A control method and system for a low-frequency therapy device for meridian flow injection
By building user knowledge graphs and intelligent analysis, the shortcomings of low-frequency therapy instruments in correlation analysis and intelligent regulation are solved, and more accurate physical therapy function output and user experience improvement are achieved.
Patent Information
- Application Number
- CN202410562705.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-08
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-05-08
AI Technical Summary
The existing low-frequency treatment instruments lack intelligence in the correlation analysis and intelligent regulation of acupoints and diseases, and cannot achieve the scientific nature of modern traditional Chinese medicine physiotherapy, and the user experience is poor.
By building the knowledge graph of the target user, using deep learning algorithms and association rules to generate association information, combining K nearest neighbor algorithms and LSTM networks, the classification and regression of low-frequency therapy instrument control characteristics are carried out, and matching physiotherapy recommendation solutions and weight data are generated to achieve Intelligent regulation of pulse strength and function.
It improves the intelligence level of low-frequency therapy instruments, enhances user experience, and achieves more accurate physiotherapy function information output and pulse intensity control, improving the treatment effect.
Smart Images

Figure CN118471458B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical equipment, and in particular to a control method and system of a meridian flow low-frequency therapeutic apparatus. Background Art
[0002] Low frequency therapy devices are medical devices that treat a variety of conditions by generating an electrical current at a specific frequency. These devices are often used in the field of physical therapy and rehabilitation and are designed to promote the body's natural healing process.
[0003] At present, low-frequency therapeutic devices often perform massages based on the concept of acupoints in traditional Chinese medicine. Although they have certain acupoint and disease information, there is no connection between them. They simply display pre-stored content and cannot play the role of intelligent correlation analysis and intelligent judgment, thus failing to achieve the characteristics of modern Chinese medicine that emphasizes scientific therapy. At the same time, traditional low-frequency therapeutic devices are not intelligent enough in regulating pulse intensity and function, resulting in mediocre user experience. To increase user experience and the intelligent development of low-frequency therapeutic devices, we propose a control method and system for Ziwu Liuzhu low-frequency therapeutic device. Summary of the invention
[0004] In view of the above problems existing in the existing low-frequency therapeutic apparatus, the present invention is proposed.
[0005] Therefore, one of the objects of the present invention is to provide a control method and system for a Ziwu Liuzhu low-frequency therapeutic instrument, which determines the physical therapy function information currently interacting with the target user after constructing a knowledge graph of the target user, outputs the physical therapy function information, and improves the intelligent control system of the pulse intensity and function of the low-frequency therapeutic instrument, thereby increasing the user experience and the intelligent development of the low-frequency therapeutic instrument.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In one aspect, the present invention provides a method for controlling a meridian flow low-frequency therapeutic apparatus, comprising:
[0008] Obtain the usage characteristics of the target user and construct a knowledge graph of the low-frequency therapeutic device, use a deep learning algorithm to extract target user information, generate original knowledge data, respond to the original knowledge data and use association rule mining to perform association analysis to generate associated information data, and construct a knowledge graph of the target user based on the associated information data;
[0009] After natural language processing of the target user's knowledge graph information, a K-nearest neighbor algorithm is used to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information;
[0010] According to the current target user matching information, a low-frequency therapeutic device expert database is established, and the LSTM long short-term memory network analysis is used to generate the corresponding physical therapy recommendation plan information. Based on the physical therapy recommendation plan information, the expert database is associated, and the weight data corresponding to the control characteristics of the low-frequency therapeutic device is generated after the association analysis. At the same time, according to the weight of the input value of the control characteristic of the low-frequency therapeutic device, the physical therapy function information currently interacting with the target user is determined, and output as the physical therapy function information output result of the low-frequency therapeutic device deep learning network;
[0011] In response to the output result of the physiotherapy function information, driving information matching the output result of the physiotherapy function information is generated, and waits for the target customer to start.
[0012] As a preferred solution of the present invention, the control characteristics of the low-frequency therapeutic device include: therapy function, therapy time, therapy site and therapy intensity.
[0013] As a preferred solution of the present invention, the following steps are used: based on the information of the physiotherapy recommendation scheme, an expert database is associated with the physiotherapy recommendation scheme, and weight data corresponding to the control features of the low-frequency therapeutic apparatus is generated after association analysis. Specifically, the associated control features in the expert database are extracted, and the Q-learning algorithm is used for enhanced learning to form an enhanced physiotherapy function information prediction model; the elements required for Q-Learning training are determined to include the state, action, reward, and interaction process between the target user and the low-frequency therapeutic apparatus of the control features;
[0014] Based on the physiotherapy function information prediction model, the sample data of the low-frequency therapy instrument expert database is divided, and the search strategy of the low-frequency therapy instrument expert database is updated.
[0015] As a preferred solution of the present invention, the knowledge graph of the target user is constructed according to the associated information data, specifically as follows:
[0016] The questionnaire and question-and-answer data of low-frequency treatment group customers are collected through the mobile terminal. The server obtains the questionnaire and question-and-answer data of low-frequency treatment group customers to form group customer information. After the original knowledge data of the target customer information is associated with the group customer information, the same type of physical therapy function association information data between the target customer and the group customer is generated;
[0017] In response to the information data of the same category of physiotherapy functions between the target customers and the group customers, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed; the questionnaire data of the group customers includes the physiotherapy intensity data of different categories of physiotherapy functions filled in by the questioned customers. After the classification, training and recognition of the control characteristics of the low-frequency therapeutic device, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed, as shown in the following formula:
[0018]
[0019] Among them, N(i) represents the physiotherapy intensity data of the i-th target customer of the same type of physiotherapy function; N(m) represents the physiotherapy intensity data filled in by the m-th customer of the same type of physiotherapy function; n is the serial number, P j is the physiotherapy intensity scoring function of the j-th category physiotherapy function, that is, the physiotherapy intensity scoring probability value of the j-th category physiotherapy function; Qi is the physiotherapy intensity scoring value of the same category physiotherapy function.
[0020] As a preferred solution of the present invention, the acquisition of the target user information includes: calculating the weight data of Qi through a weight formula; presetting a sample weight threshold, and eliminating features whose weight is less than the preset threshold according to the preset threshold, and storing them in the low-frequency therapeutic instrument expert library after updating; wherein the weight data of Qi calculated by the weight formula is calculated by the following formula, as follows:
[0021]
[0022] Among them, Wi is the weight data of the physiotherapy intensity score value of the same category of physiotherapy functions.
[0023] As a preferred solution of the present invention, the physiotherapy function information currently interacting with the target user is determined according to the weight of the control feature input value of the low-frequency therapeutic device. Specifically, the weight of the control feature input value of the low-frequency therapeutic device is calculated by the following formula:
[0024]
[0025] Among them, R i,j is the intensity value of the j-th category physiotherapy function of the i-th target customer, σ is the nonlinear activation function, C (i,j) It is the attribute value of the control feature associated with the j-th category of the physiotherapy function of the i-th target customer.
[0026] As a preferred solution of the present invention, the acquisition of the target user information includes: video, voice and / or text data; specifically, natural language processing includes machine translation, sentiment analysis and text generation; voice recognition is the conversion of audio data into text data, and video analysis includes action recognition or event prediction in the video.
[0027] In one aspect, the present invention provides a system for controlling a meridian flow low-frequency therapeutic apparatus, comprising:
[0028] An acquisition unit is used to acquire the usage characteristics of the target user and construct a knowledge graph of the low-frequency therapeutic device, use a deep learning algorithm to extract target user information, generate original knowledge data, and use association rule mining to perform association analysis in response to the original knowledge data to generate associated information data, and construct a knowledge graph of the target user based on the associated information data;
[0029] The processing unit performs natural language processing on the knowledge graph information of the target user, and then uses a K-nearest neighbor algorithm to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information;
[0030] The analysis unit establishes a low-frequency therapeutic device expert database according to the current target user matching information, uses LSTM long short-term memory network analysis to generate corresponding physical therapy recommendation information, associates the expert database based on the physical therapy recommendation information, generates weight data corresponding to the control characteristics of the low-frequency therapeutic device after association analysis, and determines the physical therapy function information currently interacting with the target user according to the weight of the input value of the control characteristics of the low-frequency therapeutic device, and outputs it as the physical therapy function information output result of the deep learning network of the low-frequency therapeutic device;
[0031] The output matching unit is used to respond to the output result of the physiotherapy function information, generate driving information that matches the output result of the physiotherapy function information, and wait for the target customer to start it.
[0032] On the other hand, the present invention provides a meridian flow low-frequency therapeutic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the low-frequency therapeutic device control method when executing the computer program. The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program implements the steps in the low-frequency therapeutic device control method when executed by the processor.
[0033] Beneficial effects of the present invention: After constructing a knowledge graph of the target user, the present invention determines the physical therapy function information currently interacting with the target user, outputs the physical therapy function information, and improves the intelligent control system of the pulse intensity and function of the low-frequency therapeutic device, thereby increasing the user experience and the intelligent development of the low-frequency therapeutic device. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 labor. Among them:
[0035] Figure 1 This is a flow chart of the low-frequency therapeutic apparatus control method in Example 1 of the present invention;
[0036] Figure 2 This is a schematic diagram of an application scenario of a low-frequency therapeutic device control system in Example 2 of the present invention;
[0037] Figure 3 This is a schematic diagram of the modular structure of the control system of the low-frequency therapeutic apparatus in Example 2 of the present invention;
[0038] Figure 4 This is a schematic diagram of the modular hardware structure of the low-frequency therapeutic apparatus in Example 2 of the present invention;
[0039] Figure 5 This is a schematic diagram of the hardware structure used in the low-frequency therapeutic device control program in Example 2 of the present invention.
[0040] Numbers in the figure: 10, acquisition unit; 20, processing unit; 30, analysis unit; 40, output matching unit; 100, MCU processor; 101, detection and adjustment module; 102, interaction module; 103, association analysis module. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.
[0042] Reference Figure 1 , is an embodiment of the present invention, which provides a method for controlling a meridian flow low-frequency therapeutic apparatus, comprising:
[0043] Step S101, obtaining the usage characteristics of the target user and constructing a knowledge graph of the low-frequency therapeutic device, using a deep learning algorithm to extract target user information, generating original knowledge data, and using association rule mining to perform association analysis in response to the original knowledge data to generate associated information data, and constructing a knowledge graph of the target user based on the associated information data;
[0044] Step S102, after natural language processing of the target user's knowledge graph information, a K-nearest neighbor algorithm is used to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information;
[0045] Step S103, based on the current target user matching information, establish a low-frequency therapeutic instrument expert database, use LSTM long short-term memory network analysis to generate corresponding physical therapy recommendation information, associate the expert database based on the physical therapy recommendation information, generate weight data corresponding to the control characteristics of the low-frequency therapeutic instrument after association analysis, and at the same time, determine the physical therapy function information currently interacting with the target user based on the weight of the input value of the control characteristic of the low-frequency therapeutic instrument, and output it as the physical therapy function information output result of the deep learning network of the low-frequency therapeutic instrument;
[0046] Step S104, in response to the output result of the physiotherapy function information, generating driving information matching the output result of the physiotherapy function information, and waiting for the target customer to start.
[0047] Among them, the control features of the low-frequency therapeutic device of this embodiment include: physical therapy function, physical therapy time, physical therapy part and physical therapy intensity.
[0048] This embodiment further associates the expert database with the information of the recommended physical therapy plan, generates the corresponding weight data of the control features of the low-frequency therapeutic instrument after the association analysis, specifically extracts the associated control features in the expert database, and uses the Q-learning algorithm to enhance the learning to form an enhanced physical therapy function information prediction model; determines the elements required for Q-Learning training, including the state, action, reward, and interaction process between the target user and the low-frequency therapeutic instrument of the control features; divides the sample data of the low-frequency therapeutic instrument expert database based on the physical therapy function information prediction model, and updates the search strategy of the low-frequency therapeutic instrument expert database. This can effectively improve the association analysis effect of machine learning on the control features in the expert database data.
[0049] In order to construct the big data support of the graph, this embodiment needs to emphasize that the knowledge graph of the target user can be constructed based on the associated information data, specifically as follows:
[0050] The questionnaire and question-and-answer data of low-frequency treatment group customers are collected through the mobile terminal. The server obtains the questionnaire and question-and-answer data of low-frequency treatment group customers to form group customer information. After the original knowledge data of the target customer information is associated with the group customer information, the same type of physical therapy function association information data between the target customer and the group customer is generated;
[0051] In response to the associated information data of the same category of physiotherapy functions between the target customers and the group customers, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed; the questionnaire data of the group customers includes the physiotherapy intensity data of different categories of physiotherapy functions filled in by the questioned customers. After the classification, training and identification of the control characteristics of the low-frequency therapeutic device, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed, as shown in the following formula:
[0052]
[0053] Among them, N(i) represents the physiotherapy intensity data of the i-th target customer of the same type of physiotherapy function; N(m) represents the physiotherapy intensity data filled in by the m-th customer of the same type of physiotherapy function; n is the serial number, P j is the physiotherapy intensity scoring function of the j-th category physiotherapy function, that is, the physiotherapy intensity scoring probability value of the j-th category physiotherapy function; Qi is the physiotherapy intensity scoring value of the same category physiotherapy function.
[0054] Through the equivalent scoring of therapy intensity of therapy functions of the same category, the intelligent control system of pulse intensity and function of low-frequency therapy device can be realized more accurately, thus reducing errors and improving user adaptability.
[0055] This embodiment further illustrates that the acquisition of target user information includes: calculating the weight data of Qi through a weight formula; presetting a sample weight threshold, and eliminating features whose weight is less than the preset threshold according to the preset threshold, and storing them in the low-frequency therapeutic instrument expert library after updating; wherein the weight data of Qi calculated by the weight formula is calculated by the following formula, as follows:
[0056]
[0057] Among them, Wi is the weight data of the physiotherapy intensity score value of the same category of physiotherapy functions.
[0058] According to the weight of the control feature input value of the low-frequency therapeutic device, the physical therapy function information currently interacting with the target user is determined. Specifically, the weight of the control feature input value of the low-frequency therapeutic device is calculated by the following formula:
[0059]
[0060] Among them, R i,j is the intensity value of the j-th category physiotherapy function of the i-th target customer, σ is the nonlinear activation function, C (i,j) It is the attribute value of the control feature associated with the j-th category of the physiotherapy function of the i-th target customer.
[0061] According to the weight of the input value of the control feature of the low-frequency therapeutic device, the physical therapy function information currently interacting with the target user is determined. That is, by filtering the associated control features by weight, the intensity value of the same category of physical therapy functions associated with the analysis can be further determined, thereby improving the output effect of the physical therapy function information interacting with the target user.
[0062] In addition, the acquisition of target user information in this embodiment includes: video, voice and / or text data; specifically, natural language processing includes machine translation, sentiment analysis and text generation; voice recognition is the conversion of audio data into text data, and video analysis includes action recognition or event prediction in the video.
[0063] Based on the above embodiments, it can be known that the present embodiment provides a method for controlling a Ziwu Liuzhu low-frequency therapeutic apparatus, which determines the physiotherapy function information currently interacting with the target user after constructing a knowledge graph of the target user, outputs the physiotherapy function information, and can respond to the associated information data of the same category of physiotherapy functions between the target customer and the group customer, and perform physiotherapy intensity equivalent scoring of the same category of physiotherapy functions. By utilizing the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions, the intelligent control system of the pulse intensity and function of the low-frequency therapeutic apparatus can be more accurately realized. At the same time, by weight screening and associating the control features, the intensity value of the physiotherapy function of the same category that is associated and analyzed can be further determined, thereby improving the output effect of the physiotherapy function information interacting with the target user, thereby increasing the user experience and facilitating the intelligent development of the low-frequency therapeutic apparatus.
[0064] Example 2
[0065] Reference Figure 2-Figure 5 , is an embodiment of the present invention, which provides a low-frequency therapeutic apparatus control system, including:
[0066] The acquisition unit 10 is used to acquire the usage characteristics of the target user and construct a knowledge graph of the low-frequency therapeutic device, use a deep learning algorithm to extract the target user information, generate original knowledge data, and use association rule mining to perform association analysis in response to the original knowledge data to generate associated information data, and construct a knowledge graph of the target user based on the associated information data;
[0067] The processing unit 20 performs natural language processing on the knowledge graph information of the target user, and then uses the K nearest neighbor algorithm to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information;
[0068] The analysis unit 30 establishes a low-frequency therapeutic apparatus expert database according to the current target user matching information, uses the LSTM long short-term memory network to generate corresponding physical therapy recommendation information, associates the expert database based on the physical therapy recommendation information, generates weight data corresponding to the control features of the low-frequency therapeutic apparatus after association analysis, and determines the physical therapy function information currently interacting with the target user according to the weight of the input value of the control feature of the low-frequency therapeutic apparatus, and outputs it as the physical therapy function information output result of the deep learning network of the low-frequency therapeutic apparatus;
[0069] The output matching unit 40 is used to respond to the output result of the physiotherapy function information, generate driving information that matches the output result of the physiotherapy function information, and wait for the target customer to start it.
[0070] like Figure 4As shown, it is a schematic diagram of the modular functional hardware structure of the low-frequency therapeutic apparatus according to the embodiment of the present application. It should be emphasized that the system of the low-frequency therapeutic apparatus control method of the present embodiment is also applied to the corresponding low-frequency therapeutic apparatus equipment, and the low-frequency therapeutic apparatus equipment includes:
[0071] The MCU processor 100 is used to receive and process the signal fed back by the composite waveform through the conducting component and send out a control signal;
[0072] The detection and adjustment module 101 is used to detect the output composite waveform and piezoelectric drive waveform in real time and adjust the piezoelectric drive waveform;
[0073] An interaction module 102, used to realize the interaction between the target user and the low-frequency therapeutic device;
[0074] The association analysis module 103 is used to establish a connection between the target user and the low-frequency therapeutic instrument expert library of the server, and to determine the physical therapy function information currently interacting with the target user, and output it to the MCU processor as the physical therapy function information output result of the low-frequency therapeutic instrument deep learning network.
[0075] Figure 5 This is a schematic diagram of the hardware structure used in the low-frequency therapeutic device control program applied to the electronic device according to the embodiment of the present application.
[0076] The electronic device of the low-frequency therapeutic device may include a processor 41 and a memory 42 storing computer program instructions. It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device of the low-frequency therapeutic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0077] Specifically, the processor 41 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0078] Among them, the memory 42 may include a large capacity memory for data or instructions. For example, but not limitation, the memory 42 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (OPENCV), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 42 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 42 may be inside or outside the data processing device. In a specific embodiment, the memory 42 is a non-volatile memory. In a specific embodiment, the memory 42 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (ErasableProgrammable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically ErasableProgrammable Read-Only Memory, EEPROM for short), an electrically alterable ROM (ElectricallyAlterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.
[0079] The memory 42 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 41; the processor 41 implements the processing method of the electronic device in the above embodiment by reading and executing the computer program instructions stored in the memory 42.
[0080] In some of the embodiments, the electronic device may further include a communication interface 43 and a bus 40. Figure 4 As shown, the processor 41, the memory 42, and the communication interface 43 are connected via a bus 40 and communicate with each other.
[0081] The steps of operating the low-frequency therapeutic device of this embodiment are as follows:
[0082] Step 1.1, after turning on the power and self-checking, remove the low-frequency treatment head; the power is turned on, the treatment starts, the interactive module 102 is started, and the screen display panel of the low-frequency treatment device displays the treatment content to be input by the target user.
[0083] Step 1.2, the target user provides the current physical therapy information to the low-frequency therapeutic apparatus through video, voice or / and text data, that is, the interactive module 102 of the low-frequency therapeutic apparatus obtains the current physical therapy information of the target user through video, voice or / and text data, generates original knowledge data, generates associated information data through the association analysis module 103, and constructs the knowledge graph of the target user according to the associated information data; classifies and regresses the control features of the low-frequency therapeutic apparatus after natural language processing of the knowledge graph information of the target user, and at the same time associates with the low-frequency therapeutic apparatus expert library to determine the physical therapy function information currently interacting with the target user, and outputs it as the physical therapy function information output result of the deep learning network of the low-frequency therapeutic apparatus; generates driving information matching the output result of the physical therapy function information, and waits for the target customer to start;
[0084] Physical therapy functions include but are not limited to physical therapy using soreness treatment; physical therapy using pain treatment; physical therapy using massage methods.
[0085] Step 1.3, adjust the strength of the physical therapy function through the interactive module 102 of the low-frequency therapeutic device, and select the standard time of appropriate intensity treatment: 10-15 minutes per part each time, 1-2 times a day; the user shall make it comfortable.
[0086] Step 1.4: When the treatment is finished, turn off the power.
[0087] Further explanation, the working principle of the low-frequency therapeutic instrument is introduced. According to the acupuncture law of "Ziwu Liuzhu" time, a corresponding complete computer model is established between the acupoint data and the disease data, providing a variety of dialectical clinical symptoms for users to choose, and combining the acupoint prescriptions of the disease to provide users with the best time and treatment plan for treatment. The low-frequency therapeutic instrument can instantaneously concentrate and diffuse the energy of the power spectrum according to certain modulation characteristics, and very realistically simulate the actual feeling of real people beating back, knocking, massaging, pushing, acupuncture and cupping. If it acts on the meridian acupoints, it can effectively treat and relieve various diseases. Regular and planned use of low-frequency therapeutic instruments can be placed on many chronic diseases and even stubborn diseases. Low-frequency therapeutic instruments can also be used for massage after work and during work to relax the mind and body. According to the ultra-low frequency effect formed by the feeling of twisting the needle to get qi in acupuncture, combined with pulses with high energy distribution, according to the spectrum of various feelings that can be formed by human body stimulation, the distribution is simulated for low-frequency modulation, thereby stimulating the reflection effect of the meridians and acupoints to form a closed-loop feeling to achieve a real treatment method and effect.
[0088] In summary, the low-frequency therapeutic instrument of this embodiment, through the combination of software and hardware, builds functions based on the existing knowledge graph, and integrates the expert database content in traditional Chinese medicine physiotherapy. Specifically, it can be established after subsequent deep learning between the acupoint data and the disease data according to the "Ziwu Liuzhu" time acupuncture law, and determine the physiotherapy function information currently interacting with the target user, and output it as the physiotherapy function information output result of the deep learning network of the low-frequency therapeutic instrument, thereby providing a variety of dialectical clinical symptoms for users to choose from. At the same time, combined with the acupoint prescription of the disease, the intelligent control system of the pulse intensity and function of the low-frequency therapeutic instrument is improved, thereby increasing the user experience and the intelligent development of the low-frequency therapeutic instrument, thereby providing users with the best time and treatment plan for treatment.
[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.
[0090] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0091] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.
[0092] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for controlling a meridian flow low-frequency therapeutic apparatus, characterized in that: include: Obtain the usage characteristics of the target user and construct a knowledge graph of the low-frequency therapeutic device. Use a deep learning algorithm to extract target user information and generate original knowledge data. After responding to the original knowledge data, use association rule mining to perform association analysis to generate associated information data. Construct the knowledge graph of the target user based on the associated information data. Specifically, The questionnaire and question-and-answer data of low-frequency treatment group customers are collected through the mobile terminal. The server obtains the questionnaire and question-and-answer data of low-frequency treatment group customers to form group customer information. After the original knowledge data of the target customer information is associated with the group customer information, the same type of physical therapy function association information data between the target customer and the group customer is generated; In response to the information data of the same category of physiotherapy functions between the target customers and the group customers, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed; the questionnaire data of the group customers includes the physiotherapy intensity data of different categories of physiotherapy functions filled in by the questioned customers. After the classification, training and recognition of the control characteristics of the low-frequency therapeutic device, the physiotherapy intensity equivalent scoring of the same category of physiotherapy functions is performed, as shown in the following formula: Among them, N(i) represents the physiotherapy intensity data of the i-th target customer of the same type of physiotherapy function; N(m) represents the physiotherapy intensity data filled in by the m-th customer of the same type of physiotherapy function; n is the serial number, P j is the physiotherapy intensity scoring function of the j-th category physiotherapy function, that is, the physiotherapy intensity scoring probability value of the j-th category physiotherapy function; Qi is the physiotherapy intensity scoring value of the same category physiotherapy function; The weight data of Qi is calculated by the weight formula; the sample weight threshold is preset, and the features with weights less than the preset threshold are eliminated, and are updated and stored in the low-frequency therapeutic device expert database; the weight data of Qi calculated by the weight formula is calculated by the following formula, as follows: Among them, Wi is the weight data of the physiotherapy intensity score value of the same type of physiotherapy function; After natural language processing of the target user's knowledge graph information, a K-nearest neighbor algorithm is used to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information; According to the current target user matching information, a low-frequency therapeutic instrument expert database is established, and the LSTM long short-term memory network analysis is used to generate corresponding physical therapy recommendation plan information. Based on the physical therapy recommendation plan information, the low-frequency therapeutic instrument expert database is associated, and the corresponding weight data of the control characteristics of the low-frequency therapeutic instrument are generated after the association analysis. At the same time, according to the weight of the control characteristic input value of the low-frequency therapeutic instrument, the physical therapy function information currently interacting with the target user is determined, and output as the physical therapy function information output result of the low-frequency therapeutic instrument deep learning network. Specifically, the weight of the control characteristic input value of the low-frequency therapeutic instrument is calculated by the following formula: Among them, R i,j is the intensity value of the j-th category physiotherapy function of the i-th target customer, σ is the nonlinear activation function, C (i,j) is the attribute value of the control feature associated with the j-th category of the physiotherapy function of the i-th target customer; In response to the output result of the physiotherapy function information, driving information matching the output result of the physiotherapy function information is generated, and waits for the target customer to start.
2. A method for controlling a meridian flow low-frequency therapeutic apparatus as claimed in claim 1, characterized in that: The control features of the low-frequency therapeutic device include: therapy function, therapy time, therapy part and therapy intensity.
3. A method for controlling a meridian flow low-frequency therapeutic apparatus as claimed in claim 1, characterized in that: Based on the information of the physiotherapy recommendation scheme, the low-frequency therapeutic instrument expert database is associated, and the weight data corresponding to the control features of the low-frequency therapeutic instrument are generated after the association analysis. Specifically, the associated control features in the low-frequency therapeutic instrument expert database are extracted, and the Q-learning algorithm is used for enhanced learning to form an enhanced physiotherapy function information prediction model; the elements required for Q-Learning training are determined, including the state, action, reward, and interaction process between the target user and the low-frequency therapeutic instrument of the control features; Based on the physiotherapy function information prediction model, the sample data of the low-frequency therapy instrument expert database is divided, and the search strategy of the low-frequency therapy instrument expert database is updated.
4. A method for controlling a meridian flow low-frequency therapeutic apparatus as claimed in claim 1, characterized in that: The acquisition of the target user information includes: video, voice and / or text data; specifically, natural language processing includes machine translation, sentiment analysis and text generation; voice recognition is the conversion of audio data into text data, and video analysis includes action recognition or event prediction in the video.
5. The system of the method for controlling the meridian flow low-frequency therapeutic apparatus according to claim 1, characterized in that: include: An acquisition unit is used to acquire the usage characteristics of the target user and construct a knowledge graph of the low-frequency therapeutic device, use a deep learning algorithm to extract target user information, generate original knowledge data, and use association rule mining to perform association analysis in response to the original knowledge data to generate associated information data, and construct a knowledge graph of the target user based on the associated information data; The processing unit performs natural language processing on the knowledge graph information of the target user, and then uses a K-nearest neighbor algorithm to classify and regress the control features of the low-frequency therapeutic device, that is, to classify, train and identify the control features of the low-frequency therapeutic device, and generate target user matching information; The analysis unit establishes a low-frequency therapeutic instrument expert database according to the current target user matching information, uses LSTM long short-term memory network analysis to generate corresponding physical therapy recommendation information, associates the low-frequency therapeutic instrument expert database based on the physical therapy recommendation information, generates weight data corresponding to the control characteristics of the low-frequency therapeutic instrument after association analysis, and determines the physical therapy function information currently interacting with the target user according to the weight of the input value of the control characteristics of the low-frequency therapeutic instrument, and outputs it as the physical therapy function information output result of the deep learning network of the low-frequency therapeutic instrument; The output matching unit is used to respond to the output result of the physiotherapy function information, generate driving information that matches the output result of the physiotherapy function information, and wait for the target customer to start it.
6. A meridian flow low frequency therapeutic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the method for controlling the meridian flow low-frequency therapeutic apparatus as described in any one of claims 1 to 4 are implemented.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for controlling the meridian flow low-frequency therapeutic apparatus as described in any one of claims 1 to 4 are implemented.
Citation Information
Patent Citations
Diagnosis and treatment suggestion scoring system based on csco guide
CN113506625A
