information includes real-time voice information and / or recorded voice information; performing voice recognition on the voice information according to the corpus to obtain a voice recognition result; performing semantic analysis on the voice recognition result to generate object status information of the target object in the electronic medical record.

[0007] Further, the object status information includes: text information and / or image information reflecting the status of the target object.

[0008] Further, after performing semantic analysis on the voice recognition result to generate the object status information of the target object, it further includes: displaying the object status information to the user.

[0009] Further, when the object status information includes the image information, before generating the object status information of the target object, it further includes: retrieving an image library of the target object from the database; selecting a standard image of the target object in a healthy state from the image library for display.

[0010] Further, displaying the object status information to the user includes: selecting an organ image corresponding to the target object status from the image library to update the standard image or generate a target object comparison image; or, correcting the standard image according to the target object status to obtain a target object image or a target object comparison image corresponding to the target object status.

[0011] Further, after performing speech recognition on the voice information according to the corpus to obtain a speech recognition result, it further includes: adding the voice information and the speech recognition result as a pair of corpus samples to the corpus.

[0012] Further, performing speech recognition on the voice information according to the corpus to obtain a speech recognition result includes: performing speech recognition on the voice information to obtain a preliminary recognition result; searching the corpus for a target corpus sample matching the voice information; and correcting the preliminary recognition result according to the target corpus sample to obtain the speech recognition result.

[0013] Further, when the object status information includes the image information and the text information, the method further includes: if the text information is modified, updating the image information according to the modified text information; if the image information is modified, updating the text information according to the modified image information.

[0014] On the other hand, an embodiment of the present invention provides an electronic medical record generation device, including: an acquisition unit for retrieving a corpus of a target object from a pre-stored database; acquiring voice information of a conversation between a user and a doctor, the voice information including real-time voice information and / or recorded voice information; a recognition unit for performing speech recognition on the voice information according to the corpus to obtain a speech recognition result; and an execution unit for performing semantic analysis on the speech recognition result to generate the object status information of the target object.

[0015] Further, the execution unit is further configured to display the object status information to the user.

[0016] Further, when the object status information includes image information, the acquisition unit is further configured to retrieve an image library of the target object from the database; the execution unit is further configured to select a standard image of the target object in a healthy state from the image library for display.

[0017] Further, the execution unit is specifically configured to: select an organ image corresponding to the target object state from the image library to update the standard image or generate a comparison map of the target object; or, correct the standard image according to the target object state to obtain a target object image or a comparison map of the target object corresponding to the target object state.

[0018] Further, the apparatus further includes: an adding unit, configured to add the voice information and the voice recognition result as a pair of corpus samples to the database.

[0019] Further, the recognition unit is specifically configured to: perform voice recognition on the voice information to obtain a preliminary recognition result; search for a target corpus sample matching the voice information from the corpus; and correct the preliminary recognition result according to the target corpus sample to obtain the voice recognition result.

[0020] Further, when the object state information includes image information and text information, the apparatus further includes: an updating unit, configured to: when the disease symptom description is modified, update the organ image according to the modified disease symptom description; and when the organ image is modified, update the disease symptom description according to the modified organ image.

[0021] So far, the embodiments of the present invention provide a method, an apparatus and a system for generating electronic medical record information, which can retrieve a corpus of a target object from a pre-stored database; further, when a user and a doctor communicate in natural language or record, the voice information of the communication can be obtained; and the voice information obtained is subjected to voice recognition according to the corpus to obtain a voice recognition result; then, semantic analysis is performed on the voice recognition result to determine the target object state of the target object, so as to generate the object state information of the target object in the electronic medical record. It can be seen that in the above method, during the medical consultation process, by obtaining the voice information when the user and the doctor communicate, the target object state information of the disease-related target object can be analyzed for the user, and there is no need for the doctor to manually input the corresponding target object state and other disease symptom descriptions for the user. Therefore, the medical consultation process can be simplified and the medical consultation efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic structural diagram of a system for generating electronic medical record information provided by an embodiment of the present invention;

[0023] Figure 2 is a flowchart of a method for generating electronic medical record information provided by an embodiment of the present invention Figure 1 ;

[0024] Figure 3 is a flowchart of a method for generating electronic medical record information provided by an embodiment of the present inventionFigure 2 ;

[0025] Figure 4 A user interface of a generating device provided by an embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of a generating device provided by an embodiment of the present invention Figure 1 ;

[0027] Figure 6 A schematic structural diagram of a generating device provided by an embodiment of the present invention Figure 2 ;

[0028] Figure 7 A schematic structural diagram of a generating device provided by an embodiment of the present invention Figure 3 ;

[0029] Figure 8 A schematic structural diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0031] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0032] An embodiment of the present invention provides a method for generating electronic medical record information, which can be applied to an electronic medical record generation system 100 as shown in Figure 1 . The system 100 includes a generating device 01 for electronic medical records (abbreviated as generating device in subsequent embodiments), and a database 02 that is data-connected to the generating device 01. The database 02 stores a corpus and / or an image library of a target object.

[0033] Among them, the corpus refers to a large-scale electronic text library that has been scientifically sampled and processed. With the help of computer analysis tools, users can carry out relevant language theory and application research.

[0034] Specifically, the corpus can store multiple pairs of corpus samples. Each pair of corpus samples refers to the original voice information and the corresponding correct electronic text of the original voice information. For example, the voice information of "I am an Olympic champion" can be used as the original voice information. Through manual annotation or speech recognition, the corresponding correct electronic text obtained is "I am an Olympic champion". Then, this voice information and the electronic text are used as a pair of corpus samples.

[0035] In addition, the generating device 02 can be set in the consulting rooms of each department in the hospital, and the database 02 can also be integrated into the generating device 01 as a functional unit of the generating device 01. The embodiments of the present invention do not impose any restrictions on this.

[0036] Based on the above electronic medical record generation system 100, an embodiment of the present invention provides a method for generating electronic medical record information, as Figure 2 shown. The above method includes:

[0037] 101. The generating device retrieves the corpus of the target object from the pre-stored database.

[0038] Since each department in the hospital is generally divided according to different diseased organs, such as the heart disease department, the kidney disease department, and the cervical spondylosis department, etc., different corpora can also be set in the pre-stored database according to different diseased parts, such as the corpus for the heart, the corpus for the kidney, etc. Each corpus stores corpus samples for the corresponding object. The content in these corpus samples can be pathological data, symptom descriptions, prescriptions, etc. The embodiments of the present invention do not impose any restrictions on this.

[0039] Among them, the above object can be any diseased part, such as a diseased organ, blood, or bone, etc. The embodiments of the present invention do not impose any restrictions on this. For the convenience of description, in the subsequent embodiments, the target organ is used as an example of the target object for illustration.

[0040] Specifically, in step 101, when the user enters the consulting room of a certain department, the diseased organ corresponding to this department is the target organ (i.e., the target object). At this time, the generating device can retrieve the corpus of this target organ from the above database to facilitate subsequent speech recognition based on this corpus.

[0041] Among them, the above database can be stored in the server of the entire hospital, can also be stored in the generating device itself, or can also be stored in the cloud server. The embodiments of the present invention do not impose any restrictions on this.

[0042] 102. The generating device obtains the voice information of the conversation between the user and the doctor.

[0043] Among them, the voice information may include the voice information of the user's real-time conversation with the doctor, and / or the voice information that has been recorded.

[0044] Taking the voice information of the user's real-time conversation with the doctor as an example, after the user enters the consulting room, the user will talk with the doctor, that is, conduct a medical interview. During this process, the generating device can obtain the voice information of the conversation between the user and the doctor through a microphone. For example, it can obtain the voice information of the conversation between the user and the doctor periodically with a period of 20 seconds.

[0045] 103. The generating device performs speech recognition on the voice information according to the above-mentioned corpus to obtain a speech recognition result.

[0046] Then, in step 103, the generating device performs speech recognition on the voice information obtained in step 102 according to the corpus retrieved in step 101 to obtain a speech recognition result.

[0047] Specifically, the generating device can use existing speech recognition software to initially perform speech recognition on the above-mentioned voice information to obtain a preliminary recognition result. Since the medical field has strong professionalism, the obtained preliminary recognition result may not be accurate. For example, if the voice information spoken by the user is "I have coronary heart disease", the preliminary recognition result may not be able to determine whether what the user said is "I have coronary heart disease" or "I have related heart disease". At this time, two preliminary recognition results will be obtained. Furthermore, in order to accurately recognize the above-mentioned voice information, the generating device can search the corpus for a target corpus sample that matches the voice information. For example, the corpus sample with the highest similarity to the voice information found is used as the target corpus sample. Then, the generating device can correct the above-mentioned preliminary recognition result according to the target corpus sample to obtain a more accurate speech recognition result.

[0048] 104. The generating device performs semantic analysis on the speech recognition result to generate object state information of the target object.

[0049] During the semantic analysis process, the target object, that is, the name of the target organ, can be searched from the natural language recognized by speech. Then, the target object state of the target organ is extracted from the context containing the name of the target organ, and finally the organ state information of the target organ, that is, the object state information, is obtained. For example, left ventricular hypertrophy in the heart, hyperplasia of the first intervertebral disc, etc.

[0050] Among them, the object state information can be text information and / or image information, and its purpose is to reflect the state of the target organ.

[0051] 105. The generating device displays the object state information.

[0052] Finally, according to the organ state information of the target organ determined in step 104, the organ state information can be displayed to the user. For example, through the display screen of the generating device, or a 3D organ image when left ventricular hypertrophy occurs is displayed by a projector connected to the generating device, enabling the user to intuitively understand their own health condition without the doctor manually inputting the electronic text describing the state of the target object, thus simplifying the consultation process and improving the communication efficiency and consultation efficiency between doctors and patients.

[0053] Based on the above steps 101-105, an embodiment of the present invention provides a method for generating electronic medical record information, as Figure 3 shown, including:

[0054] 201. The generating device retrieves the corpus and image library of the target organ from the pre-stored database.

[0055] Similar to step 101, when the user enters the corresponding consulting room, the doctor or the user can click the corresponding function button in the generating device to trigger the generating device to retrieve the corpus of the target organ from the pre-stored database. For example, if the current consulting room is a heart disease consulting room, the corpus of the heart can be retrieved from the database.

[0056] Different from step 101, the above database also stores the image library of each organ. Taking the heart as an example, 2D / 3D pictures or animations of the heart in different states can be stored. Then, in step 201, the image library of the heart can be retrieved simultaneously when retrieving the corpus of the heart.

[0057] Of course, when the corpus and image library of the target organ are not retrieved, a schematic diagram of the human body can be displayed in the generating device. When the doctor or the user clicks on the diseased organ in the schematic diagram of the human body, the diseased organ can be used as the target organ, and the corpus and image library of the target organ can be retrieved.

[0058] 202. The generating device selects the standard image of the target organ in the healthy state from the above image library for display.

[0059] For example, the generating device can select the rhythmic animation of the heart in the healthy state from the above image library as the standard image for display, enabling the user to simply and intuitively understand the mechanism of heart rhythm.

[0060] 203. The generating device obtains the voice information of the conversation between the user and the doctor.

[0061] Among them, step 203 is similar to the above step 102, so it will not be elaborated here.

[0062] 204. The generating device performs speech recognition on the voice information according to the above corpus to obtain the speech recognition result.

[0063] Similar to step 103 above, after obtaining the voice information, the generating device performs voice recognition on the voice information according to the above corpus to obtain a voice recognition result.

[0064] It should be noted that during the voice recognition process, the obtained preliminary recognition result or the corrected voice recognition result can also be manually modified. For example, when there is no corpus sample in the corpus that matches the voice information, the doctor can manually correct the preliminary recognition result, and finally use the recognition result confirmed by the doctor as the above voice recognition result.

[0065] Further, after performing step 204, the following step 205 or steps 206 - 208 can be executed simultaneously or separately, and the embodiments of the present invention do not impose any restrictions on this.

[0066] 205. The generating device adds the voice information and the voice recognition result as a pair of corpus samples to the corpus.

[0067] In step 205, since the above voice recognition result has been confirmed by the doctor, that is, the voice recognition result is the correct electronic text corresponding to the above voice information, therefore, the voice information and the voice recognition result can be used as a pair of corpus samples and added to the corpus obtained in step 201, that is, the annotation of the corpus is realized simultaneously during the consultation process.

[0068] Then, if similar or identical voice information is encountered during subsequent consultations, the voice recognition can be referred to the corpus samples stored in step 205.

[0069] Of course, an appropriate artificial intelligence program can also be set in the generating device to enable the generating device to perform intelligent learning according to various corpora in the database, continuously improving the accuracy of voice recognition.

[0070] 206. The generating device performs semantic analysis on the voice recognition result to generate organ state information of the target organ.

[0071] Similar to step 104 above, after step 204, the generating device can perform semantic analysis on the voice recognition result to determine the target object state of the target organ.

[0072] And, after performing step 206, the generating device can execute the following step 207 or 208 separately or simultaneously, and the embodiments of the present invention do not impose any restrictions on this.

[0073] 207. When the organ state information includes image information, the generating device displays an organ image corresponding to the above organ state information to the user.

[0074] In step 207, when the image library retrieved in step 201 contains an organ image corresponding to the above organ state information, the generating device may select from the image library an organ image corresponding to the organ state information and replace the standard image of the target organ in the healthy state displayed in step 202. Of course, it is also possible to generate a comparison diagram of the target object state between the above standard image and the organ image corresponding to the organ state information, enabling the user to more intuitively see the changes in the target organ.

[0075] Alternatively, an image modification algorithm may also be preset in the generating device. In this way, after determining the target object state of the target organ, based on the above algorithm, the standard image displayed in step 202 can be directly corrected to obtain an organ image corresponding to the above target object state. Similarly, it is also possible to generate a comparison diagram of the target object state between the above standard image and the corrected organ image according to the algorithm.

[0076] 208. When the organ state information includes text information, the generating device uses this text information as the user's symptom description in the electronic medical record.

[0077] Exemplarily, the user interface of the generating device may be as Figure 4 shown. Among them, the display interface displays an organ image corresponding to the above organ state information. For example, if the target object state of the user's target organ is left ventricular hypertrophy, then an organ image corresponding to left ventricular hypertrophy can be displayed at the corresponding position in the above user interface.

[0078] Moreover, a template for the electronic medical record is also set in the user interface of the generating device. Different from the prior art where doctors need to manually input the medical record content, the generating device can use the text information in the organ state information determined in step 206 as the user's symptom description and fill it in the template of the electronic medical record. For example, a symptom description of "left ventricular hypertrophy" is generated in the text input box of the electronic medical record. In this way, the workload of doctors can be reduced and the consultation efficiency can be improved.

[0079] In addition, the symptom description generated in step 208 and the organ image displayed in step 207 can have two-way interaction. That is to say, if the text information in the symptom description in the electronic medical record is modified, for example, the doctor supplements the content of "bradycardia" in the symptom description, then the generating device can update the displayed organ image according to the modified symptom description. For example, reduce the displayed heart beating rate; or, if the organ image displayed in step 207 is modified, for example, the doctor can manually drag the right ventricle to make it larger, then the generating device can update the text information in the symptom description in step 208 according to the modified organ image. For example, add the text of "right ventricular hypertrophy" to the symptom description.

[0080] So far, the embodiments of the present invention provide a method for generating electronic medical record information, which can retrieve the corpus of the target object from a pre-stored database. Further, when the user and the doctor communicate or record in natural language, the voice information of the communication can be obtained, and the obtained voice information is subjected to speech recognition according to the corpus to obtain a speech recognition result. Then, semantic analysis is performed on the speech recognition result to determine the target object state of the target object, so as to generate the object state information of the target object in the electronic medical record. It can be seen that in the above method, during the consultation process, by obtaining the voice information when the user and the doctor communicate, the target object state information of the disease-related target object can be analyzed for the user, and there is no need for the doctor to manually input the corresponding target object state and other disease descriptions for the user. Therefore, the consultation process can be simplified and the consultation efficiency can be improved.

[0081] Figure 5 The following is a schematic structural diagram of a generating device provided by an embodiment of the present invention. The electronic medical record generating device provided by the embodiment of the present invention can be used to implement the above Figures 2 - 4 method implemented by each embodiment of the present invention shown. For the sake of convenience of description, only the parts related to the embodiments of the present invention are shown. For the specific technical details not disclosed, please refer to Figures 2 - 4 each embodiment of the present invention shown.

[0082] Specifically, as Figure 5 shown, the generating device includes:

[0083] An obtaining unit 11, configured to retrieve the corpus of the target object from a pre-stored database; obtain the voice information of the conversation between the user and the doctor, where the voice information includes real-time voice information and / or recorded voice information;

[0084] A recognition unit 12, configured to perform speech recognition on the voice information according to the corpus to obtain a speech recognition result;

[0085] An execution unit 13, configured to perform semantic analysis on the speech recognition result and generate the object state information of the target object in the electronic medical record.

[0086] Further, the execution unit is further configured to display the object state information to the user.

[0087] Further, when the object state information includes image information, the obtaining unit 11 is further configured to retrieve the image library of the target object from the database; the execution unit 13 is further configured to select and display the standard image of the target object in a healthy state from the image library.

[0088] Further, the execution unit 13 is specifically configured to: select an organ image corresponding to the target object state from the image library to update the standard image or generate a comparison graph of the target object; or correct the standard image according to the target object state to obtain a target object image or a comparison graph of the target object corresponding to the target object state.

[0089] Further, as Figure 6 shown, the apparatus further includes:

[0090] An adding unit 14, configured to add the voice information and the voice recognition result as a pair of corpus samples to the database.

[0091] Further, the recognition unit 12 is specifically configured to: perform voice recognition on the voice information to obtain a preliminary recognition result; search for a target corpus sample matching the voice information from the corpus; and correct the preliminary recognition result according to the target corpus sample to obtain the voice recognition result.

[0092] Further, as Figure 7 shown, when the object state information includes image information and text information, the apparatus further includes:

[0093] An updating unit 15, configured to: when the symptom description is modified, update the organ image according to the modified symptom description; and when the organ image is modified, update the symptom description according to the modified organ image.

[0094] Exemplarily, Figures 2 - 7 the electronic medical record generation apparatus shown in Figure 8 can be implemented in the form of a computer device (or system) in

[0095] Figure 8 The following is a schematic diagram of a computer device provided by an embodiment of the present invention. The computer device includes at least one processor 31, a communication bus 32, a memory 33, and at least one communication interface 34.

[0096] Among them, the processor 31 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the solution of the present invention.

[0097] The communication bus 32 may include a path for transmitting information among the above components. The communication interface 34 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Networks (WLAN), etc.

[0098] The memory 33 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can also be an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this. The memory can exist independently and be connected to the processor through the communication bus. The memory can also be integrated with the processor.

[0099] Among them, the memory 33 is used to store the application program code for executing the solution of the present invention and is controlled by the processor 31 for execution. The processor 31 is used to execute the application program code stored in the memory 33.

[0100] In a specific implementation, as an embodiment, the processor 31 may include one or more CPUs, such as Figure 8 CPU0 and CPU1 in

[0101] In a specific implementation, as an embodiment, the computer device may include multiple processors, such as Figure 8 processor 31 and processor 38 in

[0102] In a specific implementation, as an example, the computer device may further include an output device 35 and an input device 36. The output device 35 communicates with the processor 31 and can display information in various ways. For example, the output device 35 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 36 communicates with the processor 31 and can accept user input in various ways. For example, the input device 36 may be a mouse, a keyboard, a touch screen device, or a sensing device, etc.

[0103] The above computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, or a device with a Figure 8 similar structure therein. The embodiments of the present invention do not limit the type of the computer device.

[0104] So far, the embodiments of the present invention provide an electronic medical record generation device, which can retrieve the corpus of the target object from a pre-stored database; further, when the user and the doctor communicate in natural language or record, the voice information of the communication can be obtained; and the obtained voice information is subjected to speech recognition according to the corpus to obtain a speech recognition result; then the speech recognition result is semantically analyzed to determine the target object state of the target object, so as to generate the object state information of the target object in the electronic medical record. It can be seen that in the above method, during the consultation process, by obtaining the voice information when the user and the doctor communicate, the target object state information of the disease-related target object can be analyzed for the user, and there is no need for the doctor to manually input the corresponding target object state and other symptom descriptions for the user. Therefore, the consultation process can be simplified and the consultation efficiency can be improved.

[0105] In the description of this specification, specific features, structures, materials, or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0106] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for generating electronic medical record information, characterized in that, it includes: Retrieving the corpus and image library of the target object from a pre-stored database; Selecting and displaying the standard image of the target object in a healthy state from the image library; Obtaining the voice information of the conversation between the user and the doctor, where the voice information includes real-time voice information and / or recorded voice information; Performing voice recognition on the voice information according to the corpus to obtain a voice recognition result; Performing semantic analysis on the voice recognition result to generate the object status information of the target object in the electronic medical record, where the object status information includes image information and text information reflecting the status of the target object; Selecting the organ image corresponding to the status of the target object from the image library to update the standard image or generate a comparison graph of the target object; or, Correcting the standard image according to the status of the target object to obtain a target object image or a comparison graph of the target object corresponding to the status of the target object; If the text information is modified, updating the image information according to the modified text information; if the image information is modified, updating the text information according to the modified image information.

2. The method according to claim 1, characterized in that, after performing voice recognition on the voice information according to the corpus to obtain a voice recognition result, it further includes: Adding the voice information and the voice recognition result as a pair of corpus samples to the corpus.

3. The method according to claim 1 or 2, characterized in that, performing voice recognition on the voice information according to the corpus to obtain a voice recognition result, including: Performing voice recognition on the voice information to obtain a preliminary recognition result; Searching for a target corpus sample matching the voice information from the corpus; Correcting the preliminary recognition result according to the target corpus sample to obtain the voice recognition result.

4. An electronic medical record generation device, characterized in that, it includes: An acquisition unit for retrieving the corpus and image library of the target object from a pre-stored database; Obtaining the voice information of the conversation between the user and the doctor, where the voice information includes real-time voice information and / or recorded voice information; A recognition unit for performing voice recognition on the voice information according to the corpus to obtain a voice recognition result; An execution unit for: selecting and displaying the standard image of the target object in a healthy state from the image library; performing semantic analysis on the voice recognition result to generate the object status information of the target object in the electronic medical record, where the object status information includes image information and text information reflecting the status of the target object; The execution unit is specifically used for: selecting the organ image corresponding to the status of the target object from the image library to update the standard image or generate a comparison graph of the target object; or, correcting the standard image according to the status of the target object to obtain a target object image or a comparison graph of the target object corresponding to the status of the target object; An update unit, configured to: when the text information is modified, update the organ image according to the modified text information; when the organ image is modified, update the text information according to the modified organ image.

5. The device according to claim 4, wherein, the device further comprises: An adding unit, configured to add the voice information and the voice recognition result as a pair of corpus samples to the corpus.

6. The device according to claim 4 or 5, wherein, the recognition unit is specifically configured to: perform voice recognition on the voice information to obtain a preliminary recognition result; search for a target corpus sample matching the voice information from the corpus; and correct the preliminary recognition result according to the target corpus sample to obtain the voice recognition result.

7. An electronic medical record information generation system, wherein, the system includes the electronic medical record generation device according to any one of claims 4-6, and a database connected to the electronic medical record generation device in terms of data, and a corpus and / or an image library of a target object are stored in the database.

Images