Traditional Chinese medicine treatment instruction generation method and device, electronic equipment and storage medium

Abstract

The invention discloses a traditional Chinese medicine treatment instruction generation method and device, electronic equipment and a storage medium, and the generation method is used for the electronic equipment of a traditional Chinese medicine robot, and specifically comprises the steps: receiving disease description information inputted by a user in response to an information input request of the user; processing the disease description information based on a traditional Chinese medicine treatment scheme large model to obtain a traditional Chinese medicine treatment scheme; the traditional Chinese medicine treatment scheme is deeply processed, a traditional Chinese medicine treatment instruction is obtained, and the traditional Chinese medicine treatment instruction is used for controlling the traditional Chinese medicine robot so that the traditional Chinese medicine robot can treat a patient. The traditional Chinese medicine treatment scheme is generated based on the disease information input by the user, so that the traditional Chinese medicine robot can treat the patient in different places according to different persons and diseases based on the traditional Chinese medicine treatment scheme.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and more specifically, to a method, apparatus, electronic device, and storage medium for generating traditional Chinese medicine treatment instructions. Background Technology

[0002] With the development of modern science and technology, traditional Chinese medicine is moving towards digitalization and intelligentization, providing crucial support and supplementation for the modernization of TCM and addressing the shortage of medical resources. TCM has relatively effective treatment effects on common and chronic diseases. Among these, traditional TCM treatments such as massage, acupuncture, and moxibustion have shown good efficacy in treating certain ailments and discomforts. With the development of robotics technology, it is now possible to use TCM robots to perform TCM massage, acupuncture, and moxibustion treatments, effectively alleviating the treatment pressure on TCM physicians.

[0003] Before a TCM robot can treat a patient, a treatment plan needs to be input into it so that the robot can implement the treatment based on the steps provided in the plan. However, current treatment plans generally need to be provided by TCM doctors, whose workload remains very heavy. Although TCM robots can provide patients with a variety of fixed treatment plans to choose from, this cannot realize the individualized and symptom-specific treatment characteristics of TCM. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, electronic device, and storage medium for generating TCM treatment instructions, which enable TCM robots to provide individualized and symptom-specific TCM treatment instructions to patients.

[0005] To achieve the above objectives, the following solution is proposed:

[0006] A method for generating traditional Chinese medicine treatment instructions, applied to the electronic device of a traditional Chinese medicine robot, the method comprising the following steps:

[0007] Respond to the user's information input request and receive the symptom description information entered by the user;

[0008] The disease description information is processed based on a large model of TCM treatment plans to obtain TCM treatment plans;

[0009] The TCM treatment plan is processed in depth to obtain TCM treatment instructions, which are used to control the TCM robot so that the TCM robot can treat the patient.

[0010] Optionally, the step of processing the disease description information based on a large model of TCM treatment plans to obtain a TCM treatment plan includes the following steps:

[0011] Based on the processing of the disease description information using the aforementioned large-scale model of TCM treatment plans, treatment plans corresponding to various treatment methods are obtained.

[0012] In response to the user's request to select a treatment method, one or more of the treatment methods are selected from the multiple treatment options to obtain the traditional Chinese medicine treatment plan.

[0013] Optionally, the multiple treatment methods include one or more of massage therapy, acupuncture therapy, and moxibustion therapy.

[0014] Optionally, the step of performing in-depth processing on the TCM treatment plan to obtain TCM treatment instructions includes the following steps:

[0015] Character-type instructions are extracted from the TCM treatment plan using deep learning technology.

[0016] The character-type instruction is converted into a numerical-type instruction to obtain the traditional Chinese medicine treatment instruction.

[0017] Optionally, the character-type instruction includes one or more acupoint names, and also includes treatment parameters for the acupoint names, wherein the treatment parameters include some or all of the acupoint treatment sequence, treatment method, treatment time, and treatment mode.

[0018] Optionally, the generation method further includes the step of:

[0019] The model is trained based on a sample set of TCM treatment protocols to obtain a large model of the TCM treatment protocol.

[0020] Optionally, the step of training the model based on a sample set of traditional Chinese medicine treatment plans to obtain a large model of the traditional Chinese medicine treatment plan includes the following steps:

[0021] Obtain the TCM treatment plan sample set, which includes treatment plans recorded in ancient and modern books, medical records, and medical records;

[0022] The TCM treatment plan sample set was screened, cleaned, and format-standardized using deep learning algorithms to obtain a TCM treatment plan corpus.

[0023] We chose an open-source large language model as the pre-trained model.

[0024] The pre-trained model was fine-tuned using the LoRa fine-tuning algorithm based on the TCM treatment protocol corpus to obtain the fine-tuned model.

[0025] The fine-tuned model weights and the pre-trained model weights are merged to obtain the large model of the TCM treatment plan.

[0026] A device for generating traditional Chinese medicine treatment instructions, applied to the electronic equipment of a traditional Chinese medicine robot, the device comprising:

[0027] The information input module is configured to respond to the user's information input request and receive the symptom description information entered by the user;

[0028] The treatment plan decision module is configured to process the disease description information based on a large model of traditional Chinese medicine treatment plans to obtain a traditional Chinese medicine treatment plan.

[0029] The instruction generation module is configured to perform in-depth processing on the TCM treatment plan to obtain TCM treatment instructions, which are used to control the TCM robot so that the TCM robot can treat the patient.

[0030] Optionally, the instruction generation module includes:

[0031] The first generation unit is configured to extract character-type instructions from the traditional Chinese medicine treatment plan based on deep learning technology;

[0032] The second generation unit is configured to convert the character instruction into a numerical instruction to obtain the traditional Chinese medicine treatment instruction.

[0033] Optionally, the generating apparatus further includes:

[0034] The model training module is configured to train the model based on a sample set of traditional Chinese medicine treatment plans to obtain a large model of the traditional Chinese medicine treatment plan.

[0035] An electronic device for use in a traditional Chinese medicine treatment robot, the electronic device comprising at least one processor and a memory connected to the processor, wherein:

[0036] The memory is used to store computer programs or instructions;

[0037] The processor is used to execute the computer program or instructions to enable the electronic device to implement the method for generating TCM treatment instructions as described above.

[0038] A storage medium is applied to an electronic device, the storage medium carrying one or more computer programs that can be executed by the electronic device, thereby enabling the electronic device to implement the method for generating TCM treatment instructions as described above.

[0039] As can be seen from the above technical solution, this application discloses a method, apparatus, electronic device, and storage medium for generating Traditional Chinese Medicine (TCM) treatment instructions. The generation method is used in the electronic device of a TCM robot. Specifically, it involves responding to a user's information input request and receiving the user's input description of symptoms; processing the description of symptoms based on a large-scale TCM treatment plan model to obtain a TCM treatment plan; and performing deep processing on the TCM treatment plan to obtain TCM treatment instructions. These instructions are used to control the TCM robot, enabling it to treat the patient. Since the TCM treatment plan is generated based on the user-inputted symptoms, the TCM robot can provide individualized and symptom-specific treatment based on this plan. Furthermore, it eliminates the need for TCM physicians to provide treatment plans, thus further reducing their workload. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating a method for generating traditional Chinese medicine treatment instructions according to an embodiment of this application;

[0042] Figure 2 This is a flowchart illustrating a method for generating a large-scale model of a traditional Chinese medicine treatment plan according to an embodiment of this application.

[0043] Figure 3 This is a block diagram of a device for generating traditional Chinese medicine treatment instructions according to an embodiment of this application;

[0044] Figure 4 This is a block diagram of another device for generating traditional Chinese medicine treatment instructions according to an embodiment of this application;

[0045] Figure 5 This is a block diagram of another device for generating traditional Chinese medicine treatment instructions according to an embodiment of this application. Detailed Implementation

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0047] The solution in this application is actually applied to a traditional Chinese medicine robot, specifically a robot capable of performing massage, acupuncture, or moxibustion on patients. This robot is equipped with a controller that can control its movements based on specific treatment commands; this controller can be a computer, server, or embedded device. The solution in this application aims to generate traditional Chinese medicine treatment commands that can control this robot.

[0048] Figure 1 This is a flowchart illustrating a method for generating traditional Chinese medicine treatment instructions according to an embodiment of this application.

[0049] like Figure 1 As shown, the method for generating TCM treatment instructions provided in this embodiment is applied to an electronic device, which can be understood as a controller for a TCM treatment robot, such as a computer, server, or embedded device. The generation method includes the following steps:

[0050] S1. Receive the symptom description information input by the user.

[0051] In this application, based on prompts from a Traditional Chinese Medicine (TCM) robot, the system can receive symptom descriptions input by a user upon receiving an input request. Symptom descriptions refer to information input in natural language, describing both the external and internal aspects of the symptom. When a user inputs this symptom description, they can do so via character input, voice input, or wireless or wired input using other electronic devices.

[0052] S2. Process the symptom description information based on the large model of TCM treatment plan.

[0053] Specifically, the disease description information is input into a pre-trained large-scale TCM treatment model for processing, thereby enabling the large-scale model to output a TCM treatment plan. In particular, this application obtains the TCM treatment plan based on the following steps.

[0054] First, the description of the symptom is input into a large model of TCM treatment plans, which then outputs treatment plans corresponding to various treatment methods, namely massage therapy, acupuncture therapy, and moxibustion therapy, or one or more of these three treatment methods.

[0055] For example, the following three treatment methods were obtained respectively:

[0056] Method 1: Moxibustion: 1. Acupoints: Lower back pain point, Yaoyangguan, Shenshu, Guanyuan, Shenque, Baliao, Weizhong, Zusanli, Kunlun; 2. Procedure: Lower back pain point, Yaoyangguan, Shenshu, Guanyuan, Shenque; Baliao, lower back pain point, Weizhong, Shenque; Lower back pain point, Zusanli, Kunlun, Shenque; Choose one group of acupoints and apply gentle moxibustion for 4-5 minutes per acupoint;

[0057] The second method: Massage: 1. Acupoints: Yaoyangguan, Mingmen, Shenshu, Zhishi, Juliao, Huantiao, Chengfu, Weizhong; 2. Procedure: Press each acupoint 20 times;

[0058] The third method: Acupuncture: 1. Acupoints: Shenshu (BL23), Huantiao (GB30), Weizhong (BL40); 2. Procedure: Rotate and lift / insert at each acupoint for 1-2 minutes.

[0059] Then, in response to the user's request to select a treatment method, one or more methods are selected based on manual evaluation to obtain the TCM treatment plan. Generally, this TCM treatment plan includes only one treatment method, but depending on specific needs, it may include multiple treatment methods.

[0060] For example, the final TCM treatment plan could be selected as follows: "Massage: 1. Acupoints: Yaoyangguan, Mingmen, Shenshu, Zhishi, Juliao, Huantiao, Chengfu, Weizhong; 2. Procedure: Press each acupoint 20 times."

[0061] S3. Deeply process the TCM treatment plan to obtain TCM treatment instructions.

[0062] First, based on deep learning technology, the TCM treatment plan is segmented, and the acupoint names and corresponding treatment parameters such as the treatment sequence, treatment technique, treatment time, and treatment method are extracted to form character-based instructions for each acupoint. The character-based instructions related to each acupoint and the treatment sequence are recorded and saved. For example: "Yaoyangguan", "Mingmen", "Shenshu", "Zhishi", "Juliao", "Huantiao", "Chengfu", "Weizhong"; treatment method: massage; treatment technique: acupressure; treatment time: "20" times (each treatment session is 10 seconds by default).

[0063] Then, the character-type instructions are converted into numeric-type instructions, which are the TCM treatment instructions in this application. For example, channel: "518", "517", "417", "315", "206", "208", "328", "332"; treatment_method: "01"; therapeutic_technique: "11"; treatment_time: "200".

[0064] These numerical instructions are output to the TCM robot, enabling it to treat patients under the control of the TCM treatment system. For example, based on the treatment sequence of acupoints, the robot sequentially retrieves the corresponding numerical instructions for treatment methods, treatment times, and treatment techniques for each acupoint, assigning values ​​to the relevant parameters. The parameter corresponding to the acupoint name is `channel`, the parameter for the treatment method is `treatment_method`, the parameter for the treatment technique is `therapeutic_technique`, and the parameter for the treatment duration is `treatment_time`. The robot then executes the corresponding TCM treatment operations at each acupoint location on the patient until all treatments in the TCM treatment plan are completed.

[0065] As can be seen from the above technical solution, this embodiment provides a method for generating Traditional Chinese Medicine (TCM) treatment instructions. This method is used in the electronic device of a TCM robot. Specifically, it responds to a user's information input request and receives the user's input description of symptoms; processes the description of symptoms based on a large model of TCM treatment plans to obtain a TCM treatment plan; performs deep processing on the TCM treatment plan to obtain TCM treatment instructions, which are used to control the TCM robot to treat the patient. Since the TCM treatment plan is generated based on the user's input symptom information, the TCM robot can provide individualized and symptom-specific treatment based on this plan. Furthermore, it eliminates the need for TCM physicians to provide treatment plans, thus further saving medical resources.

[0066] In addition, in one specific embodiment of this application, the following technical solution is also included, which is used to generate the aforementioned large model of the traditional Chinese medicine treatment plan. The specific generation steps are as follows: Figure 2 As shown.

[0067] S201. Obtain the sample set of the TCM treatment plan.

[0068] This involves collecting various TCM treatment plans from ancient and modern books, medical records, and medical history, and using these as a sample set of TCM treatment plans, with the TCM treatment plans included as samples.

[0069] S202. Process the sample set of TCM treatment plans to obtain a TCM treatment plan corpus.

[0070] Data is filtered and cleaned using deep learning algorithms, and the cleaned data is standardized in format to form a corpus of TCM treatment plans, which facilitates subsequent model fine-tuning.

[0071] S203. Select an open-source large language model as the pre-trained model.

[0072] The open-source large model ChatGlm3-6b was selected as the pre-trained model.

[0073] S204. Based on the corpus of TCM treatment plans, the pre-trained model is fine-tuned to obtain the fine-tuned model.

[0074] The model was fine-tuned using the LoRa fine-tuning algorithm and a corpus of TCM treatment protocols to obtain the fine-tuned model.

[0075] S205. Merge the fine-tuned model and the pre-trained model.

[0076] The weight information of the fine-tuned model is combined with the weight information of the pre-trained model to obtain the large model of the TCM treatment plan.

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0078] Although the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous.

[0079] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0080] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer.

[0081] Figure 3 This is a block diagram of a device for generating traditional Chinese medicine treatment instructions according to an embodiment of this application.

[0082] like Figure 3 As shown, the TCM treatment instruction generation device provided in this embodiment is applied to an electronic device, which can be understood as a controller for a TCM treatment robot, such as a computer, server, or embedded device. The generation device includes an information input module 10, a treatment plan decision module 20, and an instruction generation module 30.

[0083] The information input module always receives the symptom description information entered by the user.

[0084] In this application, based on prompts from a Traditional Chinese Medicine (TCM) robot, the system can receive symptom description information input by the user upon receiving an input request. Symptom description information refers to information about a symptom input in a parametric or natural language manner, used to describe the external and internal aspects of the symptom. When the user inputs this symptom description information, it can be done via character input, voice input, or through other electronic devices via wireless or wired means.

[0085] The treatment plan decision module is used to process disease description information based on a large model of traditional Chinese medicine treatment plans.

[0086] Specifically, the disease description information is input into a pre-trained large-scale TCM treatment model for processing, thereby enabling the large-scale model to output a TCM treatment plan. In particular, this application obtains the TCM treatment plan based on the following steps.

[0087] First, the description of the symptom is input into a large model of TCM treatment plans, which then outputs treatment plans corresponding to various treatment methods, namely massage therapy, acupuncture therapy, and moxibustion therapy, or one or more of these three treatment methods.

[0088] For example, the following three treatment methods were obtained respectively:

[0089] Method 1: Moxibustion: 1. Acupoints: Lower back pain point, Yaoyangguan, Shenshu, Guanyuan, Shenque, Baliao, Weizhong, Zusanli, Kunlun; 2. Procedure: Lower back pain point, Yaoyangguan, Shenshu, Guanyuan, Shenque; Baliao, lower back pain point, Weizhong, Shenque; Lower back pain point, Zusanli, Kunlun, Shenque; Choose one group of acupoints and apply gentle moxibustion for 4-5 minutes per acupoint;

[0090] The second method: Massage: 1. Acupoints: Yaoyangguan, Mingmen, Shenshu, Zhishi, Juliao, Huantiao, Chengfu, Weizhong; 2. Procedure: Press each acupoint 20 times;

[0091] The third method: Acupuncture: 1. Acupoints: Shenshu (BL23), Huantiao (GB30), Weizhong (BL40); 2. Procedure: Rotate and lift / insert at each acupoint for 1-2 minutes.

[0092] Then, in response to the user's request to select a treatment method, one or more methods are selected based on manual evaluation to obtain the TCM treatment plan. Generally, this TCM treatment plan includes only one treatment method, but depending on specific needs, it may include multiple treatment methods.

[0093] For example, the final TCM treatment plan could be selected as follows: "Massage: 1. Acupoints: Yaoyangguan, Mingmen, Shenshu, Zhishi, Juliao, Huantiao, Chengfu, Weizhong; 2. Procedure: Press each acupoint 20 times."

[0094] The instruction generation module is used to perform in-depth processing of TCM treatment plans to obtain TCM treatment instructions. This module includes a first generation unit 31 and a second generation unit 32, such as... Figure 4 As shown.

[0095] The first generation unit is used to segment TCM treatment plans based on deep learning technology, extracting acupoint names and corresponding treatment parameters such as acupoint treatment sequence, treatment techniques, treatment time, and treatment method, forming character-based instructions for each acupoint. It also records and saves the character-based instructions related to each acupoint and the treatment sequence. For example: "Yaoyangguan", "Mingmen", "Shenshu", "Zhishi", "Juliao", "Huantiao", "Chengfu", "Weizhong"; treatment method: massage; treatment technique: point pressing; treatment time: "20" times (each treatment duration is 10 seconds by default).

[0096] The second generation unit is used to convert character-type instructions into numeric-type instructions, which are the TCM treatment instructions in this application. For example, channel: “518”, “517”, “417”, “315”, “206”, “208”, “328”, “332”; treatment_method: “01”; therapeutic_technique: “11”; treatment_time: “200”.

[0097] These numerical instructions are output to the TCM robot, enabling it to treat patients under the control of the TCM treatment system. For example, based on the treatment sequence of acupoints, the robot sequentially retrieves the corresponding numerical instructions for treatment methods, treatment times, and treatment techniques for each acupoint, assigning values ​​to the relevant parameters. The parameter corresponding to the acupoint name is `channel`, the parameter for the treatment method is `treatment_method`, the parameter for the treatment technique is `therapeutic_technique`, and the parameter for the treatment duration is `treatment_time`. The robot then executes the corresponding TCM treatment operations at each acupoint location on the patient until all treatments in the TCM treatment plan are completed.

[0098] As can be seen from the above technical solution, this embodiment provides a method for generating Traditional Chinese Medicine (TCM) treatment instructions. This method is used in the electronic device of a TCM robot. Specifically, it responds to a user's information input request and receives the user's description of symptoms; processes the description of symptoms based on a large model of TCM treatment plans to obtain a TCM treatment plan; performs deep processing on the TCM treatment plan to obtain TCM treatment instructions, which are used to control the TCM robot to treat the patient. Since the TCM treatment plan is generated based on the user's input of symptoms, the TCM robot can provide individualized and symptom-specific treatment based on this plan. Furthermore, it eliminates the need for TCM physicians to provide treatment plans, thus further alleviating the treatment burden on TCM physicians.

[0099] In addition, in one specific embodiment of this application, a model training module 40 is also included, such as... Figure 5 As shown, this module is used to generate the large model of the above-mentioned TCM treatment plan. The specific generation steps are as follows.

[0100] S201. Obtain the sample set of the TCM treatment plan.

[0101] This involves collecting various TCM treatment plans from ancient and modern books, medical records, and medical history, and using these as a sample set of TCM treatment plans, with the TCM treatment plans included as samples.

[0102] S202. Process the sample set of TCM treatment plans to obtain a TCM treatment plan corpus.

[0103] Data is filtered and cleaned using deep learning algorithms, and the cleaned data is standardized in format to form a corpus of TCM treatment plans, which facilitates subsequent model fine-tuning.

[0104] S203. Select an open-source large language model as the pre-trained model.

[0105] The open-source large model ChatGlm3-6b was selected as the pre-trained model.

[0106] S204. Based on the corpus of TCM treatment plans, the pre-model is fine-tuned to obtain the fine-tuned model.

[0107] The model was fine-tuned using the LoRa fine-tuning algorithm and a corpus of TCM treatment protocols to obtain the fine-tuned model.

[0108] S205. Merge the fine-tuned model and the pre-trained model.

[0109] The weight information of the fine-tuned model is combined with the weight information of the pre-trained model to obtain the large model of the TCM treatment plan.

[0110] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0111] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0112] This application also provides an embodiment of a computer-readable storage medium.

[0113] The aforementioned computer-readable storage medium is applied to an electronic device and carries one or more programs. When these programs are executed by the electronic device, the device responds to user input requests, receives symptom descriptions from the user, processes the symptom descriptions based on a large-scale TCM treatment model to obtain a TCM treatment plan, and performs in-depth processing on the TCM treatment plan to obtain TCM treatment instructions. These instructions are used to control the TCM robot, enabling it to treat the patient. Because this TCM treatment is generated based on user-inputted symptom information, the TCM robot can provide individualized and symptom-specific treatment based on the TCM treatment plan. Furthermore, since there is no longer a need for TCM physicians to provide treatment plans, the workload of TCM physicians can be further reduced.

[0114] It should be noted that the computer-readable medium described above in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0115] In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0116] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0117] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0118] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0119] The technical solution provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for generating traditional Chinese medicine treatment instructions, applied to the electronic equipment of a traditional Chinese medicine robot, characterized in that, The generation method includes the following steps: Respond to the user's information input request and receive the symptom description information entered by the user; The disease description information is processed based on a large model of TCM treatment plans to obtain TCM treatment plans; The TCM treatment plan is processed in depth to obtain TCM treatment instructions, which are used to control the TCM robot so that the TCM robot can treat the patient.

2. The generation method as described in claim 1, characterized in that, The process of processing the disease description information based on a large model of traditional Chinese medicine treatment plans to obtain a traditional Chinese medicine treatment plan includes the following steps: Based on the processing of the disease description information by the large model of the TCM treatment plan, multiple treatment methods are obtained, including one or more of massage therapy, acupuncture therapy and moxibustion therapy. In response to the user's request to select a treatment method, one or more of the multiple treatment methods are selected to obtain the traditional Chinese medicine treatment plan.

3. The generation method as described in claim 1, characterized in that, The TCM treatment plan is processed in depth to obtain TCM treatment instructions, including the following steps: Character-type instructions are extracted from the TCM treatment plan using deep learning technology. The character-type instruction is converted into a numerical-type instruction to obtain the traditional Chinese medicine treatment instruction.

4. The generation method as described in claim 3, characterized in that, The character-based instruction includes one or more acupoint names, and also includes treatment parameters for the acupoint names. The treatment parameters include some or all of the following: acupoint treatment sequence, treatment technique, treatment time, and treatment method.

5. The generation method according to any one of claims 1 to 4, characterized in that, The generation method further includes the following steps: The model is trained based on a sample set of TCM treatment protocols to obtain a large model of the TCM treatment protocol.

6. The generation method as described in claim 5, characterized in that, The process of training a model based on a sample set of traditional Chinese medicine (TCM) treatment protocols to obtain a large model of the TCM treatment protocols includes the following steps: Obtain the TCM treatment plan sample set, which includes treatment plans recorded in ancient and modern books, medical records, and medical records; The TCM treatment plan sample set was screened, cleaned, and format-standardized using deep learning algorithms to obtain a TCM treatment plan corpus. We chose an open-source large language model as the pre-trained model. The pre-trained model was fine-tuned using the LoRa fine-tuning algorithm based on the TCM treatment protocol corpus to obtain the fine-tuned model. The fine-tuned model weights and the pre-trained model weights are merged to obtain the large model of the TCM treatment plan.

7. A device for generating traditional Chinese medicine treatment instructions, applied to electronic devices of traditional Chinese medicine robots, characterized in that, The generating apparatus includes: The information input module is configured to respond to the user's information input request and receive the symptom description information entered by the user; The treatment plan decision module is configured to process the disease description information based on a large model of traditional Chinese medicine treatment plans to obtain a traditional Chinese medicine treatment plan. The instruction generation module is configured to perform in-depth processing on the TCM treatment plan to obtain TCM treatment instructions, which are used to control the TCM robot so that the TCM robot can treat the patient.

8. The generating apparatus as claimed in claim 7, characterized in that, The generating apparatus further includes: The model training module is configured to train the model based on a sample set of traditional Chinese medicine treatment plans to obtain a large model of the traditional Chinese medicine treatment plan.

9. An electronic device used in a traditional Chinese medicine treatment robot, characterized in that, The electronic device includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instructions to enable the electronic device to implement the method for generating traditional Chinese medicine treatment instructions as described in any one of claims 1 to 6.

10. A storage medium used in an electronic device, characterized in that, The storage medium carries one or more computer programs that can be executed by the electronic device, thereby enabling the electronic device to implement the method for generating TCM treatment instructions as described in any one of claims 1 to 6.

Images