Method, device, equipment and medium for generating rehabilitation plan based on aphasia patients

Abstract

This application discloses a method, device, equipment, and medium for generating a rehabilitation plan for an aphasic patient. The method obtains the original speech signal of the aphasic patient; recognizes the original speech signal to obtain the original text information corresponding to the original speech signal; obtains the rehabilitation goal corresponding to the aphasic patient, extracts target text information from the original text information based on the rehabilitation goal, and converts the target text information into speech information; performs feature extraction on the target text information and speech information respectively to obtain the language features corresponding to the target text information and the speech features corresponding to the speech information; and generates a rehabilitation plan for the aphasic patient based on the language features and speech features. This enables aphasic patients to customize personalized rehabilitation plans at any time in any environment, significantly improving the accuracy and convenience of the plans.

Description

Technical Field

[0001] The present application relates to speech processing technology, which is applied in the medical field, and in particular to a method, device, equipment and medium for generating a rehabilitation plan for aphasic patients. Background Art

[0002] In the field of speech technology, there are already some similar products or systems used for aphasia rehabilitation, such as Lingraph i ca, Constant Therapy and Tactus Therapy.

[0003] However, existing aphasia rehabilitation products or systems have several flaws or shortcomings. First, these products or systems typically use standardized rehabilitation plans and cannot be customized to meet the individual needs of patients. Second, these systems typically require rehabilitation training in specific medical institutions or specialized organizations, resulting in poor convenience. Furthermore, some aphasia rehabilitation systems also suffer from unstable rehabilitation training results and incomplete data recording. Summary of the Invention

[0004] This application provides a method, device, equipment and medium for generating a rehabilitation plan for aphasia patients, aiming to solve the problems that existing aphasia rehabilitation products or systems cannot be customized according to the individual needs of patients, are less convenient, have unstable rehabilitation training effects and incomplete data recording.

[0005] In a first aspect, the present application provides a method for generating a rehabilitation plan for an aphasic patient, comprising:

[0006] Obtaining original speech signals from aphasic patients;

[0007] Recognize the original voice signal and obtain the original text information corresponding to the original voice signal;

[0008] Obtaining the rehabilitation goals corresponding to the aphasia patient, extracting target text information from the original text information according to the rehabilitation goals, and converting the target text information into speech information;

[0009] Extracting features of the target text information and the speech information respectively to obtain language features corresponding to the target text information and speech features corresponding to the speech information;

[0010] Generate corresponding rehabilitation plans for aphasia patients based on language features and speech features.

[0011] In some embodiments, recognizing the original voice signal includes: amplifying the original voice signal; performing voice recognition on the amplified original voice signal to obtain tone information and context information corresponding to the original voice signal; and if it is determined based on the context information that the tone information contains abnormal tones, repairing the abnormal tones.

[0012] In some embodiments, obtaining a rehabilitation goal corresponding to an aphasia patient includes: parsing an original speech signal to obtain an unrecognizable abnormal signal in the original speech signal; determining an aphasia type corresponding to the aphasia patient based on the abnormal signal, and using the aphasia type as a rehabilitation goal.

[0013] Exemplarily, extracting target text information from original text information according to rehabilitation goals includes: obtaining aphasic tones corresponding to aphasic types; and extracting target text information corresponding to aphasic tones from original text information.

[0014] In some embodiments, a rehabilitation plan corresponding to an aphasia patient is generated based on language features and speech features, including: generating an oral practice plan corresponding to an aphasia patient based on language features; generating a listening practice plan corresponding to an aphasia patient based on speech features; generating a rehabilitation plan based on the oral practice plan and the listening practice plan, so as to provide rehabilitation training for the aphasia patient based on the oral practice plan and the listening practice plan.

[0015] In some embodiments, after generating a rehabilitation plan corresponding to an aphasia patient based on language features and speech features, it also includes: conducting rehabilitation training on the aphasia patient according to the rehabilitation plan; obtaining the rehabilitation progress of the aphasia patient, and optimizing the rehabilitation plan based on the rehabilitation progress; the rehabilitation progress includes at least the duration, frequency and effect of the rehabilitation training.

[0016] In some embodiments, feature extraction is performed on the target text information and voice information respectively, including: inputting the target text information and voice information into a preset natural language processing module respectively, the natural language processing module recognizes and outputs a text feature vector and a voice feature vector; and constructing language features based on the text feature vector and constructing voice features based on the voice feature vector.

[0017] In a second aspect, the present application provides a rehabilitation plan generating device, comprising:

[0018] A signal acquisition module is used to obtain the original speech signal of the aphasia patient;

[0019] A speech recognition module, configured to recognize the original speech signal and obtain original text information corresponding to the original speech signal;

[0020] A target acquisition module is used to acquire the rehabilitation target corresponding to the aphasia patient, extract target text information from the original text information according to the rehabilitation target, and convert the target text information into voice information;

[0021] A feature extraction module is used to extract features from the target text information and the voice information respectively, and obtain language features corresponding to the target text information and voice features corresponding to the voice information;

[0022] A plan generating module is used to generate a rehabilitation plan corresponding to the aphasia patient according to the language features and the speech features.

[0023] In a third aspect, the present application further provides a computer device, comprising:

[0024] memory and processor;

[0025] The memory is used to store computer programs;

[0026] The processor is used to execute the computer program and implement the steps of the method for generating a rehabilitation plan for aphasic patients as described in the first aspect when executing the computer program.

[0027] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the steps of the method for generating a rehabilitation plan for aphasic patients as described in the first aspect above.

[0028] This application discloses a method, device, equipment, and medium for generating a rehabilitation plan for aphasic patients. First, the original speech signal of the aphasic patient is obtained; then, the original speech signal is recognized to obtain the original text information corresponding to the original speech signal; then, the rehabilitation goal corresponding to the aphasic patient is obtained, and the target text information is extracted from the original text information according to the rehabilitation goal, and the target text information is converted into speech information; further, feature extraction is performed on the target text information and speech information respectively to obtain the language features corresponding to the target text information and the speech features corresponding to the speech information; finally, a rehabilitation plan corresponding to the aphasic patient is generated based on the language features and speech features. This enables aphasic patients to customize personalized rehabilitation plans at any time in any environment, greatly improving the accuracy and convenience of the plans.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0031] Figure 1 This is a schematic flow chart of the steps of a method for generating a rehabilitation plan for an aphasic patient provided in one embodiment of the present application;

[0032] Figure 2 This is a schematic flow chart of the steps of the original speech signal recognition method provided by one embodiment of the present application;

[0033] Figure 3 This is a schematic flow chart of the steps of a rehabilitation plan generation method provided in one embodiment of the present application;

[0034] Figure 4 It is a structural diagram of a rehabilitation plan generating device provided in one embodiment of the present application;

[0035] Figure 5 This is a schematic block diagram of the structure of a computer device provided in one embodiment of the present application.

[0036] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0038] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0039] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0040] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0041] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0042] In the field of speech technology, there are already some similar products or systems used for aphasia rehabilitation, such as Lingraph ica, Constant Therapy and Tactus Therapy.

[0043] However, existing aphasia rehabilitation products or systems have several flaws or shortcomings. First, these products or systems typically use standardized rehabilitation plans and cannot be customized to meet the individual needs of patients. Second, these systems typically require rehabilitation training in specific medical institutions or specialized organizations, resulting in poor convenience. Furthermore, some aphasia rehabilitation systems also suffer from unstable rehabilitation training results and incomplete data recording.

[0044] To resolve the above issues, please refer to Figure 1 , Figure 1 This is a schematic flowchart of a method for generating a rehabilitation plan for aphasic patients provided in one embodiment of the present application.

[0045] The method for generating a rehabilitation plan for aphasic patients can be implemented by a computer device, which can be deployed on a single server or a server cluster. It can also be deployed on a handheld terminal, a laptop computer, a wearable device, or a robot.

[0046] The provided method can be applied in the medical field to provide aphasia patients with personalized rehabilitation plans that can be generated in any environment.

[0047] like Figure 1 As shown, the method for generating a rehabilitation plan for an aphasic patient provided in this embodiment includes steps S101 to S105. The details are as follows:

[0048] S101. Obtain original speech signals from an aphasic patient.

[0049] Specifically, by collecting the original speech signals of aphasia patients in any scenario, for example, when the aphasia patient is in the hospital, the original speech signals can be collected through a dedicated microphone. When the aphasia patient is at home or in any other scenario, the original speech signals of the aphasia patient can be collected through the audio input module of any terminal such as a mobile phone or computer. Furthermore, the provided method can collect the original speech signals of multiple aphasia patients at any time and formulate corresponding rehabilitation plans for them. This greatly improves the convenience and flexibility of the treatment of aphasia patients.

[0050] In some embodiments, obtaining the original voice signal of the aphasic patient includes: playing a preset prompt voice to the aphasic patient, and obtaining the original voice signal of the aphasic patient's response based on the prompt voice.

[0051] Furthermore, the provided method can test the responses of aphasic patients to preset prompt voices to determine whether the aphasic patients have hearing impairments, and can also standardize the design of rehabilitation plans.

[0052] S102. Recognize the original voice signal and obtain original text information corresponding to the original voice signal.

[0053] Specifically, by recognizing the original voice signals of aphasic patients, converting the voice signals into text form, and obtaining the corresponding original text information, it is possible to analyze the content of the original voice signals input by aphasic patients to prepare for the generation of a rehabilitation plan.

[0054] In some embodiments, please refer to Figure 2 , Figure 2 The provided original speech signal recognition method includes steps S102a to S102c.

[0055] S102a. Amplify the original speech signal.

[0056] S102b. Perform speech recognition on the amplified original speech signal to obtain tone information and context information corresponding to the original speech signal.

[0057] S102c. If it is determined based on the context information that there is an abnormal tone in the tone information, repair the abnormal tone.

[0058] Because the original speech signals of aphasic patients may be too quiet or unclear, affecting text conversion, the proposed method first amplifies the original speech signal, then identifies the corresponding tonal information and contextual information from the amplified original speech signal. This contextual information then determines whether any tones in the original speech signal are incorrect. For example, if the text contains (…wōgēnníshuō…), the tonal errors of ō and í can be confirmed as abnormal and need to be corrected to ǒ and ǐ. This method can then correct abnormal tones in the original speech signal, ensuring the accuracy of the converted text.

[0059] S103. Obtain rehabilitation goals corresponding to the aphasia patient, extract target text information from the original text information according to the rehabilitation goals, and convert the target text information into voice information.

[0060] Specifically, the rehabilitation goal for aphasia can be determined based on the case information corresponding to the aphasia patient, or based on the original speech signal. The embodiment of the present application does not limit the method for obtaining the rehabilitation goal. At the same time, after confirming the rehabilitation goal corresponding to the aphasia patient, the provided method extracts the target text information from the original text information based on the rehabilitation goal, and then can convert the target text information used for the rehabilitation of the aphasia patient into speech information for training. At the same time, the rehabilitation text information and speech information corresponding to the rehabilitation goal can also be extracted from the preset rehabilitation database for subsequent determination of the rehabilitation plan.

[0061] In some embodiments, obtaining a rehabilitation goal corresponding to an aphasia patient includes: parsing an original speech signal to obtain an unrecognizable abnormal signal in the original speech signal; determining an aphasia type corresponding to the aphasia patient based on the abnormal signal, and using the aphasia type as a rehabilitation goal.

[0062] By analyzing abnormal signals whose content cannot be identified in the original speech signal, the abnormal signal can be a signal with any abnormality such as unclear content / abnormal tone, and then the aphasia type corresponding to the aphasia patient can be determined based on the abnormal signal, such as any aphasia type such as the inability to pronounce vowels / inability to pronounce retroflex syllables / inability to read syllables in a connected manner, so as to determine the rehabilitation plan for the aphasia patient in a targeted manner and improve the accuracy of the generated rehabilitation plan.

[0063] Exemplarily, extracting target text information from original text information based on rehabilitation goals includes: obtaining aphasic tones corresponding to aphasic types; and extracting target text information corresponding to aphasic tones from the original text information. The provided method can accurately extract target text information for rehabilitation training from the converted original text information.

[0064] S104. Perform feature extraction on the target text information and the voice information respectively to obtain language features corresponding to the target text information and voice features corresponding to the voice information.

[0065] Specifically, the provided method can extract the language features and speech features of aphasic patients by performing feature extraction on target text information and speech information, so as to confirm the feature types that need to be targeted in the rehabilitation plan generated therefor.

[0066] In some embodiments, feature extraction is performed on target text information and speech information separately, including: inputting the target text information and speech information into a preset natural language processing module, the natural language processing module identifying and outputting a text feature vector and a speech feature vector; and constructing language features based on the text feature vectors and speech features based on the speech feature vectors. The provided method can thus extract language features and speech features based on the natural language processing module.

[0067] S105. Generate a rehabilitation plan corresponding to aphasia patients based on language features and speech features.

[0068] Specifically, by generating a personalized rehabilitation plan for aphasia patients based on their language and speech characteristics, rehabilitation training can be provided to aphasia patients in any scenario based on the rehabilitation plan. This enables aphasia patients to customize their own rehabilitation plan at any time in any environment, significantly improving the accuracy and convenience of the plan.

[0069] In some embodiments, please refer to Figure 3 , generating a rehabilitation plan corresponding to an aphasia patient according to language features and speech features, including steps S105a to S105c.

[0070] like Figure 3 The steps S105a to S105c include:

[0071] S105a. Generate an oral practice plan corresponding to aphasia patients based on language characteristics.

[0072] S105b. Generate a listening practice plan corresponding to aphasia patients based on speech features.

[0073] S105c. Generate a rehabilitation plan according to the oral practice plan and the listening practice plan, so as to perform rehabilitation training for the aphasia patient according to the oral practice plan and the listening practice plan.

[0074] The provided method generates a corresponding oral practice plan for aphasic patients based on their corresponding language features. For example, based on language features, it is confirmed that aphasic patients have significant difficulty pronouncing certain syllables, and a targeted oral practice plan is generated. Based on voice features, it is confirmed that aphasic patients have significant difficulty hearing certain syllables, and a corresponding voice practice plan is generated. The provided method can provide targeted training for aphasic patients based on their language and voice barriers, thereby improving the effectiveness of rehabilitation training.

[0075] In some embodiments, after generating a rehabilitation plan corresponding to an aphasia patient based on language features and speech features, it also includes: conducting rehabilitation training on the aphasia patient according to the rehabilitation plan; obtaining the rehabilitation progress of the aphasia patient, and optimizing the rehabilitation plan based on the rehabilitation progress; the rehabilitation progress includes at least the duration, frequency and effect of the rehabilitation training.

[0076] The method provided in this application determines the corresponding rehabilitation plan for aphasia patients, conducts targeted rehabilitation training for the patients, and records the rehabilitation progress of the aphasia patients, such as the duration, frequency, and effect of the rehabilitation training. The rehabilitation plan of the aphasia patients can be optimized through computer equipment, or the rehabilitation plan can be adjusted by the attending physician of the aphasia patients. The provided method can assist doctors in providing targeted treatment to patients, thereby reducing the workload of doctors and improving the efficiency of treatment.

[0077] Compared with traditional aphasia rehabilitation treatment methods, the method provided by the present invention has the following advantages:

[0078] Personalized customization: According to the patient's voice and language characteristics, a rehabilitation plan is tailored for the patient to improve the rehabilitation effect.

[0079] Anytime, anywhere: Patients can use the system for rehabilitation training at home, which is convenient and fast.

[0080] Data support: The system can record the patient's rehabilitation progress, provide data support to doctors, and optimize rehabilitation plans.

[0081] Various rehabilitation training: The system provides a variety of rehabilitation training, including pronunciation exercises, language comprehension exercises, etc., to provide patients with comprehensive rehabilitation support.

[0082] See also Figure 4 As shown, Figure 42 is a schematic diagram of the structure of a rehabilitation plan generation device 200 provided in an embodiment of the present application. The rehabilitation plan generation device 200 is used to execute the steps of the rehabilitation plan generation method for aphasic patients shown in the above embodiments. The rehabilitation plan generation device 200 can be a single server or a server cluster, or the rehabilitation plan generation device 200 can be a terminal, such as a handheld terminal, a laptop computer, a wearable device, or a robot.

[0083] like Figure 4 As shown, the rehabilitation plan generating device 200 includes:

[0084] The signal acquisition module 201 is used to acquire the original speech signal of the aphasia patient;

[0085] The speech recognition module 202 is configured to recognize the original speech signal and obtain original text information corresponding to the original speech signal;

[0086] A target acquisition module 203 is configured to acquire a rehabilitation target corresponding to the aphasia patient, extract target text information from the original text information according to the rehabilitation target, and convert the target text information into speech information;

[0087] A feature extraction module 204 is configured to extract features from the target text information and the voice information, respectively, to obtain language features corresponding to the target text information and voice features corresponding to the voice information;

[0088] The plan generating module 205 is configured to generate a rehabilitation plan corresponding to the aphasia patient according to the language features and the speech features.

[0089] In some embodiments, the speech recognition module 202 is also used to amplify the original speech signal; perform speech recognition on the amplified original speech signal to obtain tone information and context information corresponding to the original speech signal; if it is determined based on the context information that there is an abnormal tone in the tone information, repair the abnormal tone.

[0090] In some embodiments, the target acquisition module 203 is used to parse the original speech signal and obtain unrecognizable abnormal signals in the original speech signal; determine the aphasia type corresponding to the aphasia patient based on the abnormal signals, and use the aphasia type as a rehabilitation target.

[0091] Exemplarily, the target acquisition module 203 is further configured to acquire the aphasic tone corresponding to the aphasic type; and extract the target text information corresponding to the aphasic tone from the original text information.

[0092] In some embodiments, the plan generation module 205 is further used to generate an oral practice plan corresponding to aphasia patients based on language features; generate a listening practice plan corresponding to aphasia patients based on speech features; generate a rehabilitation plan based on the oral practice plan and the listening practice plan, so as to provide rehabilitation training for aphasia patients based on the oral practice plan and the listening practice plan.

[0093] In some embodiments, after generating a rehabilitation plan corresponding to an aphasia patient based on language features and speech features, the device further includes: a plan optimization module for performing rehabilitation training on the aphasia patient according to the rehabilitation plan; obtaining the rehabilitation progress of the aphasia patient and optimizing the rehabilitation plan based on the rehabilitation progress; the rehabilitation progress includes at least the duration, frequency and effect of the rehabilitation training.

[0094] In some embodiments, the feature extraction module 204 is also used to input the target text information and voice information into a preset natural language processing module respectively, and the natural language processing module recognizes and outputs text feature vectors and voice feature vectors; and constructs language features based on the text feature vectors and voice features based on the voice feature vectors.

[0095] It should be noted that those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the rehabilitation plan generating device and each module described above can refer to the corresponding processes in the embodiments of the rehabilitation plan generating method based on aphasia patients described in the above embodiments, and will not be repeated here.

[0096] The above-mentioned method for generating a rehabilitation plan based on aphasia patients can be implemented in the form of a computer program. The computer program can be used in Figure 4 Run on the device shown.

[0097] See also Figure 5 , Figure 5 1 is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0098] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the methods for generating a rehabilitation plan for an aphasic patient.

[0099] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0100] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the methods for generating a rehabilitation plan for aphasic patients.

[0101] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0102] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0103] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0104] Obtaining original speech signals from aphasic patients;

[0105] Recognize the original voice signal and obtain the original text information corresponding to the original voice signal;

[0106] Obtaining the rehabilitation goals corresponding to the aphasia patient, extracting target text information from the original text information according to the rehabilitation goals, and converting the target text information into speech information;

[0107] Extracting features of the target text information and the speech information respectively to obtain language features corresponding to the target text information and speech features corresponding to the speech information;

[0108] Generate corresponding rehabilitation plans for aphasia patients based on language features and speech features.

[0109] In some embodiments, recognizing the original voice signal includes: amplifying the original voice signal; performing voice recognition on the amplified original voice signal to obtain tone information and context information corresponding to the original voice signal; and if it is determined based on the context information that the tone information contains abnormal tones, repairing the abnormal tones.

[0110] In some embodiments, obtaining a rehabilitation goal corresponding to an aphasia patient includes: parsing an original speech signal to obtain an unrecognizable abnormal signal in the original speech signal; determining an aphasia type corresponding to the aphasia patient based on the abnormal signal, and using the aphasia type as a rehabilitation goal.

[0111] Exemplarily, extracting target text information from original text information according to rehabilitation goals includes: obtaining aphasic tones corresponding to aphasic types; and extracting target text information corresponding to aphasic tones from original text information.

[0112] In some embodiments, a rehabilitation plan corresponding to an aphasia patient is generated based on language features and speech features, including: generating an oral practice plan corresponding to an aphasia patient based on language features; generating a listening practice plan corresponding to an aphasia patient based on speech features; generating a rehabilitation plan based on the oral practice plan and the listening practice plan, so as to provide rehabilitation training for the aphasia patient based on the oral practice plan and the listening practice plan.

[0113] In some embodiments, after generating a rehabilitation plan corresponding to an aphasia patient based on language features and speech features, it also includes: conducting rehabilitation training on the aphasia patient according to the rehabilitation plan; obtaining the rehabilitation progress of the aphasia patient, and optimizing the rehabilitation plan based on the rehabilitation progress; the rehabilitation progress includes at least the duration, frequency and effect of the rehabilitation training.

[0114] In some embodiments, feature extraction is performed on the target text information and voice information respectively, including: inputting the target text information and voice information into a preset natural language processing module respectively, the natural language processing module recognizes and outputs a text feature vector and a voice feature vector; and constructing language features based on the text feature vector and constructing voice features based on the voice feature vector.

[0115] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the method for generating a rehabilitation plan for aphasic patients provided in the above embodiments of the present application.

[0116] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0117] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for generating a rehabilitation plan for an aphasic patient, characterized in that: include: Obtaining original speech signals from aphasic patients; Recognizing the original speech signal includes: amplifying the original speech signal; performing speech recognition on the amplified original speech signal to obtain tone information and context information corresponding to the original speech signal; if it is determined based on the context information that the tone information contains abnormal tones, repairing the abnormal tones; and obtaining original text information corresponding to the original speech signal; Obtaining a rehabilitation goal corresponding to the aphasia patient, including: parsing an original speech signal to obtain an abnormal signal that cannot be identified in the original speech signal; determining an aphasia type corresponding to the aphasia patient based on the abnormal signal, and using the aphasia type as a rehabilitation goal; extracting target text information from the original text information based on the rehabilitation goal, including: obtaining an aphasia tone corresponding to the aphasia type; extracting target text information corresponding to the aphasia tone from the original text information; converting the target text information into speech information; the rehabilitation goal is determined based on case information corresponding to the aphasia patient, or based on the original speech signal; Feature extraction is performed on the target text information and the voice information respectively, including: inputting the target text information and the voice information into a preset natural language processing module respectively, the natural language processing module identifying and outputting a text feature vector and a voice feature vector; constructing language features based on the text feature vector and constructing voice features based on the voice feature vector; obtaining language features corresponding to the target text information and voice features corresponding to the voice information; A rehabilitation plan corresponding to the aphasia patient is generated according to the language features and the speech features.

2. The method according to claim 1, characterized in that Generating a rehabilitation plan corresponding to the aphasia patient according to the language features and the speech features includes: generating a corresponding oral practice plan for the aphasia patient according to the language features; generating a listening practice plan corresponding to the aphasia patient according to the speech features; The rehabilitation plan is generated according to the oral practice plan and the listening practice plan, so as to perform rehabilitation training on the aphasia patient according to the oral practice plan and the listening practice plan.

3. The method according to claim 1, characterized in that After generating a rehabilitation plan corresponding to the aphasia patient according to the language features and the speech features, the method further includes: performing rehabilitation training on the aphasia patient according to the rehabilitation plan; Obtaining the rehabilitation progress of the aphasia patient and optimizing the rehabilitation plan according to the rehabilitation progress; the rehabilitation progress at least includes the duration, frequency and effect of the rehabilitation training.

4. A rehabilitation plan generating device, characterized in that: include: A signal acquisition module is used to obtain the original speech signal of the aphasia patient; a speech recognition module for recognizing the original speech signal, including: amplifying the original speech signal; performing speech recognition on the amplified original speech signal to obtain tone information and context information corresponding to the original speech signal; if abnormal tones are determined in the tone information based on the context information, repairing the abnormal tones; and obtaining original text information corresponding to the original speech signal; A target acquisition module is used to acquire a rehabilitation target corresponding to the aphasia patient, including: parsing the original speech signal to acquire an abnormal signal that cannot be identified in the original speech signal; determining the aphasia type corresponding to the aphasia patient based on the abnormal signal, and using the aphasia type as the rehabilitation target; extracting target text information from the original text information based on the rehabilitation target, including: acquiring aphasia tones corresponding to the aphasia type; extracting target text information corresponding to the aphasia tones from the original text information; converting the target text information into speech information; the rehabilitation target is determined based on the case information corresponding to the aphasia patient, or based on the original speech signal; A feature extraction module is used to extract features from the target text information and the voice information respectively, including: inputting the target text information and the voice information into a preset natural language processing module respectively, the natural language processing module identifying and outputting a text feature vector and a voice feature vector; constructing language features based on the text feature vector and voice features based on the voice feature vector; and obtaining language features corresponding to the target text information and voice features corresponding to the voice information; A plan generating module is used to generate a rehabilitation plan corresponding to the aphasia patient according to the language features and the speech features.

5. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method for generating a rehabilitation plan for an aphasic patient according to any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to implement the method for generating a rehabilitation plan for an aphasic patient according to any one of claims 1 to 3.

Images