A machine learning-based pain analysis and treatment regimen generation method and system

Abstract

The application provides a pain analysis and treatment scheme generation method and system based on machine learning, which obtains pain information of a target patient, extracts feature information in the pain information, and enters the feature information into a feature information table; identifies a pain type of the target patient based on the feature information table; generates inquiry content based on the pain type; receives reply content of the target patient to the inquiry content; generates a pain treatment scheme of the target patient based on the reply content; obtains the feature information table by extracting pain information and mental and psychological evaluation results of the target patient, determines the pain type of the target patient according to the feature information table, and inquires the target patient according to the pain type and the mental and psychological state to supplement relevant information, and then generates a treatment scheme for the pain of the target patient, improves the accuracy of pain type identification based on the feature information table, and thus a more suitable treatment scheme can be recommended for the pain type of the target patient.

Description

Technical Field

[0001] This application relates to the field of pain analysis technology, specifically to a method and system for pain analysis and treatment plan generation based on machine learning. Background Technology

[0002] The natural decline of bodily functions, the high incidence of chronic diseases, and long-term sub-health lifestyles have made pain extremely common. More and more people suffer from chronic pain, with conditions such as arthritis, cervical spondylosis, lumbar disc herniation, and osteoporotic pain becoming common problems that disrupt their daily lives. This pain not only severely affects physical activity and limits daily movement, leading to a decline in self-care ability, but also has a significant negative impact on their mental health. Anxiety, depression, and other emotional problems are frequently seen among pain sufferers, seriously reducing their quality of life and making it difficult for them to fully enjoy the pleasures of life.

[0003] With the development of medical technology and the increasing awareness of personal health management, pain management has become an important research direction in the medical field. However, current pain management mainly relies on traditional assessment methods, such as medical question-and-answer systems based on large language models. While these methods offer broad knowledge, data in the specific area of ​​pain may be relatively scarce, leading to inaccuracies in pain identification and thus reducing the precision of pain management. Therefore, a solution is needed that can accurately identify the type of pain a patient experiences and provide symptom relief. Summary of the Invention

[0004] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method and system for pain analysis and treatment plan generation based on machine learning.

[0005] According to one aspect of this application, a method for pain analysis and treatment plan generation based on machine learning is provided, comprising: acquiring pain information of a target patient; wherein the pain information includes text information or voice information; extracting feature information from the pain information and recording the feature information into a feature information table; wherein the feature information table includes a header of pain-related information and a corresponding table, and the table stores feature information corresponding to the header; identifying the pain type of the target patient based on the feature information table; generating inquiry content based on the pain type; wherein the inquiry content includes the table content that is missing in the feature information table; receiving the response content of the target patient to the inquiry content; and generating a pain treatment plan for the target patient based on the response content.

[0006] In one embodiment, extracting feature information from the pain information includes: extracting keywords and quantification words from the text information; wherein the keywords represent words corresponding to the table header, and the quantification words represent words of numerical value or degree; and determining the feature information based on the keywords and the quantification words.

[0007] In one embodiment, determining the feature information based on the keyword and the quantification word includes: dividing the text information into multiple fields based on the keyword; wherein each field contains at least one keyword; searching for quantification words in the field where the keyword is located, and matching the keyword and quantification words in the same field to obtain a set of feature information.

[0008] In one embodiment, extracting feature information from the pain information includes: recognizing the speech information to obtain semantic information; and extracting feature information from the semantic information.

[0009] In one embodiment, identifying the pain type of the target patient based on the feature information table includes: determining the pain type of the target patient based on the historical feature information table of the target patient.

[0010] In one embodiment, determining the pain type of the target patient based on the historical feature information table of the target patient includes: comparing the current feature information table and the historical feature information table of the target patient, and filtering out the target feature information table from the historical feature information table; wherein, the non-empty table in the current feature information table includes the non-empty table in the target feature information table; and determining the pain type of the target patient based on the pain type corresponding to the target feature information table.

[0011] In one embodiment, generating a pain treatment plan for the target patient based on the response content includes: supplementing the feature information table based on the response content; obtaining a feature curve for the target patient based on the supplemented feature information table and the target patient's historical feature information table; wherein the feature curve represents the changing pattern of the target patient's feature information; and generating a pain treatment plan for the target patient based on the target patient's feature curve.

[0012] According to another aspect of this application, a pain analysis and treatment plan generation system based on machine learning is provided, comprising: an information acquisition module for acquiring pain information of a target patient; wherein the pain information includes text information or voice information; a feature extraction module for extracting feature information from the pain information and recording the feature information into a feature information table; wherein the feature information table includes a header of pain-related information and a corresponding table, and the table stores feature information corresponding to the header; a type identification module for identifying the pain type of the target patient based on the feature information table; a query generation module for generating query content based on the pain type; wherein the query content includes the table content that is missing in the feature information table; a response receiving module for receiving the response content of the target patient to the query content; and a plan generation module for generating a pain treatment plan for the target patient based on the response content.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing any of the methods described above.

[0014] According to another aspect of this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform any of the methods described above.

[0015] This application provides a method and system for pain analysis and treatment plan generation based on machine learning. The method involves: acquiring pain information from a target patient, including text or voice information; extracting feature information from the pain information and recording it in a feature information table; the feature information table containing headers and corresponding tables for pain-related information, with each table storing the feature information corresponding to its header; identifying the target patient's pain type based on the feature information table; generating inquiry content based on the pain type, including any missing table content from the feature information table; receiving the target patient's response to the inquiry content; and generating a pain treatment plan for the target patient based on the response content. By extracting the target patient's pain information to obtain the feature information table, determining the target patient's pain type based on the feature information table, and inquiring about the target patient based on the pain type to supplement relevant information, a treatment plan for the target patient's pain is generated. This method improves the accuracy of pain type identification by acquiring the feature information table, thereby more accurately recommending a more suitable treatment plan based on the target patient's pain type. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 This is a flowchart illustrating a machine learning-based pain analysis and treatment plan generation method provided in an exemplary embodiment of this application.

[0018] Figure 2 This is a schematic diagram of the structure of a machine learning-based pain analysis and treatment plan generation system provided in an exemplary embodiment of this application.

[0019] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0020] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0021] Figure 1 This is a flowchart illustrating a machine learning-based pain analysis and treatment plan generation method provided in an exemplary embodiment of this application. Figure 1 As shown, the machine learning-based pain analysis and treatment plan generation method includes the following steps:

[0022] Step 110: Obtain pain information from the target patient.

[0023] The pain information includes text or voice information. This application uses a platform (APP) and corresponding devices (such as interactive robots) to interact with the target patient, thereby acquiring the target patient's pain information in real time during the interaction process, in order to understand the target patient's condition information.

[0024] Step 120: Extract the feature information from the pain information and enter the feature information into the feature information table.

[0025] The feature information table includes a header and corresponding tables containing pain-related information. The tables store the feature information corresponding to the headers. This application uses a model obtained through intelligent learning to automatically extract feature information from the pain information of the target patient and fills the extracted feature information into the corresponding feature information tables. This process collects the patient's symptom feature information, thereby providing an accurate basis for subsequently determining the type of pain.

[0026] Step 130: Identify the pain type of the target patient based on the feature information table.

[0027] This application identifies the pain type of the target patient by integrating various feature information based on a feature information table. Preferably, if the pain type cannot be accurately identified based on the current feature information table, the feature information of the target patient can be continuously obtained through interactive methods until the pain type can be identified.

[0028] Step 140: Generate inquiry content based on pain type.

[0029] The inquiry content includes any missing information in the feature information table. After determining the pain type of the target patient, this application generates more targeted inquiry content based on the pain type. For example, when the pain type is determined to be a headache, the corresponding inquiry content is generated: "Is the pain located in the entire head or only a part of it?" By asking the target patient targeted questions, the cause of the target patient's pain can be accurately determined and the corresponding treatment plan (relief plan or treatment suggestion) can be obtained.

[0030] Step 150: Receive the target patient's response to the inquiry.

[0031] After generating and sending the inquiry, this application receives the target patient's response (which can be text or voice). Upon receiving the response, it generates a personalized summary for the target patient (i.e., a summary of the current symptom) and displays it to the target patient. After the target patient verifies that it is correct, they click to confirm. After the target patient confirms, the personalized summary is sent to the doctor's end for diagnosis. At the same time, a reward (such as points, face-to-face consultation qualification, etc.) is sent to the user terminal (mobile phone, computer, etc.) used by the target patient. Through interactive means, the application further understands the cause of the target patient's pain and provides the summary to the doctor for diagnosis in real time, thereby improving the efficiency of diagnosis.

[0032] Step 160: Based on the response content, generate a pain treatment plan for the target patient.

[0033] Based on the interactive content, the system automatically generates pain treatment plans for the target patient. For example, it may suggest that the patient press corresponding acupoints to relieve pain, or suggest that the target patient go to the hospital for further examination (at this time, it can recommend the nearest suitable hospital, and can also recommend the registration department for the target patient based on the information obtained). At the same time, the pain treatment plan is sent to the doctor's terminal for professional review by a professional doctor. After the doctor confirms it, a specialist medical record is automatically generated, and personalized specialist science popularization videos are automatically pushed to the user's terminal to improve the patient's self-management ability.

[0034] This application provides a machine learning-based method for pain analysis and treatment plan generation. The method involves acquiring pain information from a target patient, including text or voice information; extracting feature information from the pain information and recording it in a feature information table; the feature information table containing headers and corresponding tables for pain-related information, with each table storing the feature information corresponding to its header; identifying the target patient's pain type based on the feature information table; generating inquiry content based on the pain type; receiving responses from the target patient to the inquiry content; and generating a pain treatment plan for the target patient based on the responses. By extracting the target patient's pain information to obtain the feature information table, determining the target patient's pain type based on the feature information table, and inquiring about the target patient based on the pain type to supplement relevant information, a treatment plan for the target patient's pain is generated. This method improves the accuracy of pain type identification based on the feature information table, thereby more accurately recommending a more suitable treatment plan for the target patient's pain type.

[0035] In one embodiment, step 120 can be implemented by: extracting keywords and quantification words from the text information; wherein, keywords represent words corresponding to the table header, and quantification words represent words of numerical value or degree; and determining feature information based on keywords and quantification words.

[0036] After receiving text information input by the target patient, this application extracts keywords (such as headache, indicating the location of pain) and quantifiers (such as descriptions of time, such as pain starting upon waking up in the morning) from the text information. Based on the extracted keywords and quantifiers, the application determines the target patient's characteristic information to generate structured data that is then entered into a feature information table. For example, based on the keyword "headache," the location of the pain can be determined as the head; based on the quantifier "pain starting upon waking up in the morning," the onset time of the pain can be inferred (this can be determined by combining the target patient's usual wake-up time; if there is no usual wake-up time, a time range is set).

[0037] In one embodiment, step 120 can be implemented as follows: dividing text information into multiple fields based on keywords; wherein each field contains at least one keyword; searching for quantified words in the field where the keyword is located, and matching the keywords and quantified words in the same field to obtain a set of feature information.

[0038] Since textual descriptions often exhibit a certain degree of continuity and correlation, this application can divide textual information into multiple fields based on keywords. Each field contains at least one keyword, meaning each field can identify at least one feature. Quantitative terms are searched within the divided fields to obtain a set of feature information matching the keywords and quantitative terms, thus leading to better feature information retrieval. For example, a field containing "pain duration 2 hours" has the keyword "pain duration" and the quantitative term "2 hours," resulting in the pain duration (header) and the corresponding numerical value (table value).

[0039] In one embodiment, step 120 can be implemented by: recognizing speech information to obtain semantic information; and extracting feature information from the semantic information.

[0040] After obtaining the voice information of the target patient, this application obtains semantic information (i.e. text information) through speech recognition. After obtaining the semantic information, it further processes the semantic information based on the above-mentioned processing method for text information to obtain feature information.

[0041] In one embodiment, step 130 can be implemented by determining the pain type of the target patient based on the target patient's historical characteristic information table.

[0042] This application stores a historical characteristic information table of the target patient. When the target patient experiences pain symptoms again, the pain type of the target patient can be determined comprehensively based on the historical characteristic information table, thereby enabling a more accurate determination of the target patient's pain type.

[0043] In one embodiment, step 130 can be implemented as follows: comparing the current feature information table and the historical feature information table of the target patient, and filtering out the target feature information table from the historical feature information table; wherein, the non-empty tables in the current feature information table include the non-empty tables in the target feature information table; and determining the pain type of the target patient based on the pain type corresponding to the target feature information table.

[0044] This application determines the pain type of a target patient by comparing the current feature information table and the historical feature information table. Specifically, this application selects the historical feature information table, in which all non-empty tables are included in the current feature information table, as the target feature information table. That is, it selects the feature information table in which all relevant feature information in the historical feature information table exists in the current feature information table, and determines the pain type of the target patient based on the pain type in the target feature information table.

[0045] In one embodiment, step 160 can be implemented as follows: based on the response content, supplement the feature information table; based on the supplemented feature information table and the target patient's historical feature information table, obtain the target patient's feature curve; wherein, the feature curve represents the changing pattern of the target patient's feature information; based on the target patient's feature curve, generate a pain treatment plan for the target patient.

[0046] This application supplements the feature information table interactively, and based on the supplemented feature information table and the historical feature information table, obtains the feature curve of the target patient. The feature curve can be the overall change pattern of the target patient (frequency of pain occurrence) or the change pattern of a certain feature (such as pain intensity, duration, etc.). A pain treatment plan for the target patient is generated based on the feature curve. For example, if the frequency of pain occurrence of the target patient decreases based on the previous pain treatment plan, it indicates that the given pain treatment plan is effective and can be maintained. If the frequency of pain occurrence of the target patient increases or remains unchanged based on the previous pain treatment plan, it indicates that the given pain treatment plan is ineffective or has unsatisfactory results, and the pain treatment plan can be changed.

[0047] Optionally, this application can also record the target patient's pain information to form a pain log, and combine it with other data of the target patient to comprehensively assess the relationship between the target patient's pain type and psychological factors. By combining pain type and psychological factors, a more comprehensive and accurate treatment plan can be generated. For example, if the target patient's chief complaint or analysis indicates knee pain, but the target patient's daily step count exceeds 20,000 steps, it is determined that the target patient has psychological anxiety, and more psychological treatment should be given while reducing physical pain treatment.

[0048] Optionally, this application can also obtain feedback data from the target patient through voice or text greetings, thereby obtaining complete data of the target patient during the treatment process, and recording and analyzing the data for subsequent review and overall analysis of the treatment process; preferably, this application can adjust the greeting cycle based on the severity or duration of the target patient's condition during the greeting process, for example, greetings are frequent at the beginning of treatment or when the condition is severe (e.g., once every one or two days), while the greeting frequency is reduced in the later stages of treatment or when the condition improves (e.g., once a week).

[0049] Optionally, in the process of obtaining pain information of the target patient, this application not only obtains information related to the location of pain, but also obtains other information associated with the location of pain, such as the impact of other diseases of the target patient on the location of pain, thereby generating a more comprehensive treatment plan by integrating the overall information of the target patient.

[0050] Optionally, this application can also generate popular science knowledge on treatment plans for treating or relieving pain (in the form of voice, text, video, etc.), and push the corresponding popular science knowledge on treatment plans to the target patients based on their pain information, so as to improve convenience and accuracy and avoid delays in treatment caused by non-professional knowledge searched by the target patients themselves.

[0051] Figure 2 This is a schematic diagram of the structure of a machine learning-based pain analysis and treatment plan generation system provided in an exemplary embodiment of this application. Figure 2 As shown, the machine learning-based pain analysis and treatment plan generation system 20 includes: an information acquisition module 21 for acquiring pain information of the target patient, wherein the pain information includes text information or voice information; a feature extraction module 22 for extracting feature information from the pain information and recording the feature information into a feature information table, wherein the feature information table contains a header of pain-related information and a corresponding table, and the table stores the feature information corresponding to the header; a type recognition module 23 for identifying the pain type of the target patient based on the feature information table; a query generation module 24 for generating query content based on the pain type, wherein the query content includes the table content missing in the feature information table; a response receiving module 25 for receiving the response content of the target patient to the query content; and a plan generation module 26 for generating a pain treatment plan for the target patient based on the response content.

[0052] This application provides a pain analysis and treatment plan generation system based on machine learning. The system acquires pain information from a target patient through an information acquisition module 21, including text or voice information. A feature extraction module 22 extracts feature information from the pain information and records it into a feature information table. This table contains headers and corresponding tables for pain-related information, with each table storing the feature information corresponding to its header. A type identification module 23 identifies the target patient's pain type based on the feature information table. A query generation module 24 generates query content based on the pain type, including any missing table content from the feature information table. A response receiving module 25 receives the target patient's response to the query. A treatment plan generation module 26 generates a pain treatment plan for the target patient based on the response. By extracting the target patient's pain information to obtain a feature information table, determining the target patient's pain type based on the feature information table, and querying the target patient based on the pain type to supplement relevant information, a treatment plan for the target patient's pain is generated. This improves the accuracy of pain type identification based on the feature information table, allowing for more accurate recommendations of suitable treatment plans for the target patient's pain type.

[0053] In one embodiment, the feature extraction module 22 can be further configured to: extract keywords and quantification words from text information; wherein, keywords represent words corresponding to the table header, and quantification words represent words of numerical value or degree; and determine feature information based on keywords and quantification words.

[0054] In one embodiment, the feature extraction module 22 can be further configured to: divide text information into multiple fields based on keywords; wherein each field contains at least one keyword; search for quantified words in the field where the keyword is located, and match the keywords and quantified words in the same field to obtain a set of feature information.

[0055] In one embodiment, the feature extraction module 22 can be further configured to: recognize speech information to obtain semantic information; and extract feature information from the semantic information.

[0056] In one embodiment, the type identification module 23 described above can be further configured to: determine the pain type of the target patient based on the target patient's historical feature information table.

[0057] In one embodiment, the type identification module 23 can be further configured to: compare the current feature information table and the historical feature information table of the target patient, and filter out the target feature information table from the historical feature information table; wherein, the non-empty table in the current feature information table includes the non-empty table in the target feature information table; and determine the pain type of the target patient based on the pain type corresponding to the target feature information table.

[0058] In one embodiment, the above-mentioned scheme generation module 26 can be further configured to: supplement the feature information table based on the response content; obtain the feature curve of the target patient based on the supplemented feature information table and the historical feature information table of the target patient; wherein the feature curve represents the change pattern of the feature information of the target patient; and generate a pain treatment plan for the target patient based on the feature curve of the target patient.

[0059] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0060] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0061] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0062] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0063] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the methods of the various embodiments of this application described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0064] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0065] When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the collected input signals from the first device and the second device.

[0066] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0067] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0068] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0069] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0070] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java 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 computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0071] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0072] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable 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.

[0073] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0074] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0075] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0076] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0077] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for pain analysis and treatment plan generation based on machine learning, characterized in that, include: Obtain pain information from the target patient; wherein the pain information includes text information or voice information; Extract feature information from the pain information and record the feature information into a feature information table; wherein, the feature information table contains a header of pain-related information and a corresponding table, and the table stores the feature information corresponding to the header; Based on the feature information table, the pain type of the target patient is identified; Based on the pain type, an inquiry is generated; wherein, the inquiry includes the missing table content in the feature information table; Receive the target patient's response to the inquiry; Based on the response, a pain treatment plan for the target patient is generated; The process of identifying the pain type of the target patient based on the feature information table includes: By comparing the current feature information table and the historical feature information table of the target patient, the target feature information table in the historical feature information table is selected; wherein, the non-empty table in the current feature information table contains the non-empty table in the target feature information table; Based on the pain type corresponding to the target feature information table, the pain type of the target patient is determined; The process of generating a pain treatment plan for the target patient based on the response content includes: Based on the content of the response, supplement the feature information table; Based on the supplemented feature information table and the historical feature information table of the target patient, a feature curve of the target patient is obtained; wherein, the feature curve represents the change pattern of the feature information of the target patient, and the feature curve is for the overall change pattern of the target patient or for the change pattern of a certain feature; Based on the characteristic curves of the target patient, a pain treatment plan for the target patient is generated; The pain information of the target patient is recorded to form a pain log, and the relationship between the pain type and psychological factors of the target patient is comprehensively evaluated by combining other data of the target patient. A treatment plan is generated by combining the pain type and the psychological factors. The extraction of feature information from the pain information includes: Extract keywords and quantification terms from the text information; wherein, the keywords refer to the words corresponding to the table header, and the quantification terms refer to words representing numerical values ​​or degrees; The feature information is determined based on the keywords and the quantification terms; The determination of the feature information based on the keywords and the quantification terms includes: The text information is divided into multiple fields based on the keywords; wherein each field contains at least one of the keywords; Search for quantified words in the field containing the keyword, and match the keyword and quantified words in the same field to obtain a set of feature information; The extraction of feature information from the pain information includes: The speech information is identified to obtain semantic information; wherein, the semantic information is text information. Extract the feature information from the semantic information.

2. A pain analysis and treatment plan generation system based on machine learning, characterized in that, include: An information acquisition module is used to acquire pain information of the target patient; wherein, the pain information includes text information or voice information; The feature extraction module is used to extract feature information from the pain information and record the feature information into a feature information table; wherein, the feature information table contains a header of pain-related information and a corresponding table, and the table stores the feature information corresponding to the header; A type recognition module is used to identify the pain type of the target patient based on the feature information table; The inquiry generation module is used to generate inquiry content based on the pain type; wherein, the inquiry content includes the missing table content in the feature information table; The response receiving module is used to receive the response content of the target patient in response to the inquiry content; The treatment plan generation module is used to generate a pain treatment plan for the target patient based on the response content. The type recognition module is further configured as follows: By comparing the current feature information table and the historical feature information table of the target patient, the target feature information table in the historical feature information table is selected; wherein, the non-empty table in the current feature information table contains the non-empty table in the target feature information table; Based on the pain type corresponding to the target feature information table, the pain type of the target patient is determined; The scheme generation module is further configured as follows: Based on the content of the response, supplement the feature information table; Based on the supplemented feature information table and the historical feature information table of the target patient, a feature curve of the target patient is obtained; wherein, the feature curve represents the change pattern of the feature information of the target patient, and the feature curve is for the overall change pattern of the target patient or for the change pattern of a certain feature; Based on the characteristic curves of the target patient, a pain treatment plan for the target patient is generated; The scheme generation module is further configured as follows: The pain information of the target patient is recorded to form a pain log, and the relationship between the pain type and psychological factors of the target patient is comprehensively evaluated by combining other data of the target patient. A treatment plan is generated by combining the pain type and the psychological factors. The feature extraction module is further configured as follows: Extract keywords and quantification terms from the text information; wherein, the keywords refer to the words corresponding to the table header, and the quantification terms refer to words representing numerical values ​​or degrees; The feature information is determined based on the keywords and the quantification terms; The feature extraction module is further configured as follows: The text information is divided into multiple fields based on the keywords; wherein each field contains at least one of the keywords; Search for quantified words in the field containing the keyword, and match the keyword and quantified words in the same field to obtain a set of feature information; The feature extraction module is further configured as follows: The speech information is identified to obtain semantic information; wherein, the semantic information is text information. Extract the feature information from the semantic information.

3. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the method described in claim 1.

4. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the method described in claim 1.

Images