Method for generating consultation feedback information

Abstract

This specification provides a method for generating consultation feedback information. The method may include: obtaining the doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data; displaying a record display page including the doctor's text data; wherein the record display page has a voice playback control corresponding to the doctor's text data; wherein, when the voice playback control is triggered, the doctor's voice data corresponding to the doctor's text data is played; and generating target consultation feedback information according to the doctor's text data selected by the doctor on the record display page. The method can bring convenience to doctors.

Description

Technical Field

[0001] This specification relates to the field of Internet medical care, and in particular to a method for generating consultation feedback information. Background Art

[0002] With the rapid development of e-commerce, people have become accustomed to the convenience that the Internet brings to their lives.

[0003] In real life, when people are sick, they can choose to go to the hospital for treatment. Or, based on their own experience, they can go to the pharmacy to buy some medicine. As people get used to the online services provided by e-commerce, some websites have also begun to provide online medical consultation services. Summary of the invention

[0004] The implementation manner of this specification provides a method for generating medical consultation feedback information, which can bring convenience to patients in medical consultation.

[0005] An embodiment of the present specification provides a method for generating consultation feedback information, including: obtaining doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data; displaying a record display page including the doctor's text data; wherein the record display page has a voice playback control corresponding to the doctor's text data; wherein, when the voice playback control is triggered, the doctor's voice data corresponding to the doctor's text data is played; and generating target consultation feedback information according to the doctor's text data selected by the doctor on the record display page.

[0006] The embodiment of the present specification provides a method for generating consultation feedback information, including: obtaining doctor audio data generated during the communication between a doctor client and a user client; performing voice recognition on the doctor audio data to obtain doctor text data; sending the doctor audio data and the doctor text data to the doctor client, so that the doctor client displays a record display page including the doctor text data; wherein, when the voice playback control corresponding to the doctor text data of the record display page is triggered, the doctor audio data corresponding to the doctor text data is played; receiving target consultation feedback information sent by the doctor client, and sending the target consultation feedback information to the user client; wherein, the target consultation feedback information is generated based on the doctor text data.

[0007] In the implementation mode of this specification, the doctor can communicate with the user's user client through voice or video through the doctor client. In this way, the doctor can quickly and accurately understand the patient's actual situation, make a more comprehensive and accurate diagnosis, and can answer the user's questions more clearly. In this solution, voice recognition can be performed on the doctor's voice data during the communication between the doctor and the user to obtain the corresponding doctor's text data. Furthermore, after the doctor and the user end the call, the doctor's text data is displayed on the doctor's client, so that the doctor can easily operate the doctor's client to generate target consultation feedback information. Yes, the doctor's work efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The included drawings are used to provide a further understanding of the embodiments of the present specification, which constitute a part of the specification, are used to illustrate the embodiments of the present specification, and together with the text description, explain the principles of the present specification. Obviously, the drawings described below are only some embodiments of the present specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0009] Figure 1 A schematic diagram of a scenario application of the data interaction system provided in the implementation mode of this specification;

[0010] Figure 2 A schematic diagram of the doctor client display interface provided in the implementation mode of this specification;

[0011] Figure 3 A schematic diagram of the doctor client display interface provided in the implementation mode of this specification;

[0012] Figure 4 A schematic diagram of the doctor client display interface provided in the implementation mode of this specification;

[0013] Figure 5 A flowchart of a method for generating medical inquiry information provided in an embodiment of this specification;

[0014] Figure 6 A flowchart of a method for generating medical inquiry information provided in an embodiment of this specification;

[0015] Figure 7 A functional module diagram of a client provided for the implementation of this specification;

[0016] Figure 8 A functional module diagram of a server provided for an implementation manner of this specification. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the implementation modes of this specification will be clearly and completely described below in conjunction with the drawings in the implementation modes of this specification. Obviously, the described implementation modes are only part of the implementation modes of this specification, not all of the implementation modes. Based on the implementation modes in this specification, all other implementation modes obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0018] The implementation method of this specification provides a data interaction system. The data interaction system includes a user client, a server, and a doctor client.

[0019] In this embodiment, the user client and the doctor client may be electronic devices with display and network access functions. The electronic device may be provided with a processing chip with certain computing capabilities. Specifically, for example, it may be a tablet computer, a smart phone, a computer terminal, etc., or it may be software that can run in the above electronic devices. The client may provide a network interface for data interaction. The client may follow the network communication protocol to interact with data information.

[0020] In this embodiment, the server may be a hardware device with data information processing function and software required to drive the hardware device to work. Of course, the server may also be only a hardware device with data processing capability, or only software running in the hardware device. The server may perform network data interaction with the user client and the doctor client based on network protocols such as HTTP, TCP / IP or FTP and a network communication module.

[0021] See also Figure 1 In one example scenario, a user feels unwell and wants to consult a doctor for diagnosis. The user can start a user client application installed in the mobile phone and communicate with the doctor through the user client.

[0022] Specifically, the user can use the user client to communicate with the doctor client used by the doctor through voice. In this way, the user and the doctor can exchange information efficiently, which can improve the doctor's work efficiency. Specifically, the following conversation may occur between the user and the doctor.

[0023] The user said: "I have been feeling dizzy lately, sometimes 2 to 3 times in a row. My blood pressure is normal when I measure it regularly."

[0024] The doctor asked: "Have you taken any medicine recently?"

[0025] The user said: "I took amoxicillin and cephalexin for two or three days."

[0026] The doctor said: "Based on your current description and symptoms, the preliminary diagnosis is that it may be atherosclerosis or painless myocardial ischemia. It is recommended that you go to the hospital for a comprehensive screening."

[0027] The doctor said: "I suggest you continue to observe for a few more days."

[0028] The user said: "Is there anything I need to pay attention to in my diet?"

[0029] The doctor said: "Avoid eating raw, cold, spicy, high-purine, high-fat foods, and foods that are prone to hair loss."

[0030] …….

[0031] During the above-mentioned conversation between the doctor and the user, the doctor client will record and generate the doctor's voice data, and send the doctor's voice data to the server, and the server will send the doctor's voice data to the user client, and the server will receive the user voice data recorded and sent by the user client, and send the user voice data to the doctor client. In this way, the voice conversation between the doctor and the user is realized.

[0032] After receiving the doctor's voice data and the user's voice data, the server may perform voice recognition on the doctor's voice data and the user's voice data respectively, generate doctor's text data corresponding to the doctor's voice data, and generate user text data corresponding to the user's voice data.

[0033] See also Figure 2 . After the conversation between the doctor and the user is completed, the server can generate primary consultation feedback information based on the obtained doctor text data. The primary consultation feedback information may include multiple information units, and the information content expressed by different information units is different. Further, different information units involve different doctor text data. Specifically, the primary consultation feedback information may include diagnosis results, precautions, dietary precautions, and medication recommendations. The diagnosis result can be to identify the doctor's text data, obtain possible disease words in the doctor's text data, and match the disease word in the preset disease word data set to obtain the target disease word, and the target disease word can be included in the diagnosis result. Of course, the disease word in the doctor's text data may be the same or similar to the target disease word, but express the same semantics as a whole. Specifically, for example, disease words such as "atherosclerosis" appear in the doctor's text data. These disease words are the same as the matched target disease words and are included in the diagnosis results. Precautions may include: it is not recommended to do strenuous exercise, walk slowly for 5 to 15 minutes every day, insist on soaking your feet every day, and go to the hospital for a review after half a month. Dietary precautions may include: avoid raw, cold, spicy, high-purine, high-fat foods, eat less food prone to inflammation, and eat more high-protein foods. Medication recommendations may include: amoxicillin and liver protection capsules.

[0034] The server sends the generated primary consultation feedback information to the doctor client. After consulting the primary consultation feedback information displayed in the doctor client, the doctor may think that the content in a certain information unit is not appropriate and needs to modify the corresponding content. In the page of primary consultation feedback information of the doctor client, an editing control can be set for each information unit. When the editing control is triggered, the doctor client sends an editing instruction to the server. Specifically, for example, the doctor clicks the control "Select from Dialogue" of the diagnosis result.

[0035] The server may send the doctor text data and the user text data to the doctor client, so that the doctor client displays a record display page including the doctor text data and the user text data. Specifically, for example Figure 3 As shown. In the record display page, the corresponding doctor text data and user text data can be displayed in chronological order of the communication dialogue between the two parties, and voice playback controls are provided for the doctor text data and user text data respectively. When the voice playback control is triggered, the doctor client can play the doctor voice data corresponding to the corresponding doctor text data, or the user voice data corresponding to the corresponding user text data. In this way, it is convenient for the doctor to review the content of the conversation with the user and to select more appropriate doctor text data as the content of the corresponding information unit. The doctor selects the doctor text data on the record display page. The doctor text data includes two disease words such as "atherosclerosis" and "painless myocardial ischemia". The doctor client re-displays the primary consultation feedback information. The content of the primary consultation feedback information can be the content updated according to the doctor's operation. Specifically, for example Figure 4 The doctor may consider that the content of the primary consultation feedback information meets the requirements, and may trigger the send button provided on the page to send the primary consultation feedback information as the target consultation feedback information to the corresponding user client, so that the user can operate the user client to browse.

[0036] See also Figure 5 The embodiment of this specification also provides a method for generating consultation feedback information. The method for generating consultation feedback information can be applied to a client. Specifically, for example, the method for generating consultation feedback information can be applied to a doctor client. The method can include the following steps.

[0037] Step S12: Acquire the doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data.

[0038] In this embodiment, the doctor client can obtain the doctor's voice data and the doctor's text data. Specifically, the doctor client can obtain the doctor's voice data in a way that the doctor client generates the doctor's voice data according to the doctor's language. The doctor client can obtain the doctor's text data in a way that includes: the doctor client performs voice recognition on the generated doctor's voice data to obtain the doctor's text data corresponding to the doctor's voice data. Specifically, the doctor client can perform content boundary detection on the doctor's voice data stream, so that the doctor's voice data after the doctor's voice data stream is segmented can be obtained, and in this way, the doctor's voice data can be conveniently voice recognized to obtain the doctor's text data. Of course, the doctor client can also obtain the doctor's voice data and the doctor's text data in a way that the doctor client sends the voice data stream during the conversation between the doctor and the user to the server, and the server feeds back the doctor's voice data and the doctor's text data to the doctor client after processing.

[0039] In this embodiment, the doctor's voice data may be the recording data of the doctor's speech during the conversation between the doctor and the user. The doctor's voice data may be all the recording data of the doctor's speech, or a part of it. In some embodiments, the doctor's voice data may be a partial segment of the doctor's recording data, and this partial segment may include a sentence or a paragraph said by the doctor. In some embodiments, the doctor's voice data may be a data segment containing the doctor's speech content obtained after content detection is performed on the doctor's recording data. The number of doctor's voice data may be multiple. Each doctor's voice data may correspond to corresponding doctor's text data. The doctor's text data may be obtained by performing voice recognition on the doctor's voice data.

[0040] In this embodiment, the doctor client can obtain the doctor's voice data and the corresponding doctor's text data after receiving the doctor's operation instruction. In some embodiments, the doctor client can monitor that the doctor has completed the conversation with the current user, that is, the doctor has completed the diagnosis communication for the user. The doctor client automatically obtains the doctor's voice data and the doctor's text data.

[0041] Step S14: Display a record display page including the doctor's text data; wherein the record display page has a voice playback control corresponding to the doctor's text data; wherein, when the voice playback control is triggered, the doctor's voice data corresponding to the doctor's text data is played.

[0042] In this embodiment, the doctor client can display the record display page so that the doctor can browse the doctor text data through the doctor client. The doctor can browse the doctor text data conveniently, which brings convenience to the doctor in making consultation feedback information and improves the doctor's work efficiency.

[0043] In this embodiment, there is a voice playback control corresponding to the doctor's text data on the record display page. In some embodiments, there may be multiple doctor text data in the record display page, and a voice playback control may be provided for each doctor text data. In this way, when a certain voice playback control is triggered, the doctor client can play the doctor's voice data corresponding to the corresponding doctor text data. Of course, it is also possible to only provide a voice playback control on the record display page, and after the voice playback control is triggered, the doctor client can play the doctor's voice data corresponding to the doctor's text data currently displayed on the record display page.

[0044] In this embodiment, the doctor client can instruct the doctor client to play the doctor's voice data corresponding to the doctor's text data as needed during the process of consulting the doctor's text data. In this way, it is convenient for the doctor to review the communication content with the user more clearly. In some embodiments, the doctor's text data may not be particularly accurate, that is, when performing voice recognition on the doctor's voice data, the content expressed by the doctor is not completely and accurately recognized. At this time, after consulting the doctor's text data, the doctor can listen to the content expressed at that time again, which is convenient for the doctor to remember and edit the doctor's text data. In some embodiments, some "slips of the tongue" may occur during the communication between the doctor and the user, so that there are also "slips of the tongue" content in the generated doctor's text data. In this way, the doctor may feel that some content is inaccurate during the review of the doctor's text data, and can click the voice playback control to make the doctor client play the doctor's voice data of the corresponding doctor's text data. In this way, it is found that the doctor's text data is wrong because of the "slip of the tongue", so it can be edited.

[0045] Step S16: Generate target consultation feedback information according to the doctor text data selected by the doctor on the record display page.

[0046] In this embodiment, the record display page displayed by the doctor client can be used for the doctor to select doctor text data for generating target consultation feedback information. Specifically, the doctor client can generate target consultation feedback information according to the order in which the doctor selects the doctor text data on the record display page. For example, the doctor can be given corresponding prompts in a certain order on the doctor client to prompt the doctor's selection requirements each time the doctor selects the doctor text data. For example, the doctor client prompts "Please select dietary advice", at which time the doctor can select the doctor text data that expresses the corresponding dietary advice in the record display page. Then, the doctor client prompts "Please select medication advice", at which time the doctor can select the doctor text data that expresses medication advice in the record display page. In this way, the target consultation feedback information can be generated according to the order in which the doctor selects the doctor text data.

[0047] In some implementations, the doctor client may have generated primary consultation feedback information, and the doctor believes that the primary consultation feedback information needs to be modified. When the doctor client receives an editing instruction for the primary consultation feedback information, the record display page is displayed, and the doctor text data selected by the doctor is received to modify the corresponding content in the primary consultation feedback information. In this way, the target consultation feedback information can be generated.

[0048] The method for generating consultation feedback information provided in the implementation mode of this specification obtains the doctor's voice data and doctor's text data during the conversation between the doctor and the user, and can provide them to the doctor's record display page, so that the doctor can conveniently view the doctor's text data and the corresponding doctor's voice data, which is convenient for the doctor to review the communication process and conveniently select the doctor's text data for generating the target consultation feedback information. It improves the efficiency of the doctor in processing the consultation feedback information after communicating with the user, and brings great convenience to the doctor's work.

[0049] In one embodiment, before displaying the record display page including the doctor's text data, it is also possible to: obtain primary consultation feedback information generated based on the doctor's text data; accordingly, when an editing instruction for the primary consultation feedback information is received, display the record display page including the doctor's text data.

[0050] In this embodiment, the doctor client may first obtain primary consultation feedback information. In some embodiments, the doctor client may automatically generate primary consultation feedback information based on the obtained doctor text data. Specifically, for example, the doctor client may be pre-set with a consultation information template, so that data information can be extracted from the obtained doctor text data according to the consultation information template to generate primary consultation feedback information. In some embodiments, the primary consultation feedback information may be generated by a server, and the doctor client may receive the primary consultation feedback information from the server.

[0051] In this embodiment, the doctor client can display the obtained primary consultation feedback information for the doctor to browse. In some embodiments, after browsing the primary consultation feedback information, the doctor may think that part of the content in the primary consultation feedback information is not accurate enough and needs to be modified. The doctor can operate the doctor client to issue an editing instruction, and the doctor client will respond to the editing instruction and display the record display page. The page of primary consultation feedback information displayed by the doctor client can be provided with an edit button. When the edit button is triggered, it is considered that the edit instruction has been received and the record display page is displayed.

[0052] In this embodiment, the doctor client can automatically generate primary consultation feedback information based on the doctor's text data. In this way, the doctor's time for operating the doctor client can be saved. If the doctor considers that the content of the primary consultation feedback information meets the requirements after consulting the primary consultation feedback information, the primary consultation feedback information can be sent to the user client as the target consultation feedback information. Furthermore, if the doctor considers that the content of the primary consultation feedback information needs to be modified after consulting the primary consultation feedback information, an editing instruction can be issued, and the doctor client can display a record display page to provide the doctor with the selection of the doctor's text data. In this way, the primary consultation feedback information can be modified to obtain the target consultation feedback information. Overall, this embodiment brings convenience to doctors and saves doctors' time in making target consultation feedback information.

[0053] In one embodiment, the primary consultation feedback information may include multiple information units. Accordingly, the editing instruction corresponds to an information unit, and the doctor text data associated with the information unit is displayed on the record display page.

[0054] In this embodiment, the primary consultation feedback information may include multiple information units, and each information unit may be configured to display specified content. Specifically, the information units may include: diagnosis results, precautions, dietary precautions, and medication recommendations. Among them, the content of the diagnosis results may include expressing the diseases that the patient may suffer from. The content of the precautions may include the doctor reminding the patient to pay attention to daily living behaviors in life. The content of the dietary precautions may include the doctor's suggestions on the patient's diet. The content of the medication recommendation may include the medicines that the doctor recommends the patient to take, and may also include medical instructions such as usage and dosage.

[0055] In this embodiment, each information unit of the primary consultation feedback information may correspond to an edit button, so that when the doctor wants to edit the content of a certain information unit, he can click the corresponding edit button of the information unit. At this time, the doctor client receives the edit instruction corresponding to the information unit and can display the record display page.

[0056] In this embodiment, each information unit in the primary consultation feedback information can be generated according to the doctor's text data. That is, the doctor's text data included in different information units is different. When an editing instruction for an information unit is received, the context of the doctor's text data included in the corresponding information unit can be displayed on the record display page. In this way, it is convenient for the doctor to review the conversation content with the user and to select the correct doctor's text data as the content of the information unit.

[0057] In this embodiment, the doctor's text data associated with the information unit may be that the content in the information unit is at least partially derived from the doctor's text data. Specifically, for example, the information unit includes all the content of the doctor's text data; or, the content of the information unit is generated according to the meaning expressed by the doctor's text data; or, the content of the information unit includes part of the text in the doctor's text data. Of course, technicians in the relevant field can also make other changes, which will not be repeated here.

[0058] In one embodiment, the primary consultation feedback information may include multiple information units; the information units may correspond to keywords; in the record display page, the keywords of the doctor's text data may be displayed separately from non-keyword texts.

[0059] In this embodiment, keywords may be set for corresponding information units. Each information unit may correspond to multiple keywords. Keywords corresponding to different information units are at least partially different. As a result, different information units ultimately contain different contents. In some embodiments, keywords corresponding to different information units are different. Specifically, for example, multiple keywords corresponding to the information unit "diagnosis result" may be disease names. Multiple keywords corresponding to the information unit "medication advice" may be drug names.

[0060] In this embodiment, in order to facilitate the doctor to trigger the edit instruction for the information unit, the doctor's text data associated with the current information unit in the record display page can be easily viewed. The display method of the keywords corresponding to the information unit can be distinguished from the display method of non-keywords. Specifically, for example, the display method of distinguishing keywords from non-keywords can include at least one of the following: different background colors, different fonts, different text colors or different font sizes. Of course, technical personnel in the field can make other changes based on the enlightenment of this embodiment, which will not be repeated here.

[0061] In some embodiments, different information units are associated with different doctor text data. Different doctor text data express different meanings. As a result, the text content contained in different doctor text data is also different. Since different information units have different content requirements, different information units are associated with different doctor text data. In this way, it is convenient for doctors to select doctor text data as the content source of an information unit on the record display page. Furthermore, different information units express different contents, which can avoid repeated feedback of the same content from different information units.

[0062] In one embodiment, the method for generating medical consultation feedback information may further include: obtaining user voice data and corresponding user text data during the communication between the doctor and the user; wherein the user text data is obtained by voice recognition of the corresponding user voice data; accordingly, in the step of displaying a record display page including the doctor's text data, a record display page including the doctor's text data and the user text data is displayed; wherein the record display page has a voice playback control corresponding to the user text data; wherein, when the voice playback control is triggered, the user voice data of the corresponding user text data is played.

[0063] In this embodiment, the consultation and communication process between the doctor and the user is usually a dialogue between the doctor and the user. Therefore, the dialogue between the doctor and the user is usually a continuous process. Therefore, the doctor's text data and the user's text data as a whole form the context of the communication process between the doctor and the user. In this embodiment, the doctor's client further obtains the user's voice data and the user's text data. In this way, the doctor's text data and the user's text data can be displayed simultaneously on the record display page, which greatly facilitates the doctor to review the communication process.

[0064] In this embodiment, during the communication between the user and the doctor, the user client can generate user voice data according to the user's speaking voice. In some embodiments, the user client can generate a user voice data stream for the user's speaking voice, and the user client can send the user voice data stream to the server so that the server can process the user voice data stream, such as content detection, etc., segment the user voice data stream to generate user voice data, and perform voice recognition to generate user text data. Then the server can send the user voice data and the corresponding user text data to the doctor client. Of course, it can also be that the user client processes the recorded user voice data stream to obtain user voice data and corresponding user text data, sends the user voice data and user text data to the server, and the server can send the user voice data and user text data to the doctor client. Of course, in some embodiments, the user client can send the user voice data stream to the server, and the server sends the user voice data stream to the doctor client. In this way, the doctor client can process the user voice data stream to obtain user voice data and user text data.

[0065] In this embodiment, the record display page can display the doctor's text data and the user's text data in chronological order. Therefore, the dialogue process between the doctor and the user can be restored through the doctor's text data and the user's text data. This facilitates the doctor to accurately generate the target consultation feedback information. In this embodiment, the record display page is provided with a voice playback control corresponding to the user text data. When the voice playback control corresponding to the user text data is triggered, the doctor client can play the corresponding user voice data.

[0066] In one embodiment, the medical consultation feedback information generating method further includes: sending the target medical consultation feedback information to the user client of the user, so that the user client displays the target medical consultation feedback information in the medical consultation feedback information page; wherein, the medical consultation feedback information page has a voice playback control, and when the voice playback control is triggered, the doctor's voice data of the doctor's text data in the target medical consultation feedback information is played.

[0067] In this embodiment, the doctor client can send the target consultation feedback information to the user client. In this way, the user can operate the user client to check the target consultation feedback information. In this way, after the user and the doctor complete the communication, the user can also review the doctor's instructions during the communication process with the doctor based on the target consultation feedback information. This brings convenience to the user and prevents the user from forgetting the content of the communication with the doctor and delaying the treatment of the disease.

[0068] In this embodiment, when the user client displays the target consultation feedback information, a voice playback control can be displayed in the consultation feedback information page. The user can click the voice playback control as needed to play the doctor's voice data. In some embodiments, the doctor's voice data can be a recording of the doctor's speech during the call between the user and the doctor. In this way, the user can click the voice playback control and hear the doctor's voice corresponding to the content of the target consultation feedback information. It is convenient for the user to review the entire communication process and understand the content of the target consultation feedback information by comparing the tone and voice of the doctor's speech. In some embodiments, the voice playback control can be associated with the text content in the target consultation feedback information. When the corresponding text content is clicked, the corresponding doctor audio data is played. Of course, the voice playback control can also be a separate picture placed next to the corresponding text content.

[0069] In this embodiment, when the target medical consultation feedback information is sent to the user client, the doctor's voice data of the doctor's text data in the target medical consultation feedback information can be sent to the user client together. When the user clicks the voice playback control, the corresponding recording can be played with less delay. Of course, in some embodiments, when the target medical consultation feedback information is sent to the user client, the doctor's text data in the target text feedback information is mainly sent to the user client. When the user clicks the voice playback control corresponding to the doctor's text data, the user client can send a doctor's voice data acquisition request to the server, so that the server feeds back the corresponding doctor's voice data. In this way, the doctor's voice data can be obtained according to the user's needs, reducing the network load.

[0070] In one embodiment, the method for generating medical consultation feedback information may further include: matching the doctor's text data in a preset disease word data set to obtain a target disease word; the target disease word is used as a part of the target medical consultation feedback information; wherein the preset disease word data set includes multiple standard disease words.

[0071] In this embodiment, a preset disease word data set may be pre-set in the doctor client, and the preset disease word data set may include multiple standard disease words. The matched target disease word may be used as the disease that the patient may suffer from. In this way, the target disease word is provided to the user as part of the target consultation feedback information, so that the user can understand his or her own disease condition.

[0072] In this embodiment, the doctor client may be pre-set with a matching model. After the doctor's text data is input into the matching model, the matching model will further provide the corresponding target disease word. In some embodiments, the doctor's text data may also be segmented, and the segmented words may be input into the matching model to obtain the target disease word. In some embodiments, the doctor's client may not need to set a model, but obtain a text vector by converting the user's text data. A disease word vector has been set for each standard disease word, and the standard disease word corresponding to the disease word vector closest to the text vector is used as the target disease word. Of course, technical personnel in the relevant field may make other changes inspired by the technical essence of this embodiment, but they should all be covered within the scope of protection of this case.

[0073] See also Figure 6 The embodiment of this specification also provides a method for generating consultation feedback information. The method for generating consultation feedback information can be used in a server. The method for generating consultation feedback information can include the following steps.

[0074] Step S30: Acquire the doctor audio data generated during the communication between the doctor client and the user client.

[0075] In this embodiment, the server can receive the doctor's voice data sent by the doctor's client and the user's voice data sent by the user's client during the conversation between the doctor and the user. Specifically, for example, the server can receive the doctor's voice data stream sent by the doctor's client, and further process it to obtain the doctor's voice data corresponding to each section of voice content. Alternatively, in some embodiments, after the doctor's client records the doctor's voice into audio data, it generates the doctor's audio data and sends the doctor's audio data to the server.

[0076] Step S32: Perform speech recognition on the doctor's audio data to obtain doctor's text data.

[0077] In this embodiment, the server can perform speech recognition on the doctor's audio data based on speech recognition technology to obtain the doctor's text data. Specifically, for example, the server can pre-build a speech recognition model. The doctor's audio data is input into the speech recognition model to obtain the corresponding doctor's audio data. In some embodiments, the speech recognition model can process the doctor's audio data stream to obtain the doctor's audio data. Of course, the construction of the specific speech recognition model can be constructed by technicians in the relevant field based on the speech recognition algorithm.

[0078] Step S34: Send the doctor audio data and the doctor text data to the doctor client, so that the doctor client displays a record display page including the doctor text data; wherein, when the voice playback control corresponding to the doctor text data on the record display page is triggered, the doctor audio data corresponding to the doctor text data is played.

[0079] Step S36: receiving the target consultation feedback information sent by the doctor client, and sending the target consultation feedback information to the user client; wherein the target consultation feedback information is generated based on the doctor text data.

[0080] In this embodiment, the server can establish communication between the doctor client and the user client. During the communication between the doctor client and the user client, the server can perform speech recognition on the received doctor audio data to obtain the doctor text data corresponding to the doctor audio data. In this way, the server can send the doctor text data to the doctor client so that the doctor can easily generate the target consultation feedback information based on the doctor text data displayed by the doctor client. In this way, after receiving the target consultation feedback information, the server can send the target consultation feedback information to the user client.

[0081] In this embodiment, the doctor's text data can be displayed in chronological order in the record display page of the doctor's client. Corresponding to the doctor's text data, a voice playback control can be displayed accordingly. In this way, when the voice playback control is triggered, the doctor's client can play the corresponding doctor's audio data. In this way, it helps the doctor to review the communication content with the user. Furthermore, by selecting the doctor's text data to generate the target consultation feedback data, it brings convenience to the doctor.

[0082] In one embodiment, the server may generate primary consultation feedback information based on the doctor text data; and send the primary consultation feedback information to the doctor client, so that the doctor client displays the primary consultation feedback information.

[0083] In this embodiment, the server can generate primary consultation feedback information. In some embodiments, the server can automatically generate primary consultation feedback information based on the doctor's text data. Specifically, for example, the server can be pre-set with a consultation information template, so that data information can be extracted from the doctor's text data according to the consultation information template to generate primary consultation feedback information.

[0084] In this embodiment, the server can send the generated primary consultation feedback information to the doctor client. In this way, the doctor client can display the primary consultation feedback information, and the doctor only needs to edit the primary consultation feedback information to obtain the target consultation feedback information, which brings convenience to the doctor.

[0085] In one embodiment, upon receiving an editing instruction for the primary consultation feedback information sent by the doctor client, the doctor audio data and the doctor text data are sent to the doctor client.

[0086] In this embodiment, after the server generates the primary consultation feedback information, it sends the content of the primary consultation feedback information to the doctor client for display by the doctor client. The doctor reviews the primary consultation feedback information displayed by the doctor client. In some cases, the primary consultation feedback information may be relatively complete, and the doctor believes that no further editing is required. At this time, the doctor can operate the doctor client to send the primary consultation feedback information to the user client. In this way, the server can only send the content of the primary consultation feedback information to the doctor client. In this way, in the scenario of big data, the workload of the server itself can be reduced, and the load on the network can also be reduced. In some cases, after the doctor reviews the primary consultation information through the doctor client, he may believe that the content of some information units in the primary consultation information needs to be edited and modified. At this time, the doctor can operate the doctor client to issue an editing instruction to request modification of the content of the corresponding information unit.

[0087] In this embodiment, the primary consultation feedback information displayed by the doctor client may have multiple information units, and each information unit may be provided with an edit button. When the edit button is triggered, it can be considered that the doctor's edit instruction for the corresponding information unit is received. The doctor client can send the edit instruction to the server. After the server receives the edit instruction, it can send the doctor's text data and the doctor's audio data to the doctor client. In this way, the doctor client can display the record display page for the doctor to operate, select appropriate content, and generate the target consultation feedback information.

[0088] In one embodiment, the primary consultation feedback information may include multiple information units, and the content of each information unit is generated according to the doctor's text data; wherein different information units are associated with different doctor's text data.

[0089] In this embodiment, the primary consultation feedback information generated by the server may have multiple information units. Specifically, for example, the information unit may include diagnosis results, precautions, dietary precautions, and medication recommendations. In some embodiments, the server may set a keyword set for each information unit, and obtain the doctor's text data corresponding to each information unit by matching the doctor's text data with the keywords in the keyword set of each information unit. Specifically, for example, the keywords of the information unit include "vegetables, eggs, meat, protein", etc. A doctor's text data may be "you can eat more crude fiber vegetables." In this way, the match finds that the doctor's text data has the keyword "vegetables", and the doctor's text data can be used as the content of the information unit.

[0090] In some embodiments, an information unit may correspond to a relatively fixed keyword. For example, the name of an information unit may be used as the keyword of the corresponding information unit, and the doctor's text data including the name of the corresponding information unit may be used as the content of the corresponding information unit. Specifically, for example, precautions are used as the name of an information unit, and "precautions" itself may also be used as a keyword. For example, a doctor's text data may be "There are two precautions at present. The first is to increase physical exercise and run more. The second is to have a regular work and rest schedule and not stay up late..." The doctor's text data includes "Precautions", and the content of the doctor's text data may be used as the content of the precautions information unit.

[0091] In one embodiment, the method for generating medical consultation feedback information may further include: obtaining user voice data generated during the communication between the doctor client and the user client; performing voice recognition on the user voice data to obtain user text data; accordingly, in the step of sending the doctor audio data and the doctor text data to the doctor client, the doctor audio data and the doctor text data, as well as the user voice data and the user text data are sent to the doctor client; so that the doctor client displays the record display page including the doctor text data and the user text data; wherein the record display page also has a voice playback control corresponding to the user text data; wherein, when the voice playback control is triggered, the user voice data of the corresponding user text data is played.

[0092] In this embodiment, the server can receive user voice data sent by the user client, and can send the user voice data to the doctor client. The server can perform voice recognition on the received user voice data to obtain user text data corresponding to the user voice data. Further, the server can send the user text data to the doctor client, so that the doctor operates the doctor client to display the record display page, and can display the user text data in the record display page. In some embodiments, the doctor's text data and the user text data can be displayed on different pages. Of course, the doctor's text data and the user text data can also be displayed on one page. In some embodiments, in the record display page, the doctor's text data and the user text data can be displayed in a chronological order and in a conversational manner, so that it is convenient for the doctor to consult.

[0093] In this embodiment, a voice playback control may be provided for each user text data. When the voice playback control corresponding to the user text data is triggered, the user voice data corresponding to the corresponding user text data may be played. In some embodiments, the user voice data may be a recording of the user speaking. This facilitates the doctor to review the communication content with the user.

[0094] In one embodiment, the method for generating consultation feedback information may further include: matching the doctor text data in a preset disease word data set to obtain a target disease word; the target disease word is used as a part of the target consultation feedback information; wherein the preset disease word data set includes multiple standard disease words.

[0095] In this embodiment, a preset disease word data set may be pre-set in the server, and the preset disease word data set may include multiple standard disease words. The matched target disease word may be used as the disease that the patient may suffer from. In this way, the target disease word is provided to the user as part of the target consultation feedback information, so that the user can understand his or her own disease condition.

[0096] In this embodiment, the doctor client may be pre-set with a matching model. After the doctor's text data is input into the matching model, the matching model will further provide the corresponding target disease word. In some embodiments, the doctor's text data may also be segmented, and the segmented words may be input into the matching model to obtain the target disease word. In some embodiments, the doctor's client may not need to set a model, but obtain a text vector by converting the user's text data. A disease word vector has been set for each standard disease word, and the standard disease word corresponding to the disease word vector closest to the text vector is used as the target disease word. Of course, technical personnel in the relevant field may make other changes inspired by the technical essence of this embodiment, but they should all be covered within the scope of protection of this case.

[0097] See also Figure 7 The embodiment of this specification also provides a client. The client can be applied to a terminal device. The client can be a doctor client. The client can include: a text data acquisition module, a record display module and an information generation module.

[0098] The text data acquisition module can be used to acquire the doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data.

[0099] The record display module can be used to display a record display page including the doctor's text data; wherein, the record display page has a voice playback control corresponding to the doctor's text data; wherein, when the voice playback control is triggered, the doctor's voice data corresponding to the doctor's text data is played.

[0100] The information generation module can be used to generate target consultation feedback information according to the doctor text data selected by the doctor on the record display page.

[0101] The functions and effects achieved by the client provided in this embodiment can be explained in comparison with other embodiments and will not be repeated here.

[0102] The present specification also provides a computer storage medium. The computer storage medium may store computer program instructions, which, when executed by a processor, may achieve: obtaining the doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data; displaying a record display page including the doctor's text data; wherein the record display page has a voice playback control corresponding to the doctor's text data; wherein, when the voice playback control is triggered, the doctor's voice data corresponding to the doctor's text data is played; and generating target consultation feedback information according to the doctor's text data selected by the doctor on the record display page.

[0103] In this embodiment, the computer storage medium includes but is not limited to random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), cache (Cache), hard disk (Hard Disk Drive, HDD) or memory card (Memory Card).

[0104] In this embodiment, the specific functions implemented by the computer storage medium can be explained with reference to other embodiments.

[0105] See also Figure 8 The embodiment of this specification provides a server. The server may include: an audio acquisition module, a text recognition module, a text data sending module and a medical consultation information sending module.

[0106] The audio acquisition module can be used to acquire doctor audio data generated during the communication between the doctor client and the user client.

[0107] The text recognition module can be used to perform speech recognition on the doctor's audio data to obtain doctor's text data.

[0108] The text data sending module can be used to send the doctor audio data and the doctor text data to the doctor client, so that the doctor client displays a record display page including the doctor text data; wherein, when the voice playback control corresponding to the doctor text data on the record display page is triggered, the doctor audio data corresponding to the doctor text data is played.

[0109] The medical consultation information sending module can be used to receive the target medical consultation feedback information sent by the doctor client, and send the target medical consultation feedback information to the user client; wherein the target medical consultation feedback information is generated based on the doctor text data.

[0110] The specific functions implemented by the audio acquisition module, text recognition module, text data sending module and medical consultation information sending module disclosed in the above embodiments can be explained in comparison with other embodiments in this specification.

[0111] The implementation mode of this specification also provides a computer storage medium. The computer storage medium may store computer program instructions, and when the computer program instructions are executed by the processor, the following may be achieved: obtaining the doctor audio data generated during the communication between the doctor client and the user client; performing voice recognition on the doctor audio data to obtain the doctor text data; sending the doctor audio data and the doctor text data to the doctor client, so that the doctor client displays a record display page including the doctor text data; wherein, when the voice playback control corresponding to the doctor text data of the record display page is triggered, the doctor audio data corresponding to the doctor text data is played; receiving the target consultation feedback information sent by the doctor client, and sending the target consultation feedback information to the user client; wherein, the target consultation feedback information is generated based on the doctor text data.

[0112] In this embodiment, the specific functions implemented by the computer storage medium can be explained with reference to other embodiments.

[0113] The above description of various embodiments of this specification is provided to those skilled in the art for the purpose of description. It is not intended to be exhaustive or to limit the present invention to a single disclosed embodiment. As mentioned above, various substitutions and variations of this specification will be apparent to those skilled in the art of the above-mentioned technology. Therefore, although some alternative embodiments have been specifically discussed, other embodiments will be apparent, or those skilled in the art will be relatively easy to derive. This specification is intended to include all substitutions, modifications, and variations of the present invention discussed herein, as well as other embodiments falling within the spirit and scope of the above-mentioned application.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. It is foreseeable that technicians in the relevant field can make any possible combination between the multiple embodiments of this specification based on the knowledge in the field.

[0115] This specification can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, quantum computing environments, etc.

[0116] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A method for generating consultation feedback information, comprising: Acquire the doctor's voice data and corresponding doctor's text data during the communication between the doctor and the user; wherein the doctor's text data is obtained by voice recognition of the corresponding doctor's voice data; Acquire the primary consultation feedback information generated based on the doctor's text data, send the initial consultation feedback information to the doctor's client, after the doctor consults the primary consultation feedback information displayed in the doctor's client, if the doctor determines the content that needs to be modified, in the page of the primary consultation feedback information of the doctor's client, set an editing control for each information unit, and when the editing control is triggered, the doctor's client sends an editing instruction to the server; In the case of receiving an editing instruction for the primary consultation feedback information, displaying a record display page including the doctor's text data; wherein the record display page has a voice playback control corresponding to the doctor's text data; wherein, in the case of triggering the voice playback control, the doctor's voice data corresponding to the doctor's text data is played; Generate target consultation feedback information according to the doctor text data selected by the doctor on the record display page; The target medical consultation feedback information is sent to the user client of the user, so that the user client displays the target medical consultation feedback information in a medical consultation feedback information page; wherein the medical consultation feedback information page has a voice playback control, and when the voice playback control is triggered, the doctor's voice data of the doctor's text data in the target medical consultation feedback information is played.

2. According to the method of claim 1, the primary consultation feedback information comprises a plurality of information units; Correspondingly, the editing instruction corresponds to an information unit, and the doctor's text data associated with the information unit is displayed on the record display page.

3. According to the method described in claim 1, the primary consultation feedback information includes multiple information units; the information units correspond to keywords; in the record display page, the keywords of the doctor's text data are displayed separately from non-keyword texts.

4. According to the method of claim 1, the primary consultation feedback information includes multiple information units; different information units are associated with different doctor text data.

5. The method according to claim 1, further comprising: Acquire user voice data and corresponding user text data during the communication between the doctor and the user; wherein the user text data is obtained by voice recognition of the corresponding user voice data; Correspondingly, in the step of displaying a record display page including the doctor's text data, a record display page including the doctor's text data and the user text data is displayed; wherein, the record display page has a voice playback control corresponding to the user text data; wherein, when the voice playback control is triggered, the user voice data of the corresponding user text data is played.

6. The method according to claim 1, further comprising: Matching the doctor's text data with a preset disease word data set to obtain a target disease word; The target disease word serves as a part of the target medical consultation feedback information; wherein the preset disease word data set includes a plurality of standard disease words.

7. A method for generating consultation feedback information, comprising: Obtain the doctor audio data generated during the communication between the doctor client and the user client; Performing speech recognition on the doctor's audio data to obtain doctor's text data; Sending the doctor audio data and the doctor text data to the doctor client so that the doctor client displays a record display page including the doctor text data; wherein, when the voice playback control corresponding to the doctor text data on the record display page is triggered, the doctor audio data corresponding to the doctor text data is played; Receive the target consultation feedback information sent by the doctor client, and send the target consultation feedback information to the user client; wherein the target consultation feedback information is generated based on the doctor text data; wherein the consultation feedback information page has a voice playback control, and when the voice playback control is triggered, the doctor voice data of the doctor text data in the target consultation feedback information is played; The method further includes: generating primary consultation feedback information based on the doctor text data; sending the primary consultation feedback information to the doctor client so that the doctor client displays the primary consultation feedback information; and upon receiving an editing instruction for the primary consultation feedback information sent by the doctor client, sending the doctor audio data and the doctor text data to the doctor client.

8. The method according to claim 7, wherein the primary consultation feedback information includes a plurality of information units, and the content of each of the information units is generated according to the doctor's text data; wherein, The doctor text data associated with different information units is different.

9. The method according to claim 7, further comprising: Acquire user voice data generated during the communication between the doctor client and the user client; Performing speech recognition on the user speech data to obtain user text data; Correspondingly, in the step of sending the doctor audio data and the doctor text data to the doctor client, the doctor audio data and the doctor text data, as well as the user voice data and the user text data are sent to the doctor client; so that the doctor client displays the record display page including the doctor text data and the user text data; wherein the record display page also has a voice playback control corresponding to the user text data; wherein, when the voice playback control is triggered, the user voice data of the corresponding user text data is played.

10. The method according to claim 7, further comprising: Matching the doctor's text data with a preset disease word data set to obtain a target disease word; The target disease word serves as a part of the target medical consultation feedback information; wherein the preset disease word data set includes a plurality of standard disease words.

Images