Follow-up visit image data processing method and system based on artificial intelligence

Abstract

The invention discloses a follow-up visit image data processing method and system based on artificial intelligence. The method comprises the steps of obtaining historical medical records of a target patient; based on a keyword matching rule, according to the historical medical record, determining a follow-up visit strategy and preference doctor information of the target patient; according to the follow-up visit strategy and the image data corresponding to the preferred doctor information, training to obtain a follow-up visit dialogue algorithm model capable of generating a face response image; responding to real-time speaking data input by the target patient, and generating response image data corresponding to the real-time speaking data according to the follow-up dialogue algorithm model; the response image data is used for being displayed to the target patient. Visibly, the virtual follow-up visit method and system can provide more real and efficient virtual follow-up visit service for the patient, the follow-up visit experience of the patient is improved, and errors of manual follow-up visit cost are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a follow-up image data processing method and system based on artificial intelligence. Background Art

[0002] With the increasing demand for big data computing and the widespread improvement of data processing capabilities, more and more medical institutions have begun to consider adopting more intelligent ways to provide follow-up services for patients. Among them, how to improve the patient experience during follow-up has become an important technical issue. Most of the existing follow-up solutions still only use simple data collection technology to obtain patient information. In actual follow-up, doctors are still arranged to follow up based on patient information. They do not fully consider the use of patients' historical medical records and the corresponding attending physicians' information to achieve more intuitive and real follow-up. The user experience is poor, the efficiency is low, and the labor cost is high. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a follow-up image data processing method and system based on artificial intelligence, which can provide patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a follow-up image data processing method based on artificial intelligence, the method comprising: Obtain historical medical records of target patients; Based on the keyword matching rules, according to the historical medical records, determine the follow-up strategy and preferred doctor information of the target patient; According to the follow-up strategy and the image data corresponding to the preferred doctor information, a follow-up dialogue algorithm model capable of generating facial response images is trained; In response to the real-time speech data input by the target patient, response image data corresponding to the real-time speech data is generated according to the follow-up dialogue algorithm model; the response image data is used to be displayed to the target patient.

[0005] As an optional embodiment, in the first aspect of the present invention, the historical medical records include consultation records and prescription records of the target patient in multiple historical time periods; the consultation records include historical records of communication with doctors on an online consultation platform.

[0006] As an optional implementation, in the first aspect of the present invention, the following steps are performed based on the keyword matching rule and the historical medical records to determine the follow-up strategy and preferred doctor information of the target patient, including: Based on the keyword matching rules, determining the consultation doctor information and prescription information in the consultation records and prescription records of the target patient in each historical time period; According to the preset correspondence between the prescribed medicine and the symptom, determining the symptom information corresponding to each prescribed medicine information; Counting the majority of the target patient's consulting doctor information in all the historical time periods to determine the target patient's preferred doctor information; A follow-up strategy for the target patient is determined according to the prescription information and the corresponding disease information of the target patient in all the historical time periods.

[0007] As an optional embodiment, in the first aspect of the present invention, determining the follow-up strategy of the target patient according to the prescription information and the corresponding symptom information of the target patient in all the historical time periods includes: Sort the prescription information and the corresponding symptom information of the target patient in all the historical time periods from early to late according to the corresponding historical time periods to obtain an information sequence; The information sequence is input into a trained follow-up strategy prediction neural network model to obtain the follow-up strategy for the target patient.

[0008] As an optional embodiment, in the first aspect of the present invention, the follow-up strategy prediction neural network model is trained by a training data set including multiple training information sequences and corresponding follow-up strategy annotations; the follow-up strategy includes follow-up frequency, follow-up time period, follow-up disease theme and follow-up tone type.

[0009] As an optional embodiment, in the first aspect of the present invention, the follow-up dialogue algorithm model includes a language response generation algorithm model and an image generation algorithm model; the language response generation algorithm model is used to analyze the input speech data to obtain corresponding response text data; the image generation algorithm model is used to generate voice data and facial speech image data according to the response text data and combine them to obtain facial speech audio and video data.

[0010] As an optional implementation, in the first aspect of the present invention, the training of a follow-up dialogue algorithm model capable of generating facial response images based on the image data corresponding to the follow-up strategy and the preferred doctor information includes: Acquire multiple follow-up dialogue texts corresponding to the same follow-up strategy in a historical database; Inputting the multiple follow-up dialogue texts into the LLM model for iterative training to obtain a language response generation algorithm model; Determine each frame of face image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information to obtain a face image training data set; The face image training data set is input into the multimodal RNN neural network algorithm model for iterative training to obtain an image generation algorithm model.

[0011] As an optional implementation, in the first aspect of the present invention, generating the response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model includes: Inputting the real-time speech data into a speech recognition algorithm to obtain a corresponding real-time speech text; Inputting the real-time speech text into the language response generation algorithm model to obtain a corresponding real-time response text; The real-time response text is input into the image generation algorithm model to obtain corresponding response image data.

[0012] A second aspect of an embodiment of the present invention discloses a follow-up image data processing system based on artificial intelligence, the system comprising: An acquisition module, used to obtain historical medical records of target patients; A determination module, configured to determine the follow-up strategy and preferred doctor information of the target patient based on the keyword matching rule and the historical medical records; A training module, for training a follow-up dialogue algorithm model capable of generating a facial response image based on the follow-up strategy and the image data corresponding to the preferred doctor information; A response module is used to respond to the real-time speech data input by the target patient and generate response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model; the response image data is used to display to the target patient.

[0013] As an optional embodiment, in the second aspect of the present invention, the historical medical records include consultation records and prescription records of the target patient in multiple historical time periods; the consultation records include historical records of communication with doctors on an online consultation platform.

[0014] As an optional implementation, in the second aspect of the present invention, the determination module determines the specific manner of the follow-up strategy and preferred doctor information of the target patient based on the keyword matching rule and the historical medical records, including: Based on the keyword matching rules, determining the consultation doctor information and prescription information in the consultation records and prescription records of the target patient in each historical time period; According to the preset correspondence between the prescribed medicine and the symptom, determining the symptom information corresponding to each prescribed medicine information; Counting the majority of the target patient's consulting doctor information in all the historical time periods to determine the target patient's preferred doctor information; A follow-up strategy for the target patient is determined according to the prescription information and the corresponding disease information of the target patient in all the historical time periods.

[0015] As an optional implementation, in the second aspect of the present invention, the determination module determines the specific manner of the follow-up strategy of the target patient according to the prescription information and the corresponding symptom information of the target patient in all the historical time periods, including: Sort the prescription information and the corresponding symptom information of the target patient in all the historical time periods from early to late according to the corresponding historical time periods to obtain an information sequence; The information sequence is input into a trained follow-up strategy prediction neural network model to obtain the follow-up strategy for the target patient.

[0016] As an optional embodiment, in the second aspect of the present invention, the follow-up strategy prediction neural network model is trained by a training data set including multiple training information sequences and corresponding follow-up strategy annotations; the follow-up strategy includes follow-up frequency, follow-up time period, follow-up disease theme and follow-up tone type.

[0017] As an optional embodiment, in the second aspect of the present invention, the follow-up dialogue algorithm model includes a language response generation algorithm model and an image generation algorithm model; the language response generation algorithm model is used to analyze the input speech data to obtain corresponding response text data; the image generation algorithm model is used to generate voice data and facial speech image data according to the response text data and combine them to obtain facial speech audio and video data.

[0018] As an optional implementation, in the second aspect of the present invention, the training module trains a follow-up dialogue algorithm model capable of generating a facial response image according to the follow-up strategy and the image data corresponding to the preferred doctor information, including: Acquire multiple follow-up dialogue texts corresponding to the same follow-up strategy in a historical database; Inputting the multiple follow-up dialogue texts into the LLM model for iterative training to obtain a language response generation algorithm model; Determine each frame of face image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information to obtain a face image training data set; The face image training data set is input into the multimodal RNN neural network algorithm model for iterative training to obtain an image generation algorithm model.

[0019] As an optional implementation, in the second aspect of the present invention, generating response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model includes: Inputting the real-time speech data into a speech recognition algorithm to obtain a corresponding real-time speech text; Inputting the real-time speech text into the language response generation algorithm model to obtain a corresponding real-time response text; The real-time response text is input into the image generation algorithm model to obtain corresponding response image data.

[0020] The third aspect of the present invention discloses another follow-up image data processing system based on artificial intelligence, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the artificial intelligence-based follow-up image data processing method disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the artificial intelligence-based follow-up image data processing method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can determine the follow-up strategy and preferred doctor information according to the historical medical records of the target patient based on the keyword matching rules, and then train the follow-up strategy and the preferred doctor information based on the image data corresponding to the image data to obtain a follow-up dialogue algorithm model that can generate the facial response image of the preferred doctor, so as to respond to the patient's speech in real time, thereby providing the patient with a more realistic and efficient virtual follow-up service, improving the patient's follow-up experience, and reducing the cost and errors of manual follow-up. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a follow-up image data processing method based on artificial intelligence disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of an artificial intelligence-based follow-up image data processing system disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another follow-up image data processing system based on artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a follow-up image data processing method and system based on artificial intelligence, which can determine the follow-up strategy and preferred doctor information according to the historical medical records of the target patient based on the keyword matching rule, and then train the image data corresponding to the follow-up strategy and the preferred doctor information to obtain a follow-up dialogue algorithm model that can generate the facial response image of the preferred doctor, so as to respond to the patient's speech in real time, thereby providing the patient with a more realistic and efficient virtual follow-up service, improving the patient's follow-up experience, and reducing the cost and error of manual follow-up. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 : is a flow chart of a method for processing follow-up image data based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The described artificial intelligence-based follow-up imaging data processing method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the artificial intelligence-based follow-up image data processing method may include the following operations: 101. Obtain the historical medical records of the target patient.

[0032] 102. Based on keyword matching rules and historical medical records, determine the target patient's follow-up strategy and preferred doctor information. 103. Based on the imaging data corresponding to the follow-up strategy and preferred doctor information, a follow-up dialogue algorithm model capable of generating facial response images is trained. 104. In response to the real-time speech data input by the target patient, generate response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model.

[0033] Optionally, the response image data is used for display to the target patient.

[0034] Specifically, during the implementation of the entire solution, in order to ensure that the patient's privacy data is protected, historical medical records and real-time speech data need to be encrypted using the AES encryption algorithm to obtain ciphertext, and when sent to the corresponding processing terminal, they are decrypted using the decryption algorithm and key to obtain plaintext for processing, and when the corresponding data is re-issued, it also needs to be encrypted using the encryption algorithm.

[0035] It can be seen that the above-mentioned embodiment of the invention can determine the follow-up strategy and preferred doctor information according to the historical medical records of the target patient based on the keyword matching rules, and then train the image data corresponding to the follow-up strategy and the preferred doctor information to obtain a follow-up dialogue algorithm model that can generate facial response images of the preferred doctor, so as to respond to the patient's speech in real time, thereby providing patients with more realistic and efficient virtual follow-up services, improving the patient's follow-up experience, and reducing the cost and errors of manual follow-up.

[0036] As an optional embodiment, in the above steps, the historical medical records include consultation records and prescription records of the target patient in multiple historical time periods.

[0037] It can be seen that through the above optional embodiments, the content of historical medical records is clarified, which can more accurately characterize the characteristics of the patient's historical medical conditions, assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0038] As an optional embodiment, in the above steps, based on the keyword matching rule and according to the historical medical records, determining the follow-up strategy and preferred doctor information of the target patient includes: Based on the keyword matching rules, determine the consultation doctor information and prescription information of the target patient in the consultation records and prescription records in each historical time period; According to the preset correspondence between prescription drugs and symptoms, determine the symptom information corresponding to each prescription drug information; Count the mode items of the target patient's consultation doctor information in all historical time periods to determine the target patient's preferred doctor information; Determine the follow-up strategy for the target patient based on the target patient's prescription information and corresponding disease information in all historical time periods.

[0039] In some optional embodiments, the follow-up time strategy of the target patient can be determined based on the follow-up records and preferences of the target patient in historical time periods, and the focus of the follow-up of the target patient can be determined based on the target patient's mental state, living habits, and awareness of the disease.

[0040] It can be seen that through the above optional embodiments, the follow-up strategy and preferred doctor information of the target patient can be determined based on the analysis and statistics of the patient's consultation records and prescription records in the historical time period, so as to facilitate subsequent training to obtain an accurate dialogue algorithm model, and assist in providing patients with more realistic and efficient virtual follow-up services, thereby improving the patient's follow-up experience and reducing the cost and errors of manual follow-up.

[0041] As an optional embodiment, in the above step, determining the follow-up strategy for the target patient according to the prescription information and corresponding symptom information of the target patient in all historical time periods includes: Sort the prescription information and corresponding symptom information of the target patient in all historical time periods from early to late according to the corresponding historical time periods to obtain an information sequence; The information sequence is input into the trained follow-up strategy prediction neural network model to obtain the follow-up strategy for the target patients.

[0042] It can be seen that through the above optional embodiments, the follow-up strategy can be predicted based on the target patient's prescription information and corresponding symptom information in all historical time periods through the trained follow-up strategy prediction neural network model, so as to obtain an accurate dialogue algorithm model through subsequent training, and assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0043] As an optional embodiment, in the above steps, the follow-up strategy prediction neural network model is trained by a training data set including multiple training information sequences and corresponding follow-up strategy annotations; the follow-up strategy includes follow-up frequency, follow-up time period, follow-up disease theme and follow-up tone type.

[0044] It can be seen that through the above optional embodiments, the training details of the follow-up strategy prediction neural network model and the content of the follow-up strategy are clarified, which can more accurately predict the follow-up strategy and characterize the points for following up on patients through the follow-up strategy, thereby assisting in providing patients with more realistic and efficient virtual follow-up services, improving the patient's follow-up experience, and reducing the cost and errors of manual follow-up.

[0045] As an optional embodiment, in the above steps, the follow-up dialogue algorithm model includes a language response generation algorithm model and an image generation algorithm model; the language response generation algorithm model is used to analyze the input speech data to obtain corresponding response text data; the image generation algorithm model is used to generate voice data and facial speech image data based on the response text data and combine them to obtain facial speech audio and video data.

[0046] It can be seen that through the above optional embodiments, the model architecture of the follow-up dialogue algorithm model is clarified, which can realize the generation of more intelligent facial speech audio and video data, assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0047] As an optional embodiment, in the above steps, training a follow-up dialogue algorithm model capable of generating facial response images based on the image data corresponding to the follow-up strategy and the preferred doctor information includes: Obtain multiple follow-up dialogue texts corresponding to the same follow-up strategy in the historical database; Input multiple follow-up dialogue texts into the LLM model for iterative training to obtain a language response generation algorithm model; Determine each frame of face image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information to obtain a face image training data set; The face image training data set is input into the multimodal RNN neural network algorithm model for iterative training to obtain the image generation algorithm model.

[0048] It can be seen that through the above-mentioned optional embodiments, a language response generation algorithm model can be trained based on multiple historical follow-up conversation texts, and an image generation algorithm model can be trained based on each frame of facial image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information and a multimodal RNN neural network algorithm, so as to provide patients with more realistic and efficient virtual follow-up services in the future, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0049] As an optional embodiment, in the above steps, generating response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model includes: Input the real-time speech data into the speech recognition algorithm to obtain the corresponding real-time speech text; Input the real-time speech text into the language response generation algorithm model to obtain the corresponding real-time response text; The real-time response text is input into the image generation algorithm model to obtain the corresponding response image data.

[0050] It can be seen that through the above-mentioned optional embodiments, the corresponding real-time speech text can be obtained through the speech recognition algorithm, and then the generation of facial response image data can be realized based on the language response generation algorithm model and the image generation algorithm model of the follow-up dialogue algorithm model, so as to provide patients with more realistic and efficient virtual follow-up services, improve the patient's follow-up experience, and reduce the cost and errors of manual follow-up.

[0051] Embodiment 2 See also Figure 2 , Figure 2 : is a schematic diagram of the structure of a follow-up image data processing system based on artificial intelligence disclosed in an embodiment of the present invention. Figure 2 The described artificial intelligence-based follow-up image data processing system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the artificial intelligence-based follow-up image data processing system may include: The acquisition module 201 is used to acquire the historical medical records of the target patient.

[0052] The determination module 202 is used to determine the follow-up strategy and preferred doctor information of the target patient based on the keyword matching rules and according to the historical medical records. The training module 203 is used to train a follow-up dialogue algorithm model capable of generating facial response images based on the image data corresponding to the follow-up strategy and the preferred doctor information. The response module 204 is used to respond to the real-time speech data input by the target patient and generate response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model.

[0053] Optionally, the response image data is used for display to the target patient.

[0054] It can be seen that the above-mentioned embodiment of the invention can determine the follow-up strategy and preferred doctor information according to the historical medical records of the target patient based on the keyword matching rules, and then train the image data corresponding to the follow-up strategy and the preferred doctor information to obtain a follow-up dialogue algorithm model that can generate facial response images of the preferred doctor, so as to respond to the patient's speech in real time, thereby providing patients with more realistic and efficient virtual follow-up services, improving the patient's follow-up experience, and reducing the cost and errors of manual follow-up.

[0055] As an optional embodiment, the historical medical records include consultation records and prescription records of the target patient in multiple historical time periods.

[0056] It can be seen that through the above optional embodiments, the content of historical medical records is clarified, which can more accurately characterize the characteristics of the patient's historical medical conditions, assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0057] As an optional embodiment, the determination module determines the specific manner of the target patient's follow-up strategy and preferred doctor information based on the keyword matching rule and historical medical records, including: Based on the keyword matching rules, determine the consultation doctor information and prescription information of the target patient in the consultation records and prescription records in each historical time period; According to the preset correspondence between prescription drugs and symptoms, determine the symptom information corresponding to each prescription drug information; Count the mode items of the target patient's consultation doctor information in all historical time periods to determine the target patient's preferred doctor information; Determine the follow-up strategy for the target patients based on their prescription information and corresponding disease information in all historical time periods.

[0058] It can be seen that through the above optional embodiments, the follow-up strategy and preferred doctor information of the target patient can be determined based on the analysis and statistics of the patient's consultation records and prescription records in the historical time period, so as to facilitate subsequent training to obtain an accurate dialogue algorithm model, and assist in providing patients with more realistic and efficient virtual follow-up services, thereby improving the patient's follow-up experience and reducing the cost and errors of manual follow-up.

[0059] As an optional embodiment, the determination module determines the specific manner of the follow-up strategy for the target patient according to the prescription information and corresponding symptom information of the target patient in all historical time periods, including: Sort the prescription information and corresponding symptom information of the target patient in all historical time periods from early to late according to the corresponding historical time periods to obtain an information sequence; The information sequence is input into the trained follow-up strategy prediction neural network model to obtain the follow-up strategy for the target patients.

[0060] It can be seen that through the above optional embodiments, the follow-up strategy can be predicted based on the target patient's prescription information and corresponding symptom information in all historical time periods through the trained follow-up strategy prediction neural network model, so as to obtain an accurate dialogue algorithm model through subsequent training, and assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0061] As an optional embodiment, the follow-up strategy prediction neural network model is trained by a training data set including multiple training information sequences and corresponding follow-up strategy annotations; the follow-up strategy includes follow-up frequency, follow-up time period, follow-up disease theme and follow-up tone type.

[0062] It can be seen that through the above optional embodiments, the training details of the follow-up strategy prediction neural network model and the content of the follow-up strategy are clarified, which can more accurately predict the follow-up strategy and characterize the points for following up on patients through the follow-up strategy, thereby assisting in providing patients with more realistic and efficient virtual follow-up services, improving the patient's follow-up experience, and reducing the cost and errors of manual follow-up.

[0063] As an optional embodiment, the follow-up dialogue algorithm model includes a language response generation algorithm model and an image generation algorithm model; the language response generation algorithm model is used to analyze the input speech data to obtain corresponding response text data; the image generation algorithm model is used to generate voice data and facial speech image data based on the response text data and combine them to obtain facial speech audio and video data.

[0064] It can be seen that through the above optional embodiments, the model architecture of the follow-up dialogue algorithm model is clarified, which can realize the generation of more intelligent facial speech audio and video data, assist in providing patients with more realistic and efficient virtual follow-up services, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0065] As an optional embodiment, the training module trains the follow-up dialogue algorithm model capable of generating facial response images according to the image data corresponding to the follow-up strategy and the preferred doctor information, including: Obtain multiple follow-up dialogue texts corresponding to the same follow-up strategy in the historical database; Input multiple follow-up dialogue texts into the LLM model for iterative training to obtain a language response generation algorithm model; Determine each frame of face image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information to obtain a face image training data set; The face image training data set is input into the multimodal RNN neural network algorithm model for iterative training to obtain the image generation algorithm model.

[0066] It can be seen that through the above-mentioned optional embodiments, a language response generation algorithm model can be trained based on multiple historical follow-up conversation texts, and an image generation algorithm model can be trained based on each frame of facial image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information and a multimodal RNN neural network algorithm, so as to provide patients with more realistic and efficient virtual follow-up services in the future, improve patients' follow-up experience, and reduce the cost and errors of manual follow-up.

[0067] As an optional embodiment, generating response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model includes: Input the real-time speech data into the speech recognition algorithm to obtain the corresponding real-time speech text; Input the real-time speech text into the language response generation algorithm model to obtain the corresponding real-time response text; The real-time response text is input into the image generation algorithm model to obtain the corresponding response image data.

[0068] It can be seen that through the above-mentioned optional embodiments, the corresponding real-time speech text can be obtained through the speech recognition algorithm, and then the generation of facial response image data can be realized based on the language response generation algorithm model and the image generation algorithm model of the follow-up dialogue algorithm model, so as to provide patients with more realistic and efficient virtual follow-up services, improve the patient's follow-up experience, and reduce the cost and errors of manual follow-up.

[0069] Embodiment 3 See also Figure 3 , Figure 3 This is another artificial intelligence-based follow-up image data processing system disclosed in an embodiment of the present invention. Figure 3 The described artificial intelligence-based follow-up image data processing system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the artificial intelligence-based follow-up image data processing system may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the artificial intelligence-based follow-up image data processing method described in the first embodiment.

[0070] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based follow-up image data processing method described in the first embodiment.

[0071] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the artificial intelligence-based follow-up image data processing method described in Example 1.

[0072] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0074] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0075] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0076] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0081] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0083] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0084] 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. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0085] Finally, it should be noted that the artificial intelligence-based follow-up image data processing method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A follow-up image data processing method based on artificial intelligence, characterized in that: The method comprises: Obtain historical medical records of target patients; Based on the keyword matching rules, according to the historical medical records, determine the follow-up strategy and preferred doctor information of the target patient; According to the follow-up strategy and the image data corresponding to the preferred doctor information, a follow-up dialogue algorithm model capable of generating facial response images is trained; In response to the real-time speech data input by the target patient, response image data corresponding to the real-time speech data is generated according to the follow-up dialogue algorithm model; the response image data is used to be displayed to the target patient.

2. The artificial intelligence-based follow-up image data processing method according to claim 1, characterized in that: The historical medical records include the target patient's consultation records and prescription records in multiple historical time periods; the consultation records include historical records of communication with doctors on an online consultation platform.

3. The artificial intelligence-based follow-up image data processing method according to claim 2, characterized in that: The method of determining the follow-up strategy and preferred doctor information of the target patient based on the keyword matching rule and the historical medical records includes: Based on the keyword matching rules, determining the consultation doctor information and prescription information in the consultation records and prescription records of the target patient in each historical time period; According to the preset correspondence between the prescribed medicine and the symptom, determining the symptom information corresponding to each prescribed medicine information; Counting the majority of the target patient's consulting doctor information in all the historical time periods to determine the target patient's preferred doctor information; A follow-up strategy for the target patient is determined according to the prescription information and the corresponding disease information of the target patient in all the historical time periods.

4. The artificial intelligence-based follow-up image data processing method according to claim 3, characterized in that: Determining the follow-up strategy for the target patient according to the prescription information and the corresponding symptom information of the target patient in all the historical time periods includes: Sort the prescription information and the corresponding symptom information of the target patient in all the historical time periods from early to late according to the corresponding historical time periods to obtain an information sequence; The information sequence is input into a trained follow-up strategy prediction neural network model to obtain the follow-up strategy for the target patient.

5. The artificial intelligence-based follow-up image data processing method according to claim 4, characterized in that: The follow-up strategy prediction neural network model is obtained by training a training data set including multiple training information sequences and corresponding follow-up strategy annotations; the follow-up strategy includes follow-up frequency, follow-up time period, follow-up disease theme and follow-up tone type.

6. The artificial intelligence-based follow-up image data processing method according to claim 5, characterized in that: The follow-up dialogue algorithm model includes a language response generation algorithm model and an image generation algorithm model; the language response generation algorithm model is used to analyze the input speech data to obtain corresponding response text data; the image generation algorithm model is used to generate voice data and facial speech image data according to the response text data and combine them to obtain facial speech audio and video data.

7. The artificial intelligence-based follow-up image data processing method according to claim 6, characterized in that: The training of a follow-up dialogue algorithm model capable of generating a facial response image based on the follow-up strategy and the image data corresponding to the preferred doctor information includes: Acquire multiple follow-up dialogue texts corresponding to the same follow-up strategy in a historical database; Inputting the multiple follow-up dialogue texts into the LLM model for iterative training to obtain a language response generation algorithm model; Determine each frame of face image and corresponding pronunciation text annotation and pronunciation audio annotation in the image data corresponding to the preferred doctor information to obtain a face image training data set; The face image training data set is input into the multimodal RNN neural network algorithm model for iterative training to obtain an image generation algorithm model.

8. The artificial intelligence-based follow-up image data processing method according to claim 6, characterized in that: The generating the response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model includes: Inputting the real-time speech data into a speech recognition algorithm to obtain a corresponding real-time speech text; Inputting the real-time speech text into the language response generation algorithm model to obtain a corresponding real-time response text; The real-time response text is input into the image generation algorithm model to obtain corresponding response image data.

9. An artificial intelligence-based follow-up image data processing system, characterized in that: The system comprises: An acquisition module, used to obtain historical medical records of target patients; A determination module, configured to determine the follow-up strategy and preferred doctor information of the target patient based on the keyword matching rule and the historical medical records; A training module, for training a follow-up dialogue algorithm model capable of generating a facial response image based on the follow-up strategy and the image data corresponding to the preferred doctor information; A response module is used to respond to the real-time speech data input by the target patient and generate response image data corresponding to the real-time speech data according to the follow-up dialogue algorithm model; the response image data is used to display to the target patient.

10. A follow-up image data processing system based on artificial intelligence, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based follow-up image data processing method as described in any one of claims 1-8.

Images