Video consultation processing method and device

Abstract

The present invention discloses a video consultation processing method and device, and relates to the field of Internet medical technology. A specific implementation of the method includes obtaining the current consultation data and historical consultation duration of each doctor's end in response to a video call request not being answered during a preset waiting period; calling a preset waiting time prediction model to calculate the remaining consultation duration of each doctor's end based on the current consultation data and the historical consultation duration; according to the remaining consultation duration of each doctor's end, allocating the doctor's end to be answered for the video call request, and then pushing the corresponding doctor information and the remaining consultation duration to the user end of the video call request, and pushing the call information of the video call request to the doctor end. Therefore, the implementation of the present invention can solve the problem that the existing ultra-fast video consultation has a poor user experience under high concurrency conditions and cannot highlight high-efficiency consultation.

Description

Technical Field

[0001] The present invention relates to the field of Internet medical technology, and in particular to a video consultation processing method and device. Background Art

[0002] At present, high-speed video consultation is an important form of online service in Internet medical services. Users can initiate video calls at any time without waiting, and real-time online doctors will immediately see the patient for communication. Doctors, as the service supply side, can only provide services at a fixed time and place every day. They belong to real-time services, and the supply side quantity requirements are many times higher than the asynchronous delayed text and image consultation requirements. Service providers must balance the supply side quantity and efficiency, otherwise the revenue will not be able to cover the cost.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] Doctors (supply side) and patients (demand side) in ultra-fast video consultations are always in a dynamic state of change, and it is impossible to accurately estimate the demand, which results in the failure to highlight the greatest advantage of ultra-fast video consultations, which is high efficiency. In addition, for unavoidable high concurrency situations, users are forced to wait, affecting the user experience. Secondly, there is a possibility of missing the time window for emergency consultations, causing the user's condition to become serious, and the doctor cannot effectively and timely adjust his rhythm. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a video consultation processing method and device, which can solve the problem that the existing ultra-fast video consultation has a poor user experience under high concurrency conditions and cannot highlight high-efficiency consultation.

[0006] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, a video consultation processing method is provided, including obtaining the current consultation data and historical consultation duration of each doctor end in response to a video call request not being answered during a preset waiting period; calling a preset waiting time prediction model to calculate the remaining consultation time of each doctor end based on the current consultation data and the historical consultation time; according to the remaining consultation time of each doctor end, allocating the doctor end to be answered to the video call request, and then pushing the corresponding doctor information and the remaining consultation time to the user end of the video call request, and pushing the call information of the video call request to the doctor end.

[0007] Optionally, after the video call request is not answered during a preset waiting period, the method further includes: in response to the video call request initiated by the user not being answered by the doctor, storing the video call request in a call queue; and marking the video call request as an unanswered user order when it is monitored that the video call request is not answered by the doctor during the preset waiting period.

[0008] Optionally, after obtaining the current consultation data and historical consultation duration of each doctor, including:

[0009] Generate medical consultation information based on preset target attribute statistics; and convert the real-time voice information in the current medical consultation data into text information through a voice recognition program, so as to process the text information using a natural language processing algorithm to obtain medical condition information; store the mapping relationship between the doctor's medical consultation information and the medical condition information.

[0010] Optionally, a preset waiting time prediction model is called to calculate the remaining consultation time of each doctor based on the current consultation data and the historical consultation time, including:

[0011] A multivariate linear regression model is constructed based on the current consultation data to utilize the historical consultation duration, and the multivariate linear regression model is solved using the gradient descent method to obtain the remaining consultation duration of each doctor.

[0012] Optionally, pushing corresponding doctor information and remaining consultation time to the user terminal of the video call request includes:

[0013] The notification program is triggered to push the corresponding doctor information and the remaining consultation time to the user end of the video call request, and then the user is prompted with the assigned doctor information through language synthesis, and a call back request from the doctor end is received or a call program is initiated after the remaining consultation time.

[0014] Optionally, pushing the call information of the video call request to the doctor side includes: triggering a notification program, pushing the call information of the video call request to the doctor side, and then displaying the call information in the doctor's waiting list, so that the doctor side can initiate a call back procedure based on the call information.

[0015] Optionally, it also includes:

[0016] In response to the doctor side executing a program to adjust the current consultation data, the adjusted consultation data is obtained, and then a preset waiting time prediction model is called to calculate the remaining consultation time adjusted by the doctor side based on the historical consultation time;

[0017] According to the remaining consultation time adjusted by the doctor end, it is determined that the doctor end to be answered assigned to the video call request is inconsistent with the doctor end to be answered currently assigned to the video call request, and the doctor information of the doctor end and the adjusted remaining consultation time are pushed to the user end of the video call request;

[0018] Receive the update allocation instruction sent by the user terminal, update the doctor terminal currently allocated to the video call request to the doctor terminal, so as to push the call information of the video call request to the doctor terminal.

[0019] In addition, the present invention also provides a video consultation processing device, including an acquisition module, which is used to obtain the current consultation data and historical consultation time of each doctor end in response to a video call request not being answered during a preset waiting period; a processing module, which is used to call a preset waiting time prediction model to calculate the remaining consultation time of each doctor end based on the current consultation data and the historical consultation time; according to the remaining consultation time of each doctor end, the doctor end to be answered is allocated to the video call request, and then the corresponding doctor information and user waiting time are pushed to the user end of the video call request, and the call information of the video call request is pushed to the doctor end.

[0020] One embodiment of the above invention has the following advantages or beneficial effects: The ultra-fast video consultation service of the present invention realizes real-time analysis of load conditions in high-concurrency scenarios. For users who do not answer calls, the service analyzes the multi-dimensional information of doctors and assigns them to the most suitable doctors. Doctors can adjust the consultation rhythm based on user call record information so that waiting users can get doctor services faster. At the same time, based on the remaining processing time of the doctor, the user is reminded of how long it will take for the doctor to call back or to actively call, so as to give users clear expectations and improve user experience.

[0021] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0023] Figure 1 is a schematic diagram of the main process of the video consultation processing method according to the first embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of a TextCNN model structure according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of disease entity recognition according to an embodiment of the present invention;

[0026] Figure 4 is a schematic diagram of a doctor-side prompt for a missed user order according to an embodiment of the present invention;

[0027] Figure 5 is a timing diagram of a video consultation processing method according to a second embodiment of the present invention;

[0028] Figure 6 is a schematic diagram of main modules of a video medical consultation processing device according to an embodiment of the present invention;

[0029] Figure 7 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0030] Figure 8 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0032] Figure 1 FIG. 1 is a schematic diagram of the main flow of the video consultation processing method according to the first embodiment of the present invention. Figure 1 As shown, the video consultation processing method includes:

[0033] Step S101, in response to a video call request not being answered during a preset waiting period, obtaining current consultation data and historical consultation duration of each doctor's terminal.

[0034] In some embodiments, after the video call request is not answered during the preset waiting period, the process may further include: in response to the video call request initiated by the user not being answered by the doctor, the video call request is stored in a call queue. Then, if it is monitored that the video call request is not answered by the doctor during the preset waiting period, the video call request is marked as an unanswered user order. For example, when the user initiates a video call request, an idle doctor terminal can be allocated for access. However, if all doctor terminals are busy, the video call request enters a 60-second pre-waiting call queue. If a doctor terminal is idle during the 60-second pre-waiting period, an idle doctor terminal is automatically allocated. If the doctor terminal is not connected during the 60-second pre-waiting period, it is defined as an unanswered user order. Such orders enter the reminder system for analysis and processing, that is, step S102 and step S103 are executed.

[0035] As other embodiments, after obtaining the current consultation data and historical consultation duration of each doctor, consultation information can be generated according to preset target attribute statistics. In addition, the real-time voice information in the current consultation data can be converted into text information through a voice recognition program, and the text information can be processed using a natural language processing algorithm to obtain the condition information. Finally, the mapping relationship between the doctor's consultation information and the condition information is stored.

[0036] It is worth noting that the video consultation includes real-time video and real-time voice, in which the real-time voice information can be monitored and analyzed, and the present invention uses ASR (Automatic Speech Recognition, automatic speech recognition technology, which can convert voice into text to facilitate subsequent analysis by the system.) Voice recognition, converts real-time voice information into text information, and distinguishes the source of voice (such as user or doctor). After that, semantic understanding can be performed through NLP (Natural Language Processing, natural language processing is a discipline that studies language problems in human-computer interaction, and can analyze, judge and understand the meaning and significance of text information.) Algorithm capabilities can be used to perform semantic understanding, and two preliminary judgments can be made. On the one hand, it is disease information, that is, the main disease of the patient in this consultation. Although the doctor has not filled in the disease information, the content of the doctor-patient communication can be identified through semantic analysis; on the other hand, the progress of the consultation is estimated based on the communication information whether the consultation is close to completion. The disease information and the progress of the consultation are the condition information of the present invention. For example, the disease information included in the condition information is the diagnosis result, and the progress of the consultation is whether the consultation summary is filled in.

[0037] Among them, based on the analysis of historical consultation dialogue data of Internet hospitals, the progress of consultation can be divided into four stages: the first stage, asking about the condition: for example, "What discomfort do you have?", "How long have you been coughing?", "Do you have a fever?". The second stage, give a possible diagnosis (possible disease diagnosis): for example, "Your condition is considered to be pneumonia.", "There is currently a possibility of hyperthyroidism.". The third stage, give treatment suggestions: for example, "You can go to an offline hospital to check your thyroid function.", "It is recommended to take Lianhua Qingwen Capsules.". The fourth stage, give the end of the consultation script: for example, "If there are no other questions, then it's over, I wish you a speedy recovery.", "If there is no improvement, you can ask me again, please evaluate my service.". The consultation summary can be completed at the end of the fourth stage, of course, it can also be filled in based on some special circumstances that prevent the entire consultation progress from being completed. In addition, disease information can be determined during the execution of the four stages of the consultation.

[0038] In a further embodiment, the specific implementation process of semantic understanding through NLP algorithm capabilities may include: since the progress of the consultation dialogue is mainly driven by the doctor, after the real-time voice conversion, the TextCNN model is used to determine the stage of the consultation based on the doctor's words, such as Figure 2 As shown in Figure 1, the TextCNN model can apply convolutional neural network (CNN) to text classification tasks, using multiple kernel functions K of different granularities to extract key information in sentences, so as to better capture local correlations. Specifically, the TextCNN model applies convolutional neural network (CNN) to text classification tasks, including an input layer (e.g. Figure 2 , multi-channel text input), convolutional layers (e.g. Figure 2 One-dimensional convolutional layer with multiple convolution kernels), pooling layer and output layer (e.g. Figure 2 SoftMax layer in the middle). Among them, the words in the text information are encoded in the input layer, and the embeddings of different dimensions such as word level and word level are combined (Embedding can have word embedding or word embedding, which is equivalent to finding and replacing the vector of each word or word recorded in the dictionary from a dictionary, that is, mapping ordinary text into a multi-dimensional space.) are expressed as model input. The convolution layer uses a one-dimensional convolution method to extract the features of the sentence matrix through different numbers of channels and convolution kernel sizes. The pooling layer calculates the average value from the extracted feature matrix, splices it with the average values ​​from other channels, and combines it into the final feature vector. Finally, the SoftMax layer classifies the text. In this embodiment, the doctor's consultation content annotation data is used for model training. The TextCNN model can classify which of the four stages the sentence belongs to: "asking about the condition", "giving a tentative diagnosis", "giving treatment suggestions", and "giving the end of the consultation speech".

[0039] In a further embodiment, since the user's condition is not yet clear at the "asking about the condition" stage and the consultation is far from the end, disease information extraction is not performed at this stage. The doctor will summarize the user's condition at the "giving a tentative diagnosis" stage, and the mid-term of the consultation is more conducive to predicting the end time, so the user's condition in the consultation information is extracted through entity recognition at this stage. Entity recognition refers to the identification of entities with specific meanings in the text. In the embodiment, the LatticeLSTM (LatticeLSTM is a neural network structure that can capture time series information and convert it into explanations in the text for simultaneous processing of contextual information) model and CRF (Conditional Random Field, which is a conditional probability distribution model of another set of output random variables under the condition of a given set of input random variables) model are used to identify the disease words (disease entities) in the doctor's words at the target consultation stage (for example, the "giving a tentative diagnosis" stage). As Figure 3As shown in the figure, firstly, the text information of the target consultation stage (such as the text of the "give a tentative diagnosis" stage) is located through TextCNN classification, and the text is encoded using the word embedding method to obtain the vector of the target consultation stage sentence. The LatticeLSTM+CRF model trained with the labeled data is input to calculate the disease entities contained in the text as the condition information of the user in this consultation. For example, the text of the "give a tentative diagnosis" stage sentence is "currently there is a possibility of diabetes", and the "diabetes" disease entity is extracted through entity recognition, so "diabetes" is the condition information of the user in this consultation.

[0040] It can be seen that by analyzing the consultation stages and user condition information through TextCNN and entity recognition technology, as the input features of the linear regression model for predicting the end time of the consultation (step S102), combined with the doctor's historical consultation time, the prediction accuracy can be greatly improved.

[0041] For example, the real-time status of online doctors is analyzed. As shown in Table 1, real-time information includes two categories. One is consultation information, which can be generated by statistics of target attributes, including the number of orders to be received, the number of video orders to be received, the duration of the consultation (the duration of the current consultation) and the remaining duration (the remaining duration of a single consultation (the total duration of a single video is preset to end automatically in 15 minutes, of course, the doctor can also manually extend the time to 30 minutes)). The other category is condition information, including: consultation summary (doctor's summary of the current order), diagnosis (whether there is diagnosis information), consultation information volume (whether the consultation information has a complete file), prescription (whether the prescription has been issued), etc. For example: Based on the current information, it is preliminarily judged that Dr. Wang Chuan has few orders to be received and little remaining time, but the consultation summary has not been filled in. Dr. Hu Qi has a little more remaining time, but the summary has been completed.

[0042] Table 1

[0043]

[0044] As some further embodiments, when obtaining the historical consultation duration of the doctor, the specific implementation process may include: obtaining multiple consultation durations of the doctor within a preset time period, calling a preset consultation duration calculation model, and obtaining the historical consultation duration. Furthermore, the consultation duration calculation model may use the average value of multiple consultation durations as the historical consultation duration, the consultation duration calculation model may also use the median value of multiple consultation durations as the historical consultation duration, and so on. Which consultation duration calculation model to use may be determined based on the actual application scenario.

[0045] For example, big data is used to count the consultation duration of all consultation types of doctors in the previous month, and the electronic medical record diagnosis and user profile information are associated to form a doctor-order type-diagnosis-patient information (gender and age)-consultation duration detailed database association, as shown in Table 2, and matching is performed based on the current unanswered user orders and the corresponding historical average consultation duration is calculated.

[0046] Table 2

[0047]

[0048] Step S102, calling a preset waiting time prediction model to calculate the remaining consultation time of each doctor based on the current consultation data and the historical consultation time.

[0049] In some embodiments, a multiple linear regression model is constructed according to the current consultation data to utilize the historical consultation time, and the multiple linear regression model is solved using the gradient descent method to obtain the remaining consultation time of each doctor. Among them, the multiple linear regression model is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of mutual dependence between two or more variables. The characteristic of multiple linear regression is that there are two or more input variables (independent variables), and there is a linear relationship between the input variables and the output variables (dependent variables). In an embodiment, the present invention determines the end time of the consultation by a multiple linear regression model, and the independent variables of the regression model are formed by multivariate data (doctor's department, doctor's real-time status, doctor's historical consultation data, number of consultation rounds, consultation stage, disease information and other consultation data). The time from the doctor's current consultation time to the end of the consultation is used as the dependent variable of the regression model, and the doctor's historical consultation time is used to solve the regression model using the gradient descent method. It should be noted that the multiple linear regression model is trained based on all previous data, and the predicted data and actual data are subjected to error analysis, and the error is reduced through training.

[0050] Step S103, according to the remaining consultation time of each doctor end, allocate the doctor end to be answered for the video call request, and then push the corresponding doctor information and the remaining consultation time to the user end of the video call request, and push the call information of the video call request to the doctor end.

[0051] For example, as shown in Table 3, based on the current consultation data (consultation information and condition information), historical information (historical consultation time) and predicted information (remaining consultation time), comprehensive analysis shows that Dr. Hu Qi will complete the current consultation first, and the unreceived orders will be assigned to the doctor for reminder.

[0052] Table 3

[0053]

[0054] In some embodiments, the corresponding doctor information and the remaining consultation time are pushed to the user end of the video call request. The specific implementation process may include: triggering a notification program, pushing the corresponding doctor information and the remaining consultation time to the user end of the video call request, and then prompting the user of the assigned doctor information through language synthesis, and receiving a call back request from the doctor end or initiating a call program after the remaining consultation time.

[0055] For example, the user will use TTS (TTS is a speech synthesis technology that converts text information generated by a computer or externally input into understandable and fluent Chinese spoken output) to prompt the user that he has been assigned to Dr. Hu Qi and is expected to be available in 2 minutes before the system automatically hangs up. The user can wait for the doctor to call back or call again after 2 minutes.

[0056] In other embodiments, the call information of the video call request is pushed to the doctor side. The specific implementation process may include: triggering a notification program, pushing the call information of the video call request to the doctor side, and then displaying the call information in the doctor's waiting list, so that the doctor side can initiate a call back procedure based on the call information.

[0057] For example, Figure 4 As shown in the table below, the list of patients to be seen on the doctor's workbench ( Figure 4 The user call information will be displayed in the dashed box in the middle to remind the doctor that he is currently waiting for user information.

[0058] As some embodiments, the doctor end of the present invention can adjust the current consultation data according to the actual consultation situation (for example, the doctor end adjusts the preset total duration of a single video from the preset 15 minutes to 30 minutes.), and then dynamically allocates and adjusts according to the adjusted real-time consultation data. The specific implementation process includes: in response to the doctor end executing the program to adjust the current consultation data, the adjusted consultation data is obtained, and then the preset waiting time prediction model is called to calculate the adjusted remaining consultation time of the doctor end based on the historical consultation time. According to the adjusted remaining consultation time of the doctor end, the doctor end to be answered is allocated to the video call request, and it is determined whether the doctor end to be answered allocated to the video call request is consistent with the doctor end to be answered currently allocated to the video call request. If so, it will not be processed. Otherwise, the doctor information of the doctor end and the adjusted remaining consultation time are pushed to the user end of the video call request. Afterwards, an update allocation instruction sent by the user terminal is received, and the doctor terminal currently allocated for the video call request is updated to the doctor terminal, so as to push the call information of the video call request to the doctor terminal.

[0059] It can be seen that the present invention analyzes the load situation in real time and allocates it to appropriate doctors and users through data analysis. Both parties can intervene in the current behavior according to the real-time situation, so as to improve the experience of both doctors and patients.

[0060] Figure 5 FIG. 4 is a schematic diagram of the main flow of the video consultation processing method according to the second embodiment of the present invention. Figure 5 As shown, applied to a reminder system, the video consultation processing method includes:

[0061] The user terminal initiates a video call request to the dispatching system. The dispatching system detects the doctor's status and determines whether there is an available doctor. If not, the video call request is pushed to the reminder system. If yes, the dispatching system assigns a doctor and then determines whether the video call request is answered (i.e., whether the doctor answers the video call request). If yes, the doctor is connected to the video terminal for a video consultation. The doctor writes the consultation information to complete the video consultation. If not, the video call request is pushed to the reminder system.

[0062] The reminder system receives a video call request initiated by a user that is not answered by the doctor, stores the video call request in a call queue, monitors that the doctor is not answered during the preset waiting period, and marks the video call request as an unanswered user order. After that, the current consultation data of each doctor is obtained to perform real-time status analysis (for example, the consultation information and condition information are analyzed to obtain the number of orders to be received, the number of video orders to be received, the consultation time and the remaining time), and the historical consultation data of the doctor is obtained to obtain the historical consultation time. The preset waiting time prediction model is called to calculate the remaining consultation time of each doctor based on the current consultation data and the historical consultation time, that is, to complete the prediction of the waiting time. Based on the current consultation data (consultation information and condition information), historical information (historical consultation time) and predicted information (remaining consultation time), the doctor status information is obtained, so as to comprehensively evaluate the doctor status information to allocate the doctor to be answered for the video call request. It is worth noting that when evaluating the comprehensive doctor status information, the doctor end to be answered can be directly assigned to the video call request based on the remaining consultation time of the doctor end, or the doctor end to be answered can be assigned to the video call request based on other dimensions of the doctor status information.

[0063] In addition, the reminder system pushes the corresponding doctor information and the remaining consultation time to the user end of the video call request, and then prompts the user of the assigned doctor information through language synthesis, and receives the doctor end's call back request or initiates a call procedure after the remaining consultation time. And pushes the call information of the video call request to the doctor end, and then displays the call information in the doctor end's waiting list, so that the doctor end can initiate a call back procedure based on the call information.

[0064] Figure 6 is a schematic diagram of the main modules of the video medical consultation processing device according to an embodiment of the present invention. Figure 6 As shown, the video consultation processing device 600 includes an acquisition module 601 and a processing module 602. Among them, the acquisition module 601 acquires the current consultation data and historical consultation duration of each doctor's end in response to the video call request not being answered during the preset waiting period; the processing module 602 calls the preset waiting time prediction model to calculate the remaining consultation duration of each doctor's end based on the current consultation data and the historical consultation duration; according to the remaining consultation duration of each doctor's end, the doctor end to be answered is allocated to the video call request, and then the corresponding doctor information and user waiting time are pushed to the user end of the video call request, and the call information of the video call request is pushed to the doctor end.

[0065] In some embodiments, after the video call request is not answered during the preset waiting period, the acquisition module 601 further includes:

[0066] In response to a video call request initiated by a user not being answered by a doctor, the video call request is stored in a call queuing queue; if it is monitored that the video call request is not answered by the doctor during a preset waiting period, the video call request is marked as an unanswered user order.

[0067] In some embodiments, after the acquisition module 601 acquires the current consultation data and historical consultation duration of each doctor, it includes:

[0068] Generate medical consultation information based on preset target attribute statistics; and convert the real-time voice information in the current medical consultation data into text information through a voice recognition program, so as to process the text information using a natural language processing algorithm to obtain medical condition information; store the mapping relationship between the doctor's medical consultation information and the medical condition information.

[0069] In some embodiments, the processing module 602 calls a preset waiting time prediction model to calculate the remaining consultation time of each doctor based on the current consultation data and the historical consultation time, including:

[0070] A multivariate linear regression model is constructed based on the current consultation data to utilize the historical consultation duration, and the multivariate linear regression model is solved using the gradient descent method to obtain the remaining consultation duration of each doctor.

[0071] In some embodiments, the processing module 602 pushes the corresponding doctor information and the remaining consultation time to the user end of the video call request, including:

[0072] The notification program is triggered to push the corresponding doctor information and the remaining consultation time to the user end of the video call request, and then the user is prompted with the assigned doctor information through language synthesis, and a call back request from the doctor end is received or a call program is initiated after the remaining consultation time.

[0073] In some embodiments, the processing module 602 pushes the call information of the video call request to the doctor end, including:

[0074] The notification program is triggered to push the call information of the video call request to the doctor side, and then the call information is displayed in the waiting list of the doctor side, so that the doctor side can initiate a call back program based on the call information.

[0075] In some embodiments, the acquisition module 601 is further used to: in response to the doctor end executing a program to adjust the current medical consultation data, acquire the adjusted medical consultation data;

[0076] The processing module 602 is also used to: call a preset waiting time prediction model to calculate the adjusted remaining consultation time of the doctor side based on the historical consultation time; according to the adjusted remaining consultation time of the doctor side, determine that the doctor side to be answered assigned to the video call request is inconsistent with the doctor side to be answered currently assigned to the video call request, and then push the doctor information of the doctor side and the adjusted remaining consultation time to the user side of the video call request; receive the update allocation instruction sent by the user side, update the doctor side to be answered currently assigned to the video call request to the doctor side, so as to push the call information of the video call request to the doctor side.

[0077] It should be noted that the video medical consultation processing method and the video medical consultation processing device of the present invention have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0078] Figure 7 An exemplary system architecture 700 is shown to which the video medical consultation processing method or the video medical consultation processing device according to the embodiment of the present invention can be applied.

[0079] like Figure 7 As shown, system architecture 700 may include terminal devices 701, 702, 703, network 704 and server 705. Network 704 is used to provide a medium for communication links between terminal devices 701, 702, 703 and server 705. Network 704 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0080] The user can use the terminal devices 701, 702, 703 to interact with the server 705 through the network 704 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 701, 702, 703.

[0081] The terminal devices 701, 702, 703 may be various electronic devices having a video consultation processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0082] The server 705 may be a server that provides various services, such as a background management server (only an example) that provides support for users to use the terminal devices 701, 702, and 703. The background management server may analyze and process the received data such as the product information query request, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0083] It should be noted that the video medical consultation processing method provided in the embodiment of the present invention is generally executed by the server 705 , and accordingly, the computing device is generally disposed in the server 705 .

[0084] It should be understood that Figure 7 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0085] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 800 of a terminal device suitable for implementing an embodiment of the present invention. Figure 8 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0086] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the computer system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0087] The following components are connected to the I / O interface 805: an input section 805 including a keyboard, a mouse, etc.; an output section 806 including a cathode ray tube (CRT), a liquid crystal video interrogation processor (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0088] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-mentioned functions defined in the system of the present invention are executed.

[0089] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0090] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, it may be described as follows: a processor includes an acquisition module and a processing module. The names of these modules do not, in some cases, limit the modules themselves.

[0092] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by a device, the device includes obtaining the current consultation data and historical consultation duration of each doctor end in response to the video call request not being answered during the preset waiting period; calling the preset waiting time prediction model to calculate the remaining consultation duration of each doctor end based on the current consultation data and the historical consultation duration; according to the remaining consultation duration of each doctor end, assigning the doctor end to be answered to the video call request, and then pushing the corresponding doctor information and the remaining consultation duration to the user end of the video call request, and pushing the call information of the video call request to the doctor end.

[0093] The technical solution according to the embodiment of the present invention can solve the problem that the existing ultra-fast video consultation has a poor user experience under high concurrency conditions and cannot highlight high-efficiency consultation.

[0094] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A video consultation processing method, characterized in that: include: In response to the video call request not being answered during a preset waiting period, obtaining current consultation data and historical consultation duration of each doctor terminal; Call the preset waiting time prediction model to calculate the remaining consultation time for each doctor based on the current consultation data and historical consultation time; According to the remaining consultation time of each doctor terminal, the doctor terminal to be answered is allocated to the video call request, and then the corresponding doctor information and the remaining consultation time are pushed to the user terminal of the video call request, and the call information of the video call request is pushed to the doctor terminal; In response to the doctor side executing a program to adjust the current consultation data, the adjusted consultation data is obtained, and then a preset waiting time prediction model is called to calculate the remaining consultation time adjusted by the doctor side based on the historical consultation time; According to the remaining consultation time adjusted by the doctor end, it is determined that the doctor end to be answered assigned to the video call request is inconsistent with the doctor end to be answered currently assigned to the video call request, and the doctor information of the doctor end and the adjusted remaining consultation time are pushed to the user end of the video call request; Receive the update allocation instruction sent by the user terminal, update the doctor terminal currently allocated to the video call request to the doctor terminal, so as to push the call information of the video call request to the doctor terminal.

2. The method according to claim 1, characterized in that: After the video call request is not answered within a preset waiting period, it also includes: In response to a video call request initiated by a user not being answered by the doctor, storing the video call request in a call queuing queue; If it is monitored that the doctor does not answer the call during the preset waiting period, the video call request is marked as an unanswered user order.

3. The method according to claim 1, characterized in that After obtaining the current consultation data and historical consultation duration of each doctor, including: Generate medical consultation information according to preset target attribute statistics; and convert the real-time voice information in the current medical consultation data into text information through a voice recognition program, so as to process the text information using a natural language processing algorithm to obtain condition information; Store the mapping relationship between the doctor's consultation information and the condition information.

4. The method according to claim 1, characterized in that: Call the preset waiting time prediction model to calculate the remaining consultation time for each doctor based on the current consultation data and historical consultation time, including: A multivariate linear regression model is constructed based on the current consultation data to utilize the historical consultation duration, and the multivariate linear regression model is solved using the gradient descent method to obtain the remaining consultation duration of each doctor.

5. The method according to claim 1, characterized in that Pushing corresponding doctor information and remaining consultation time to the user terminal of the video call request includes: The notification program is triggered to push the corresponding doctor information and the remaining consultation time to the user end of the video call request, and then the user is prompted with the assigned doctor information through language synthesis, and a call back request from the doctor end is received or a call program is initiated after the remaining consultation time.

6. The method according to claim 1, characterized in that Pushing the call information of the video call request to the doctor end includes: The notification program is triggered to push the call information of the video call request to the doctor side, and then the call information is displayed in the waiting list of the doctor side, so that the doctor side can initiate a call back program based on the call information.

7. A video consultation processing device, characterized in that: include: An acquisition module, for acquiring current consultation data and historical consultation duration of each doctor's terminal in response to a video call request not being answered during a preset waiting period; A processing module, used to call a preset waiting time prediction model to calculate the remaining consultation time of each doctor terminal based on the current consultation data and the historical consultation time; according to the remaining consultation time of each doctor terminal, assign a doctor terminal to be answered for the video call request, and then push the corresponding doctor information and user waiting time to the user terminal of the video call request, and push the call information of the video call request to the doctor terminal; In response to the doctor side executing a program to adjust the current consultation data, the adjusted consultation data is obtained, and then a preset waiting time prediction model is called to calculate the remaining consultation time adjusted by the doctor side based on the historical consultation time; According to the remaining consultation time adjusted by the doctor end, it is determined that the doctor end to be answered assigned to the video call request is inconsistent with the doctor end to be answered currently assigned to the video call request, and the doctor information of the doctor end and the adjusted remaining consultation time are pushed to the user end of the video call request; Receive the update allocation instruction sent by the user terminal, update the doctor terminal currently allocated to the video call request to the doctor terminal, so as to push the call information of the video call request to the doctor terminal.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images