Online inquiry method and device based on 5G message

Abstract

The invention discloses an online inquiry method and device based on a 5G message, and relates to the technical field of rich media message processing, and the method comprises the steps: after an inquiry request sent by 5G terminal equipment is obtained, based on inquiry demand information in the inquiry request, issuing a 5G message template corresponding to the inquiry demand information to the 5G terminal equipment in a 5G message form; obtaining a target 5G message from the 5G terminal device, the target 5G message comprising a 5G message template filled with inquiry information; based on the types of the inquiry information, inquiry results corresponding to different types of inquiry information are determined, and the types of the inquiry information comprise the type containing skin picture information and the type containing chronic disease description text. And information inquiry interaction and inquiry result determination are performed through the 5G message, so that the problems of easy information leakage and tedious inquiry caused by a software mode are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of rich media message processing based on artificial intelligence, and particularly relates to an online consultation method and device based on 5G messages. Background Art

[0002] In the related art, the form of online consultation usually requires users to download relevant software to realize online consultation. This method has the risks of information leakage and the defect of cumbersome consultation. Summary of the Invention

[0003] The main object of the present invention is to provide an online consultation method and device based on 5G messages to solve the deficiencies in the related art.

[0004] To achieve the above object, according to the first aspect of the present invention, an online consultation method based on 5G messages is provided, including: after obtaining a consultation request sent by a 5G terminal device, based on the consultation requirement information in the consultation request, sending a 5G message template corresponding to the consultation requirement information to the 5G terminal device in the form of a 5G message; obtaining a target 5G message from the 5G terminal device, where the target 5G message includes the 5G message template filled with consultation information; based on the category of the consultation information, respectively determining consultation results corresponding to different types of consultation information, where the category of the consultation information includes a type containing skin picture information and a type containing chronic disease description text.

[0005] Optionally, when the category of the consultation information belongs to the type containing skin picture information, input the picture information into a pre-trained neural network model to output the disease name corresponding to the picture information; retrieve information of a specified dimension associated with the disease name from a medical knowledge database, where the information of the specified dimension includes medication instructions and precautions information.

[0006] Optionally, the pre-trained neural network model is composed of a convolutional neural network, where in the convolutional neural network, there are an input layer, a convolutional layer, and a fully connected layer; the convolutional layer uses a KAN convolutional layer, and the connection parameter function of the trained KAN convolutional layer is:

[0007] The function μ has a domain of [0,1] and a range of real numbers R, and the function has a domain of R and a range of R; f(x) is an arbitrary continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with a subscript of p, and μ q，p (x p ) represents a single variable x PRepresentation function under q Represents the q-subscript binary finite group function.

[0008] Optionally, when training the shown neural network model, use the training samples as the input of the neural network model and use the disease names corresponding to each training sample as the output for training.

[0009] Optionally, when the category of the consultation information belongs to the type including chronic disease description text, match the corresponding chronic disease medication information and chronic disease precautions information from the medical knowledge database.

[0010] Optionally, regularly send specified health care information to the users of 5G terminal devices belonging to the consultation information of the chronic disease description text type, where the specified health care information is sent in the form of 5G messages.

[0011] Optionally, when constructing the medical knowledge database, construct a name library of different disease names and establish corresponding structured data according to each disease name, where the structured data includes medication information corresponding to skin diseases and precautions information; and chronic disease medication and chronic disease precautions information corresponding to chronic diseases.

[0012] According to the second aspect of the present invention, there is provided an online consultation device based on 5G messages, including: a 5G message sending unit, configured to, after obtaining a consultation request sent by a 5G terminal device, based on the consultation requirement information in the consultation request, send a 5G message template corresponding to the consultation requirement information to the 5G terminal device in the form of 5G messages; a 5G message obtaining unit, configured to obtain a target 5G message from the 5G terminal device, where the target 5G message includes the 5G message template filled with consultation information; and a processing unit, configured to respectively determine consultation results corresponding to different types of consultation information based on the category of the consultation information, where the category of the consultation information includes the type including skin picture information and the type including chronic disease description text.

[0013] According to the third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a computer to execute the method according to any one of the first aspect.

[0014] According to the fourth aspect of the present invention, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; where the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the method according to any one of the implementation manners of the first aspect.

[0015] The online consultation method and device based on 5G messages in this embodiment, wherein the method includes: after obtaining a consultation request sent by a 5G terminal device, based on the consultation requirement information in the consultation request, sending a 5G message template corresponding to the consultation requirement information to the 5G terminal device in the form of a 5G message; obtaining a target 5G message from the 5G terminal device, where the target 5G message includes the 5G message template filled with consultation information; based on the category of the consultation information, respectively determining consultation results corresponding to different types of consultation information, where the category of the consultation information includes a type containing skin picture information and a type containing chronic disease description text. Through the more friendly interactive 5G message for information consultation interaction with artificial intelligence and determining the consultation result, it avoids the problems of easy information leakage caused by software methods and cumbersome consultation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is the flowchart of the online consultation method based on 5G messages in the embodiment of the present invention;

[0018] Figure 2 is the system architecture diagram applicable to the online consultation method based on 5G messages in the embodiment of the present invention;

[0019] Figure 3 is the schematic diagram of the electronic device in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so as to implement the embodiments of the present invention described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0023] The system architecture applicable to the method of this embodiment may include 5G terminal devices. Different users can send consultation requests to the execution entity, the 5G message platform, of the method of this embodiment through the terminal devices. The consultation requests may be consultation requests for skin diseases, etc., or consultation requests for chronic disease health care users. For skin disease consultation, pictures can be uploaded. The platform includes a 5G message server or a server cluster. The server or the server cluster performs disease judgment based on the deployed CNN+KAN model and calls the information corresponding to the disease from the medical knowledge database. For chronic diseases, text descriptions can be uploaded, and then the corresponding health care information can be called from the medical knowledge database based on the description information. The medical knowledge in the medical knowledge database can be improved by existing materials, or can be improved by medical workers or medical experts.

[0024] According to an embodiment of the present invention, an online consultation method based on 5G messages is provided, as Figure 1 shown, including the following steps 101 to step 103:

[0025] Step 101: After receiving the consultation request sent by the 5G terminal device, based on the consultation requirement information in the consultation request, send the 5G message template corresponding to the consultation requirement information to the 5G terminal device in the form of a 5G message.

[0026] In this step, referring to Figure 2, the user can send a consultation request to the 5G message platform through the 5G message terminal, that is, the 5G terminal device of this embodiment. The 5G terminal device can be a mobile phone with a 5G message communication mechanism. The mobile phone with the 5G message communication mechanism can be a 5G mobile phone that supports 5G network communication, or a mobile phone that supports receiving and displaying 5G messages. 5G messages are 5GRCS, 5G rich media messages. A consultation request can be sent to the 5G message platform through a 5G terminal device. Exemplarily, a user can register through a registration terminal device of a hospital, and the user automatically registers after entering the mobile phone number when registering. The registration device and the 5G message platform can communicate through the Internet, and after registration, the server of the 5G message platform can send a 5G message to the user's mobile phone. The 5G terminal device can interact with the 5G message platform based on the registered mobile phone number. After receiving the consultation information, the server of the 5G message platform can send a template to the 5G terminal device in a 5G message mode based on the mobile phone number, so that the user can interact directly through the 5G message, and the user can save the download, registration, login and other operations. For example, since online consultation for relatively intuitive diseases such as dermatology and infectious surgery, as well as non-emergency (chronic disease) scenarios are suitable for interactive online consultation in 5G message scenarios, corresponding 5G message templates can be sent to 5G terminal devices of different types of consultation information. The template can include a fill-in area for users to upload photos and text descriptions.

[0027] Compared with traditional messages, 5G messages support picture replies, which provides a technical basis for interacting with skin disease pictures. Compared with the PC system, 5G messages are mobile-side operations that support RCS messages, which is very convenient.

[0028] Step 102: Obtain a target 5G message from the 5G terminal device, wherein the target 5G message includes a 5G message template filled with medical consultation information.

[0029] Step 103: Based on the categories of the medical inquiry information, determine the medical inquiry results corresponding to different types of medical inquiry information, wherein the categories of the medical inquiry information include a type containing skin picture information and a type containing chronic disease description text.

[0030] In the above steps, the user can fill in the 5G message template through the 5G terminal device, and after receiving the filled template sent by the 5G terminal device, the filled medical information can be processed. The types of medical information can include pictures such as dermatology and infectious surgery that can be objectively diagnosed through pictures, and can include non-emergency categories (chronic diseases) and text that can be diagnosed through text descriptions.

[0031] As an alternative implementation of this embodiment, when the category of the consultation information belongs to the type including skin picture information, the picture information is input into a pre-trained neural network model to output the disease name corresponding to the picture information; based on the disease name, information of a specified dimension associated with the disease name is retrieved from a medical knowledge database, where the information of the specified dimension includes medication instructions and precautions information.

[0032] In this alternative implementation, if a user uploads pictures of skin or

[0033] surgical infection, the CNN+KAN model can be used for recognition. After identifying the disease name, such as a skin disease name or an infection name, the corresponding disease materials in the library can be retrieved, which may include medication instructions and life precautions, etc. If the model fails to identify the disease, the user will be prompted to go to the hospital for further examination.

[0034] Compared with the mini-programs of third-party platforms, 5G messaging is easier to integrate with AI and use AI message agents to reply to questions submitted by patients.

[0035] As an alternative implementation of this embodiment, the pre-trained neural network model is composed of a convolutional neural network, where the convolutional neural network includes an input layer, a convolutional layer, and a fully connected layer; the convolutional layer uses a KAN convolutional layer, and the connection parameter function of the trained KAN convolutional layer is: The domain of the function μ is [0,1], and the range is the set of real numbers R. The function has the domain of R and the range of R; f(x) is an arbitrary continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with the subscript p, and μ q，p (x p ) represents the representation function of the single variable x P under q, represents the function of the q-th subscript binary finite group.

[0036] As an alternative implementation of this embodiment, when training the neural network model, the training samples are used as the input of the neural network model, and the disease names corresponding to the training samples are used as the output for training.

[0037] In the above optional implementation, the present application uses the structure of CNN (Convolutional Neural Network) + KAN (Kolmogorov - Arnold Networks) to achieve prediction. When training this model, first obtain training samples: collect pictures and videos of the dermatology department and infectious surgery department of the medical system (after intercepting key video frames from the video, the obtained frame pictures are processed as pictures) and the correct diagnosis conclusions of doctors and other data, and use CNN + KAN for training. Through training a large number of pictures, it is used to identify the disease name. Exemplarily, picture materials of the dermatology department and infectious surgery department in the medical system that have been successfully diagnosed with corresponding diseases can be screened, and those that have completed recovery and are single skin diseases or infectious diseases are selected (to prevent interference of data).

[0038] The convolutional neural network of CNN (Convolutional Neural Network) + KAN (Kolmogorov - Arnold Networks) multi - layer perceptron. In this embodiment, when building, the input layer, output layer, pooling layer, etc. of CNN are retained. The convolutional layer of the convolutional neural network is replaced by the KAN convolutional layer, and each convolutional kernel is obtained through a non - linear function learned by the KAN model (to replace the activation function with fixed nodes). During the CNN + KAN training process, a part of the collected picture data set of the dermatology department and infectious surgery department of the medical system is used for training (training data set), and the other part is used for testing (testing data set). The connection lines of the KAN convolutional layer are dynamically adjusted during the learning process (different from the traditional neural network connected through the activation function). Retain the input layer (input of the original learning pictures), pooling layer (reduce parameters and improve efficiency) and fully - connected layer (perform classification regression) of the convolutional neural network. During training, KAN quickly and efficiently performs image segmentation and more accurately identifies the key points and edge information of the image.

[0039] The reason for using CNN (Convolutional Neural Network) + KAN (Kolmogorov - Arnold Network) in this embodiment is that although the single CNN model is efficient in training in the field of picture recognition, it loses some accuracy. This is mainly reflected in that the network uses a unified activation function (common sigmod function, Tanh, PReLU, ReLU, etc.), and the training process is the gradient descent of the loss function. Finally, the optimal model is trained for recognition. The input parameters are added with weights to obtain a value, and the activation function is used to judge whether it is used as the output. The training structure effect is not the best. Through the above - trained model, the purpose of recognizing the corresponding name of the input picture is achieved.

[0040] In this embodiment, the KAN (Kolmogorov-Arnold network) model places the activation function on the weights and uses a learnable activation function on the weights, parameterizing the one-dimensional activation function of the CNN into a curve so that the network can process and learn the complex relationships of the input data in a more flexible and closer way to the Kolmogorov-Arnold representation theorem. Compared with the multi-layer perceptron neural network that uses the activation function as the output, KAN trains each activation function into a non-linear combination function, and the input generates parameter output values through the trained activation function.

[0041] The difference between CNN+KAN and using only CNN is that the activation function of the CNN network nodes uses the Kolmogorov-Arnold theorem to obtain the complex relationships of the input data. Compared with directly using a fixed activation function in CNN, this process requires additional training time, resulting in a slower training speed, but it can obtain very high interpretability, improve the recognition accuracy, and enhance the accuracy of identifying a certain skin disease or surgical infectious disease in the photographed pictures.

[0042] Compared with the independent CNN, in CNN+KAN, the convolutional layer of CNN is replaced by the KAN convolution, and the connection parameter function of each level of the convolutional layer after the final training of KAN (the activation function in the independent CNN) is a finite composite function of the Kolmogorov-Arnold representation theorem (binary addition finite composition). The mathematical formula of the Kolmogorov-Arnold representation theorem can be expressed as:

[0043] The domain of the function μ is [0,1], and the range is the real number R. The function has a domain of R and a range of R; here: μ q，p [0,1]->R, function; the domain of μ is [0,1], f(x) is an arbitrary continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with subscript p, and μ q，p (x p ) represents the representation function of the single variable x P under q, represents the binary finite group function with subscript q.

[0044] Example: Then the composite function is expressed as: For the combination of binary finite addition: In this way, the multi-variable continuous function is transformed into the finite addition of multi-variable single functions, increasing the interpretability and accurate output.

[0045] As an alternative implementation of this embodiment, when the category of the inquiry information belongs to the type including chronic disease description text, the corresponding chronic disease medication information and chronic disease precautions information are matched from the medical knowledge database.

[0046] In this alternative implementation, the chronic disease description submitted by the user through the 5G message can be used to retrieve the conventional medication instructions and life precautions from the database and send them to the user based on the description text.

[0047] As an alternative implementation of this embodiment, the designated health care information is regularly sent to the users of 5G terminal devices belonging to the inquiry information of the chronic disease description text type, and the designated health care information is sent in the form of 5G messages.

[0048] In this alternative implementation, the users who have received the treatment plan and have good effects are labeled. By recording the user information, for the labeled users who meet the stock of chronic diseases, based on the data in the medical knowledge database, health care messages such as chronic disease medications and precautions are regularly pushed.

[0049] As an alternative implementation of this embodiment, when constructing the medical knowledge database, a name library of different disease names is constructed, and corresponding structured data is established according to each disease name, where the structured data includes the medication information corresponding to skin diseases and the precautions information; and the chronic disease medications and chronic disease precautions information corresponding to chronic diseases.

[0050] In this alternative implementation, a proprietary name library for routine health care, skin and surgical infection diseases, etc. of the medical system is established, and the structured data is stored in the system database. Establish the association data of routine health care (such as medications and life precautions for common chronic diseases such as hypertension), and skin and surgical infection disease names and corresponding medications and life precautions. Refer to Figure 2 , medical workers or experts can maintain the medical knowledge database based on the medical knowledge they master.

[0051] Compared with other systems, the 5G message has a high sending and reaching rate. For the push of 5G messages corresponding to chronic diseases, it can improve the viewing and clicking effects (the effects of other systems that require login, apps, mini-programs, etc. are relatively poor).

[0052] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0053] According to an embodiment of the present invention, there is also provided an online medical consultation device based on 5G messages, including: a 5G message sending unit, configured to, after obtaining a medical consultation request sent by a 5G terminal device, based on the medical consultation requirement information in the medical consultation request, send a 5G message template corresponding to the medical consultation requirement information to the 5G terminal device in the form of a 5G message; a 5G message obtaining unit, configured to obtain a target 5G message from the 5G terminal device, where the target 5G message includes the 5G message template filled with medical consultation information; and a processing unit, configured to respectively determine medical consultation results corresponding to different types of medical consultation information based on the category of the medical consultation information, where the category of the medical consultation information includes a type containing skin picture information and a type containing chronic disease description text.

[0054] As an optional implementation manner of this embodiment, when the category of the medical consultation information belongs to the type containing skin picture information, the picture information is input into a pre-trained neural network model, and the disease name corresponding to the picture information is output; and the information of the specified dimension associated with the disease name is retrieved from the medical knowledge database based on the disease name, where the information of the specified dimension includes medication instructions and precautions information.

[0055] As an optional implementation manner of this embodiment, the pre-trained neural network model is composed of a convolutional neural network, where in the convolutional neural network, there are an input layer, a convolutional layer, and a fully connected layer; the convolutional layer uses a KAN convolutional layer, where the connection parameter function of the trained KAN convolutional layer is: The function μ has a domain of [0,1] and a range of real numbers R, and the function has a domain of R and a range of R; f(x) is an arbitrary continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with a subscript of p, and μ q，p (x p ) represents the representation function of a single variable x P under q, and represents the function of the q-th subscript binary finite group.

[0056] As an optional implementation manner of this embodiment, when training the neural network model, training samples are used as the input of the neural network model, and the disease names corresponding to the training samples are used as the output for training.

[0057] As an optional implementation manner of this embodiment, when the category of the medical consultation information belongs to the type containing chronic disease description text, the corresponding chronic disease medication information and chronic disease precautions information are matched from the medical knowledge database.

[0058] As an alternative implementation of this embodiment, specified health care information is periodically sent to the users of 5G terminal devices belonging to the consultation information of the chronic disease description text type, where the specified health care information is sent in the form of 5G messages.

[0059] As an alternative implementation of this embodiment, when constructing the medical knowledge database, a name library of different disease names is constructed, and corresponding structured data is established according to each disease name, where the structured data includes medication information corresponding to skin diseases and information on precautions; and chronic disease medications and chronic disease precaution information corresponding to chronic diseases.

[0060] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor can implement the method described in any of the above embodiments.

[0061] According to an embodiment of the present invention, the present invention also provides a readable storage medium, which stores computer instructions for enabling a computer to implement the method described in any of the above embodiments when executed.

[0062] According to an embodiment of the present invention, the present invention also provides a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.

[0063] Figure 3 The schematic block diagram of an example electronic device 300 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0064] As Figure 3 shown, the electronic device 300 includes a computing unit 301, which can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 302 or the computer program loaded from the storage unit 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0065] Multiple components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disc, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0066] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be executed.

[0067] The various embodiments of the systems and techniques described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0068] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0069] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 foregoing.

Claims

1. An online consultation method based on 5G messages, characterized in that: include: After obtaining the consultation request sent by the 5G terminal device, based on the consultation requirement information in the consultation request, a 5G message template corresponding to the consultation requirement information is sent to the 5G terminal device in the form of a 5G message; Obtaining a target 5G message from the 5G terminal device, wherein the target 5G message includes a 5G message template filled with medical inquiry information; Based on the categories of the medical inquiry information, respectively determine the medical inquiry results corresponding to the different types of medical inquiry information, wherein the categories of the medical inquiry information include a type containing skin picture information and a type containing chronic disease description text; When the category of the medical inquiry information belongs to the type including skin picture information, the picture information is input into the pre-trained neural network model, and the disease name corresponding to the picture information is output; Based on the disease name, retrieve information of a specified dimension associated with the disease name from a medical knowledge database, wherein the information of the specified dimension includes medication instructions and precautions information; The pre-trained neural network model is composed of a convolutional neural network, wherein the convolutional neural network includes an input layer, a convolutional layer and a fully connected layer; the convolutional layer uses a KAN convolutional layer, wherein the connection parameter function of the trained KAN convolutional layer is: The domain of the function μ is [0,1], the range is the real number R, and the function The domain is R, the range is R; f(x) is any continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with subscript p, μ q，p (x p ) represents a single variable x P The representation function under q is, Denotes the qth subscript two-variable finite group function.

2. The online consultation method based on 5G messages according to claim 1 is characterized in that: When training the neural network model shown, the training samples are used as inputs of the neural network model, and the disease names corresponding to the training samples are used as outputs for training.

3. The online consultation method based on 5G messages according to claim 1 is characterized in that: When the category of the medical inquiry information belongs to the type containing chronic disease description text, the corresponding chronic disease medication information and chronic disease precaution information are matched from the medical knowledge database.

4. The online consultation method based on 5G messages according to claim 1 or 3, characterized in that: Specified health care information is regularly sent to users of 5G terminal devices that provide chronic disease description text-type medical consultation information, wherein the specified health care information is sent in the form of 5G messages.

5. The online consultation method based on 5G messages according to claim 1 or 3, characterized in that: When constructing the medical knowledge database, a name library of different disease names is constructed, and corresponding structured data is established according to each disease name, wherein the structured data includes medication information and precautions information corresponding to skin diseases; and chronic disease medication and chronic disease precautions information corresponding to chronic diseases.

6. An online consultation device based on 5G messages, characterized in that: include: A 5G message sending unit is used to send a 5G message template corresponding to the medical consultation requirement information to the 5G terminal device in the form of a 5G message based on the medical consultation requirement information in the medical consultation request after obtaining the medical consultation request sent by the 5G terminal device; A 5G message acquisition unit, configured to acquire a target 5G message from the 5G terminal device, wherein the target 5G message includes a 5G message template filled with medical inquiry information; A processing unit is used to determine the consultation results corresponding to different types of consultation information based on the category of the consultation information, wherein the category of the consultation information includes a type containing skin picture information and a type containing chronic disease description text; when the category of the consultation information belongs to the type containing skin picture information, the picture information is input into a pre-trained neural network model, and the disease name corresponding to the picture information is output; based on the disease name, information of a specified dimension associated with the disease name is retrieved from a medical knowledge database, wherein the information of the specified dimension includes medication instructions and precautions information; the pre-trained neural network model is composed of a convolutional neural network, wherein the convolutional neural network includes an input layer, a convolutional layer and a fully connected layer; the convolutional layer uses a KAN convolutional layer, wherein the connection parameter function of the trained KAN convolutional layer is: The domain of the function μ is [0,1], the range is the real number R, and the function The domain is R, the range is R; f(x) is any continuous function, expressed as a combination of several single-variable functions and addition operations; x P represents a single variable with subscript p, μ q，p (x p ) represents a single variable x P The representation function under q is, Denotes the qth subscript two-variable finite group function.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one of claims 1-5.

Images