Ultrasonic examination report input system and method

Abstract

The invention discloses an ultrasonic examination report input system and method, and the system comprises a voice recognition module which is used for collecting voice and converting the voice into computer text information; the interaction module is used for cooperating with user interaction to call, modify and store the report; the preset template module is used for calling a report template, and the report template comprises a preset text and a to-be-written text bar; a plurality of trigger keywords and binding words are preset in the voice recognition module, and each trigger keyword corresponds to one part of a to-be-written text column; when the collected voice information contains a trigger keyword, converting characters after the trigger keyword into computer character information, and filling the computer character information into a to-be-written text column corresponding to the trigger keyword; and after the keyword is triggered, ending the current character conversion through the binding language until the next trigger keyword is received. According to the scheme, the problems of human resource waste, low working efficiency caused by the fact that primary doctors are not equipped with assistants, and omission and errors of diagnosis reports can be relieved.

Description

Technical Field

[0001] The invention relates to a diagnosis auxiliary system, in particular to an ultrasonic examination report entry system and method. Background Art

[0002] The current ultrasound report is generally that the doctor collects the ultrasound image and enters the report on the computer through an assistant. Although this solution can speed up the diagnosis efficiency to a certain extent, it requires additional staffing. Some grassroots areas do not have assistants. At this time, the doctor needs to collect the ultrasound image and then enter it on the computer. On the one hand, it is easy to miss something. On the other hand, the diagnostic efficiency is low, and the doctor is responsible for many things, which may affect the diagnosis results. For this reason, it is also necessary to enable doctors to quickly generate reports during the ultrasound examination, even without the help of assistants, to reduce omissions. This is a solution that can maintain high diagnostic efficiency and more accurate diagnostic results while saving staffing. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an ultrasound examination report entry system and method, which can alleviate the waste of human resources and the low work efficiency caused by the lack of assistants for primary doctors, as well as the omissions and errors in diagnostic reports.

[0004] To achieve the above object, the present invention provides the following technical solutions: An ultrasound examination report entry system, comprising: Speech recognition module, used to collect speech and convert it into computer text information; The interactive module is used to cooperate with the user to call, modify and save the report; The preset template module is used to cooperate with the interactive module to call the report template, and the report template includes a preset text and a text column to be written; The speech recognition module is preset with several trigger keywords and ending words, and each trigger keyword corresponds to a part of the text column to be written; when the collected voice information contains a trigger keyword, the text after the trigger keyword is converted into computer text information and filled into the text column to be written corresponding to the trigger keyword; and the current text conversion is ended by the ending word after the trigger keyword until the next trigger keyword is received.

[0005] As a further improvement of the present invention, the voice recognition module has a closing remark entry module, which interacts with the user, uses voice to input the user's regular dialogue segments and analyzes and summarizes the closing remark, and the user enters the closing remark by correction and supplementation; the closing remark at least includes the customary ending word and pause duration.

[0006] As a further improvement of the present invention, the speech recognition module has a voiceprint recognition module for recognizing the voiceprint of the current user to filter the patient's voice.

[0007] As a further improvement of the present invention, the speech recognition module also records the entire speech, and records the speech in a database after classifying it according to the voiceprint. When the user interacts with the interactive module, he interacts with the corresponding text column to be written, and displays the entire speech segment content corresponding to the text in the text column to be written, and the content at least includes the text within at least five seconds before and after the corresponding text column to be written, and the selected text is filled or covered in the text column to be written by selecting it in the displayed content.

[0008] As a further improvement of the present invention, the interactive module interacts with the text field to be written by means of a mouse or touch screen, and displays a text box near the text field to be written. The corresponding full voice segment content is displayed in the text box and is used to assist the user in selecting.

[0009] As a further improvement of the present invention, the content in the text box corresponding to the text field to be written is marked with a color change.

[0010] A method for entering an ultrasonic examination report, the method comprising the following steps: Call the preset template; Ultrasound captures images and makes diagnoses based on them; Enter diagnostic information via voice; The speech recognition diagnostic information is converted into computer text information and entered into the database; Fill the corresponding text into the corresponding text column in the preset template by triggering the keyword; By interacting with the text field to be written, determine whether modification is required; If modification is required, the text within five seconds before and after the text column to be written will be displayed in a text box through the interactive text column to be written, and the user can select and fill in the text column to be written or cover the text column to be written, and save the report; If no modification is required, save the report through the interactive module.

[0011] The beneficial effect of the present invention is that the above keyword triggering can automatically trigger the process of communication between doctors and patients, or the doctor can trigger it when explaining to the patient. At this time, the diagnosis content can be quickly filled in with the communication, and the current required content can be filled in by triggering the ending remarks, avoiding excessive text filling. At this time, only one person is needed to perform ultrasound examination and report entry, at least relevant content can be entered into the report, which is convenient for doctors to recall and correct, avoid omissions, and can be quickly corrected and saved through the interactive module to form a final report, effectively solving the current problem of needing to be equipped with assistants to consume human resources or low inspection efficiency when there are no assistants. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flow chart of the method steps of the present invention; Figure 2 A reference diagram showing a state diagram for the report of the present invention; Figure numbers: 1. Preset template; 2. Text field to be written; 3. Text box. DETAILED DESCRIPTION

[0013] The present invention will be further described below in detail with reference to the embodiments shown in the accompanying drawings.

[0014] Reference Figure 1-2 As shown, An ultrasound examination report entry system, comprising: Speech recognition module, used to collect speech and convert it into computer text information; The interactive module is used to cooperate with the user to call, modify and save the report; The preset template module is used to cooperate with the interactive module to call the report template, and the report template includes a preset text and a text column 2 to be written; Several trigger keywords and ending words are preset in the voice recognition module, and each trigger keyword corresponds to a part of the text column 2 to be written; when the collected voice information contains a trigger keyword, the text after the trigger keyword is converted into computer text information and filled into the text column 2 to be written corresponding to the trigger keyword; and the current text conversion is ended by the ending word after the trigger keyword until the next trigger keyword is received.

[0015] In this solution, the voice recognition module is combined with a lavalier microphone to assist the diagnosing doctor in recording data, and it can be closer to the sound source. As a component of the software, the voice recognition is set on the computer to convert it into computer text information, which can be in English or Chinese. The interactive module is used for user interaction and can call, modify, save and other operations on the report.

[0016] Among them, the preset template module can form report templates for different departments through pre-editing, which is convenient for use in more departments. The preset text in the report is not editable and is a directly formed template. The text column 2 to be written can be edited. First, the voice is collected in conjunction with the voice recognition module. When the collected voice contains trigger keywords, the voice recognition module will fill the computer text information after the trigger keyword into the text column 2 to be written until the ending statement is triggered and the current text column 2 to be written is stopped until the next time the trigger keyword is received to continue voice recognition, conversion, and filling.

[0017] The above keyword triggers can be automatically triggered during the communication between doctors and patients, or when doctors are explaining to patients. At this time, the diagnosis content can be quickly filled in with the communication, and the current required content can be filled in by triggering the ending remarks to avoid filling in too much text. At this time, only one person is needed to perform ultrasound examination and report entry, at least relevant content can be entered into the report, which is convenient for doctors to recall and correct, avoid omissions, and can be quickly corrected and saved through the interactive module to form a final report, effectively solving the current problem of needing assistants to consume human resources or low inspection efficiency when there are no assistants.

[0018] Among them, the voice recognition module has a closing remark entry module. The closing remark entry module interacts with the user, uses voice to input the user's regular dialogue segments and analyzes and summarizes the closing remark. The user enters the closing remark by correction and supplementation; the closing remark at least includes the customary ending word and pause duration.

[0019] The ending entry module is used to assist users in learning. It can enter and judge the user's habitual ending, including the pause duration, and can identify whether the user's current paragraph has ended, so as to stop the current computer text information entry in time. This makes text entry more accurate and reduces the number and duration of subsequent corrections.

[0020] Since there is a lot of communication with the patient during the ultrasound examination, the voice recognition module in this solution has a voiceprint recognition module for identifying the voiceprint of the current user to filter the patient's voice.

[0021] The voiceprint recognition module can filter the patient's voice or accurately identify the current doctor's voice, and can classify the sound source to avoid irrelevant content of other characters appearing when filling in computer text in the text column 2 to be written.

[0022] Preferably, the voice recognition module also records the entire speech, and records the speech in a database after classifying it according to the voiceprint. When the user interacts with the interactive module, he interacts with the corresponding text column 2 to be written, and displays the entire speech segment content corresponding to the text in the text column 2 to be written, and the content at least includes the text within five seconds before and after the corresponding text column 2 to be written, and the selected text is filled in or overwritten in the text column 2 to be written by selecting it in the displayed content.

[0023] In the further configuration of the present scheme, the speech recognition module can convert the entire speech, and classify it in conjunction with voiceprint recognition, so that the corresponding patient and doctor can distinguish the content converted into computer text information, and record it in the database. When the doctor examines the report, if there are places that need to be corrected or the content in the text column 2 to be written is insufficient, interaction can be carried out to display the text within five seconds before and after the relevant content in the text column 2 to be written (an additional pop-up window can be used for display), and the displayed content can be used for selection by the doctor. If the selected text is a word that does not exist in the original text column 2 to be written, it can be filled in; if it is a part that exists in the original text column 2 to be written, it can be overwritten.

[0024] The solution can also back up the communication records between patients and doctors to form diagnostic records.

[0025] Preferably, the interactive module interacts with the text field 2 to be written by means of a mouse or a touch screen, and displays a text box 3 near the text field 2 to be written. The corresponding full voice segment content is displayed in the text box 3 and is used to assist the user in selecting.

[0026] The interactive module can be coordinated according to the type of display terminal. For example, if the display terminal is a touch screen, the interaction can be carried out through the touch screen. If the display terminal is a conventional display screen, the interaction can be carried out through the mouse. For the operation of interacting and modifying the text column 2 to be written, the text content within five seconds before and after the corresponding text content can be displayed during the operation for the doctor to select.

[0027] Preferably, after the text box 3 is displayed, the various text items corresponding to the existing contents in the text column 2 to be written have been marked with color changes, allowing the doctor to quickly find the corresponding position and increase or decrease the text desired to be filled in the text column 2 to be written by selection. Specifically, the existing contents in the text box 3 corresponding to the text column 2 to be written are changed to red, and the selection state is cleared by selecting the existing content, and the red color is changed to the original color, and the content that has not been selected is selected and changed to red, which allows the doctor to quickly select and edit in the text box 3, and the part marked in red will be directly filled in the text column 2 to be written without the need for additional confirmation, and the operation is more convenient, that is, when the doctor is selecting in the text box 3, the content in the text column to be written will change accordingly, and finally the doctor can manually make corrections in the text column 2 to be written.

[0028] In summary, this solution can quickly fill in the required content in the preset template 1, and can be quickly operated and corrected by doctors. It has the display and editing function of the text box 3, and can quickly display the corresponding previous and next texts in the text box 2 to be written, so that doctors can quickly operate the relevant content, and at least display the content within five seconds before and after for doctors to operate. Of course, it can be adjusted according to needs. It effectively solves the current waste of manpower that doctors need to be equipped with assistants for data entry, and also effectively solves the problem that some grassroots doctors do not have assistants and have low work efficiency. It can also avoid the problem of omissions or errors in reports due to the heavy workload of doctors.

[0029] Based on the above system and according to its operation process, a method for entering an ultrasonic examination report can also be formed, and the method includes the following steps: Call preset template 1; Ultrasound captures images and makes diagnoses based on them; Enter diagnostic information via voice; The speech recognition diagnostic information is converted into computer text information and entered into the database; Fill the corresponding text into the corresponding to-be-written text column 2 in the preset template 1 by triggering the keyword; By interacting with the text to be written column 2, determine whether modification is required; If modification is required, the text corresponding to the to-be-written text column 2 within at least five seconds before and after the to-be-written text column 2 is displayed through the text box 3, and is used for the user to select and fill in the to-be-written text column 2 or cover the to-be-written text column 2, and save the report; If no modification is required, save the report through the interactive module.

[0030] This method is the same as the aforementioned system process, and the technical effects achieved are also the same, so no further elaboration is made here.

[0031] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An ultrasonic examination report entry system, characterized in that: include Speech recognition module, used to collect speech and convert it into computer text information; The interactive module is used to cooperate with the user to call, modify and save the report; The preset template module is used to cooperate with the interactive module to call the report template, and the report template includes a preset text and a text column to be written; The speech recognition module is preset with a number of trigger keywords and ending words, each trigger keyword corresponds to a part of the text column to be written; when the collected speech information contains a trigger keyword, the text after the trigger keyword is converted into computer text information and filled into the text column to be written corresponding to the trigger keyword; and the current text conversion is ended by the ending word after the trigger keyword until the next trigger keyword is received; The speech recognition module has a voiceprint recognition module for recognizing the voiceprint of the current user to filter the patient's voice; The speech recognition module also records the entire speech, and records the speech in a database after classifying it according to the voiceprint. When the user interacts with the interactive module, he interacts with the corresponding text column to be written, and displays the entire speech segment content corresponding to the text in the text column to be written, and the content at least includes the text within at least five seconds before and after the corresponding text column to be written, and the selected text is filled or covered in the text column to be written by selecting it from the displayed content.

2. The ultrasonic examination report entry system according to claim 1, characterized in that: The speech recognition module includes a closing remark entry module, which uses speech to input user routine conversation segments and analyze and summarize closing remark through user interaction, and the user enters closing remark by correction and supplementation; the closing remark at least includes a customary closing word and a pause duration.

3. The ultrasonic examination report entry system according to claim 2, characterized in that: The interaction module interacts with the text field to be written by means of a mouse or a touch screen, and displays a text box near the text field to be written. The corresponding full voice segment content is displayed in the text box and is used to assist the user in selecting.

4. The ultrasonic examination report entry system according to claim 3, characterized in that: The content in the text box corresponding to the text field to be written is marked with a color change.

5. A method for entering an ultrasonic examination report, characterized in that: The method comprises the following steps: Call the preset template; Ultrasound captures images and makes diagnoses based on them; Enter diagnostic information via voice; The speech recognition diagnostic information is converted into computer text information and entered into the database; Fill the corresponding text into the corresponding text column in the preset template by triggering the keyword; By interacting with the text field to be written, determine whether modification is required; If modification is required, the text within five seconds before and after the text column to be written will be displayed in a text box through the interactive text column to be written, and the user can select and fill in the text column to be written or cover the text column to be written, and save the report; If no modification is required, save the report through the interactive module.

Images