Automatic telephone follow-up visit method and device, electronic equipment and storage medium
Through the automated telephone follow-up method, the dialing plan and dialogue process are optimized using the GBDT model and BERT model, the problem of time-consuming manual follow-up is solved, efficient patient information collection and management is achieved, and the risk of human error is reduced.
Patent Information
- Application Number
- CN202411249904.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-26
AI Technical Summary
The existing manual manual follow-up methods are time-consuming and inefficient, making it difficult to achieve effective management of large-scale patients, especially in monitoring and evaluating the treatment effect of patients during medical follow-up.
Using automated telephone follow-up method, by obtaining the patient's telephone follow-up information, performing telephone follow-up, converting voice answers into text information, extracting key information, and synthesizing it with telephone follow-up information, and using GBDT model and BERT model for dialing plan optimization and dialogue Process adjustment to achieve automated follow-up.
Automatic telephone follow-up is realized, reducing the need for manual information entry, saving time, reducing the risk of human errors, and improving the follow-up efficiency.
Smart Images

Figure CN119031075A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of automated processing technology, and specifically relates to an automated telephone follow-up method, device, electronic device and storage medium. Background Art
[0002] Medical follow-up is an important part of medical services, involving the monitoring and evaluation of patient treatment effects. With the advancement of medical information technology, the demand for automation and intelligence of patient follow-up processes is growing.
[0003] The existing manual follow-up method is time-consuming and inefficient, and it is difficult to achieve effective management of large-scale patients. Summary of the invention
[0004] The purpose of this application is to provide an automated telephone follow-up method, device, electronic device and storage medium to realize automated telephone follow-up and improve the efficiency of telephone follow-up.
[0005] According to a first aspect of an embodiment of the present application, an automated telephone follow-up method is provided, which may include:
[0006] Obtain telephone follow-up information from patients;
[0007] Follow up the patient by phone according to the follow-up information and get the patient's voice answer;
[0008] Convert voice responses into text messages;
[0009] Extract key information from text information;
[0010] The key information is synthesized with the telephone follow-up information to obtain the patient's current medical information.
[0011] In some optional embodiments of the present application, obtaining the patient's telephone follow-up information includes:
[0012] Obtain the patient's phone number and time zone information;
[0013] Create a dial plan based on time zone information.
[0014] In some optional embodiments of the present application, formulating a dialing plan according to the time zone information includes:
[0015] Collect the patient's historical call data and construct a feature vector, which includes time periodicity features and personal call preferences;
[0016] Use the feature vector to train the GBDT model to obtain a trained GBDT model;
[0017] Use the trained GBDT model to predict the probability of the patient answering the call;
[0018] Create a dial plan based on the model's predictions.
[0019] In some optional embodiments of the present application, after conducting a telephone follow-up on the patient according to the telephone follow-up information and obtaining the patient's voice answer, the method further includes:
[0020] Record the result of each call, including success, busy and no answer;
[0021] Based on the dialing result, the exponential backoff algorithm is applied to dynamically adjust the redial interval and number of times to form a replay strategy;
[0022] Analyze the effect of the redial strategy and fine-tune the prediction parameters of the trained GBDT model based on the analysis results.
[0023] In some optional embodiments of the present application, formulating a dial plan according to the time zone information further includes:
[0024] Obtain patient medical records;
[0025] Select the corresponding follow-up questionnaire based on the medical record information and follow-up purpose.
[0026] In some optional embodiments of the present application, a telephone follow-up is performed on the patient according to the telephone follow-up information to obtain the patient's voice answer, including:
[0027] Follow-up questions were asked to patients by telephone according to the follow-up questionnaire;
[0028] Use the trained BERT model to parse the patient’s answers and identify the patient’s intent;
[0029] Dynamically adjust the conversation flow based on intent.
[0030] In some optional embodiments of the present application, after extracting key information from the text message, the automated telephone follow-up method further includes:
[0031] Determine the question text based on the key information;
[0032] Convert question text into voice information;
[0033] According to the patient's age and gender, the voice information parameters are adjusted to form voice questions.
[0034] According to a second aspect of an embodiment of the present application, an automated telephone follow-up device is provided, which may include:
[0035] The acquisition module is used to obtain the patient's telephone follow-up information;
[0036] The follow-up module is used to conduct telephone follow-up on the patient based on the telephone follow-up information and obtain the patient's voice answer;
[0037] A text conversion module, used to convert the voice answer into text information;
[0038] A key information extraction module is used to extract key information from text information;
[0039] The synthesis module is used to synthesize the key information with the telephone follow-up information to obtain the patient's current medical information.
[0040] According to a third aspect of an embodiment of the present application, an electronic device is provided, which may include:
[0041] processor;
[0042] a memory for storing processor-executable instructions;
[0043] The processor is configured to execute instructions to implement the automated telephone follow-up method as shown in any one of the embodiments of the first aspect.
[0044] According to a fourth aspect of an embodiment of the present application, a storage medium is provided. When instructions in the storage medium are executed by a processor of an information processing device or a server, the information processing device or the server implements an automated telephone follow-up method as shown in any one of the embodiments of the first aspect.
[0045] The above technical solution of the present application has the following beneficial technical effects:
[0046] The method of the embodiment of the present application obtains the patient's telephone follow-up information; performs a telephone follow-up on the patient according to the telephone follow-up information to obtain the patient's voice answer; converts the voice answer into text information; extracts key information from the text information; and finally synthesizes the key information with the telephone follow-up information to obtain the patient's current medical information. The method realizes automated telephone follow-up, reduces the need for manual information entry, thereby saving time and reducing the risk of human error. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 is a flowchart of an automated telephone follow-up method in an exemplary embodiment of the present application;
[0048] Figure 2 is a schematic structural diagram of an automated telephone follow-up device in an exemplary embodiment of the present application;
[0049] Figure 3 is a schematic structural diagram of an electronic device in an exemplary embodiment of the present application;
[0050] Figure 4 It is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with specific implementations and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present application. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concepts of the present application.
[0052] The accompanying drawings show schematic diagrams of layer structures according to embodiments of the present application. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clarity. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.
[0053] Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0054] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0055] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.
[0056] The following, in conjunction with the accompanying drawings, describes in detail the automated telephone follow-up method, device, electronic device, and storage medium provided in the embodiments of the present application through specific embodiments and their application scenarios.
[0057] like Figure 1 As shown, in a first aspect of an embodiment of the present application, an automated telephone follow-up method is provided, which may include:
[0058] S110: Obtain the patient's telephone follow-up information;
[0059] S120: Follow up the patient by phone according to the follow-up information, and obtain a voice answer from the patient;
[0060] S130: Convert the voice answer into text information;
[0061] S140: extracting key information from the text information;
[0062] S150: The key information is combined with the telephone follow-up information to obtain the patient's current medical information.
[0063] The method of this embodiment realizes automated telephone follow-up, reducing the need for manual information entry, thereby saving time and reducing the risk of human error.
[0064] In some embodiments, obtaining telephone follow-up information of the patient includes:
[0065] Obtain the patient's phone number and time zone information;
[0066] Create a dial plan based on time zone information.
[0067] Specifically, telephone number preprocessing may include:
[0068] Extract the patient's phone number and time zone information from the database; use regular expressions to validate the phone number format to ensure compliance with the E.164 international standard; adjust the dialing plan based on the patient's time zone information to match the local time of the patient's area.
[0069] In some embodiments, formulating a dial plan based on the time zone information includes:
[0070] Collect the patient's historical call data and construct a feature vector, which includes time periodicity features and personal call preferences;
[0071] Use the feature vector to train the GBDT model to obtain a trained GBDT model;
[0072] Use the trained GBDT model to predict the probability of the patient answering the call;
[0073] Create a dial plan based on the model's predictions.
[0074] To formulate a dialing plan, the first step is to determine the optimal dialing time. For example, the optimal dialing time prediction can include: collecting historical call data of patients, constructing feature vectors, including time periodicity features and personal call preferences; training the GBDT model, and using cross-validation to optimize model parameters to improve the accuracy of prediction. ; Arranging the dialing plan according to the model prediction results, giving priority to tasks with a high predicted call probability.
[0075] In some embodiments, after conducting a telephone follow-up on the patient according to the telephone follow-up information and obtaining the patient's voice answer, the method further includes:
[0076] Record the result of each call, including success, busy and no answer;
[0077] Based on the dialing result, the exponential backoff algorithm is applied to dynamically adjust the redial interval and number of times to form a replay strategy;
[0078] Analyze the effect of the redial strategy and fine-tune the prediction parameters of the trained GBDT model based on the analysis results.
[0079] In some embodiments, formulating a dial plan according to the time zone information further includes:
[0080] Obtain patient medical records;
[0081] Select the corresponding follow-up questionnaire based on the medical record information and follow-up purpose.
[0082] In some embodiments, a telephone follow-up is performed on the patient according to the telephone follow-up information to obtain a voice answer from the patient, including:
[0083] Follow-up questions were asked to patients by telephone according to the follow-up questionnaire;
[0084] Use the trained BERT model to parse the patient’s answers and identify the patient’s intent;
[0085] Dynamically adjust the conversation flow based on intent.
[0086] The BERT model training process in this embodiment may include: pre-training the BERT model on a large-scale text dataset in the medical field to learn medical-related language features; fine-tuning the model using annotated follow-up conversation data to optimize the model's performance in intent recognition and key information extraction; and verifying the performance of the fine-tuned model in actual follow-up conversations to ensure accurate understanding of patient responses.
[0087] In some embodiments, after extracting key information from the text message, the automated telephone follow-up method further includes:
[0088] Determine the question text based on the key information;
[0089] Convert question text into voice information;
[0090] According to the patient's age and gender, the voice information parameters are adjusted to form voice questions.
[0091] Specifically, the appropriate follow-up questionnaire can be dynamically selected based on the patient's medical history information and follow-up purpose; during the conversation, the BERT model is applied in real time to parse the patient's answers, identify intent, and extract information; based on the model analysis results, the conversation process is dynamically adjusted, such as skipping related questions about the information already obtained or providing additional explanations. Based on the output of the follow-up questionnaire and the dialogue management module, the text content that needs to be converted into speech is prepared; the text content is preprocessed, including the standardization of medical terms and the filling of personalized information.
[0092] In this implementation, speech conversion may include: using Tacotron 2 to convert the preprocessed text into a Mel spectrum; using the WaveNet vocoder to convert the Mel spectrum into a digital audio waveform to generate natural language speech; adjusting speech parameters such as speech rate and pitch according to the patient's age and gender to improve the clarity and naturalness of the speech. Outputting the generated speech to the patient through the telephone system for interactive question and answer; collecting patient feedback on the speech interaction, including comprehension and acceptance; adjusting the parameters and processes of speech synthesis based on the feedback results to continuously optimize the quality of speech output.
[0093] In a specific embodiment, an automated telephone follow-up method is provided, comprising:
[0094] Confirm the patient information. Patient information may include the following:
[0095] Patient ID: Uniquely identifies each patient.
[0096] Telephone number: Standard E.164 format.
[0097] Time Zone: The time zone where the patient is located, used to calculate the best local time to call.
[0098] Historical answering time: The specific time point of the last successful answering, used for pattern analysis.
[0099] Answering rate: the ratio of the number of successful answering attempts to the total number of attempts.
[0100] Dial time prediction.
[0101] The GBDT model is used to analyze the patient's historical call data, with features including days of the week, time periods of the day, and historical call answering rates, and the output is the predicted optimal time period for making calls. Cross-validation is used in model training to optimize hyperparameters to ensure the accuracy and generalization of predictions.
[0102] Adaptive redial strategy based on patient answering situation.
[0103] The result of each dial attempt is recorded as success, busy, no answer, etc., and the number of redials and waiting time fields are associated for subsequent policy adjustments. The policy is automatically adjusted based on the optimal redial time predicted by the random forest model, such as redialing busy calls after 10 minutes and redialing no answer calls after 2 hours, and setting a maximum daily redial limit.
[0104] The training process of the BERT conversation model may include:
[0105] BERT is fine-tuned on a specialized medical conversation dataset, using patient conversation content to train the model to identify different intents and extract key information. The fine-tuning process uses a finely annotated dataset that contains intent and key information for specific medical follow-up scenarios to enhance the model's application performance in the medical field.
[0106] High-quality speech synthesis.
[0107] Tacotron 2 is selected as the main framework for text-to-speech, combined with WaveNet vocoder to generate highly natural and fluent speech output. Tacotron 2 provides the ability to convert from text to Mel spectrum, while WaveNet is responsible for converting Mel spectrum into clear speech waveform.
[0108] The question ID and question text are used to specify the follow-up question to be converted to speech.
[0109] According to the patient's age and gender information, adjust the speech synthesis parameters, such as adjusting the speaking speed to a speed that is easier for elderly patients to understand and adjusting the pitch to match the general audio characteristics of the patient's gender.
[0110] Special processing is performed on medical terms to ensure their accurate pronunciation and improve the quality of voice information transmission.
[0111] It should be noted that the automated telephone follow-up method provided in the embodiment of the present application can be performed by an automated telephone follow-up device, or a control module in the automated telephone follow-up device for performing the automated telephone follow-up method. In the embodiment of the present application, the automated telephone follow-up method performed by the automated telephone follow-up device is taken as an example to illustrate the automated telephone follow-up device provided in the embodiment of the present application.
[0112] like Figure 2 As shown, in a second aspect of the embodiment of the present application, an automated telephone follow-up device is provided, which may include:
[0113] An acquisition module 210 is used to acquire the patient's telephone follow-up information;
[0114] A follow-up module 220 is used to conduct a telephone follow-up on the patient according to the telephone follow-up information and obtain a voice answer from the patient;
[0115] A text conversion module 230, for converting the voice answer into text information;
[0116] A key information extraction module 240 is used to extract key information from text information;
[0117] The synthesis module 250 is used to synthesize the key information and the telephone follow-up information to obtain the patient's current medical information.
[0118] The automated telephone follow-up device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.
[0119] The automated telephone follow-up device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.
[0120] The automated telephone follow-up device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.
[0121] Alternatively, if Figure 3 As shown, the embodiment of the present application further provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned automated telephone follow-up method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.
[0122] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.
[0123] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.
[0124] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .
[0125] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
[0126] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 409 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.
[0127] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned automated telephone follow-up method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0128] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0129] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned automated telephone follow-up method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0130] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0131] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0133] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. An automated telephone follow-up method, characterized in that: include: Obtain telephone follow-up information from patients; Performing a telephone follow-up on the patient according to the telephone follow-up information to obtain a voice response from the patient; Converting the voice response into text information; Extracting key information from the text information; The key information is synthesized with the telephone follow-up information to obtain the patient's current medical information.
2. The automated telephone follow-up method according to claim 1, characterized in that: Obtaining the patient's telephone follow-up information includes: Obtain the patient's phone number and time zone information; A dial plan is created based on the time zone information.
3. The automated telephone follow-up method according to claim 2, characterized in that: The step of formulating a dialing plan according to the time zone information includes: Collecting historical call data of patients and constructing a feature vector, wherein the feature vector includes time periodicity features and personal call preference; Using the feature vector to train the GBDT model to obtain a trained GBDT model; Using the trained GBDT model to predict the probability of the patient answering the call; Create a dial plan based on the model's predictions.
4. The automated telephone follow-up method according to claim 3, characterized in that: After conducting a telephone follow-up on the patient according to the telephone follow-up information and obtaining a voice response from the patient, the method further includes: Record the result of each call, including success, busy and no answer; Based on the dialing result, an exponential backoff algorithm is applied to dynamically adjust the redial interval and number of times to form a replay strategy; Analyze the effect of the redial strategy and fine-tune the trained GBDT model prediction parameters based on the analysis results.
5. The automated telephone follow-up method according to claim 2, characterized in that: The step of formulating a dial plan according to the time zone information further includes: Obtaining medical records of the patient; Select the corresponding follow-up questionnaire based on the medical record information and follow-up purpose.
6. The automated telephone follow-up method according to claim 5, characterized in that: The step of performing a telephone follow-up on the patient according to the telephone follow-up information and obtaining a voice response from the patient includes: Conduct telephone follow-up interviews with the patients based on the follow-up questionnaire; Analyze the patient's response using the trained BERT model to identify the patient's intent; Based on the stated intent, dynamically adjust the conversation flow.
7. The automated telephone follow-up method according to claim 1, characterized in that: After extracting the key information from the text message, the automated telephone follow-up method further includes: determining a question text based on the key information; Converting the question text into voice information; The voice information parameters are adjusted according to the age and gender of the patient to form a voice question.
8. An automated telephone follow-up device, characterized in that: include: The acquisition module is used to obtain the patient's telephone follow-up information; A follow-up module is used to conduct a telephone follow-up on the patient according to the telephone follow-up information and obtain the patient's voice response; A text conversion module, configured to convert the voice response into text information; A key information extraction module, used to extract key information from the text information; A synthesis module is used to synthesize the key information and the telephone follow-up information to obtain the patient's current medical information.
9. An electronic device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, the steps of the automated telephone follow-up method according to any one of claims 1 to 7 are implemented.
10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the automated telephone follow-up method according to any one of claims 1 to 7 are implemented.
