Method, system, device and medium for recommending personalized solutions for aphasia

Abstract

The present application provides a personalized program recommendation method, system, device and medium for aphasia, which relates to the field of medical information processing technology, including obtaining current hypothesis information; the current hypothesis information includes: a current evaluation node obtained based on a hypothesis verification method; executing an evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result; locating the target damaged node of the target patient based on the evaluation result; improving the accuracy and efficiency of the evaluation; predicting the damaged language module based on all the target damaged nodes, constructing a personalized training program, and improving the pertinence and training effect of the training.

Description

Technical Field

[0001] The present invention relates to the field of medical information processing technology, and in particular to a method, system, electronic device and readable storage medium for recommending personalized solutions for aphasia. Background Art

[0002] Aphasia is a syndrome of acquired language dysfunction caused by organic damage to the brain, which results in damage to the language center of the cerebral hemisphere and its related language network. Patients show impaired or lost ability to receive (understand) and use (express) language symbols while being conscious.

[0003] Traditional methods of rehabilitation training for aphasia often focus on functional recovery, but lack the precise location of the specific damaged links in the patient's language processing, resulting in poor rehabilitation effects and low efficiency.

[0004] Therefore, it is necessary to propose a personalized solution recommendation method, system, electronic device and readable storage medium for aphasia. Summary of the Invention

[0005] This specification provides a personalized aphasia recommendation method, system, electronic device, and readable storage medium. By acquiring current hypothetical information and executing a corresponding assessment process, the method accurately locates the target patient's impaired language modules and constructs a personalized training plan. This method not only improves the accuracy and efficiency of aphasia assessment but also ensures the effectiveness and targeted nature of the training plan. Furthermore, by incorporating a dialect dictionary, the assessment and training process is more closely aligned with the patient's actual language environment, contributing to improved training effectiveness.

[0006] The present application provides a method for recommending personalized solutions for aphasia using the following technical solutions, including:

[0007] Obtaining current hypothesis information; the current hypothesis information includes: a current evaluation node;

[0008] Executing the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result;

[0009] locating a target damaged node of the target patient based on the evaluation result;

[0010] Based on all the target damaged nodes, the damaged language modules are predicted and a personalized training plan is constructed.

[0011] Optionally, obtaining current hypothesis information includes:

[0012] Based on the user's evaluation instruction, original evaluation information is displayed; the original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes;

[0013] Based on the user's selection instruction, a current evaluation node obtained based on a hypothesis testing method is determined as current hypothesis information.

[0014] Optionally, the evaluation result includes: evaluation type;

[0015] The locating the target damaged node of the target patient based on the type includes:

[0016] Based on the evaluation type, determining whether the current evaluation node is a critical evaluation node;

[0017] If the current evaluation node is not a critical evaluation node, re-determine a new current evaluation node; and execute a corresponding evaluation process on the target patient using the new current evaluation node;

[0018] If the current evaluation node is a critical evaluation node, the current evaluation node is used as a target damaged node.

[0019] Optionally, the determining, based on the evaluation type, whether the current evaluation node is a critical evaluation node includes:

[0020] When the evaluation type is the first evaluation type, it is determined that the current evaluation node is not a critical evaluation node; the first evaluation type is used to indicate that the evaluation is normal;

[0021] When the evaluation type is the second evaluation type, whether the current evaluation node is a critical evaluation node is determined based on a criticality judgment strategy; the second evaluation type is used to characterize evaluation anomalies.

[0022] Optionally, if the current evaluation node is not a critical evaluation node, re-determining a new current evaluation node, and using the new current evaluation node to execute a corresponding evaluation process for the target patient, including:

[0023] Identifying the information flow where the current evaluation node is located;

[0024] A new current evaluation node is determined according to the evaluation result of the current evaluation node and the information flow in which it is located.

[0025] Optionally, each evaluation node corresponds to a preset question bank; the preset question bank includes a plurality of test information;

[0026] Optionally, executing the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result further includes:

[0027] Establish a dialect dictionary based on dialect phonetic materials;

[0028] Based on the dialect dictionary library, the test information is replaced with the dialect version of the test information to construct a dialect version of the preset question bank.

[0029] Optionally, also include:

[0030] In combination with the training situation of the target patient, the personalized training program is updated to obtain a new personalized training program.

[0031] The present application provides a personalized solution recommendation system for aphasia using the following technical solutions, including:

[0032] An information acquisition module is used to acquire current hypothesis information; the current hypothesis information includes: a current evaluation node;

[0033] An evaluation module, configured to execute the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result;

[0034] a node positioning module, configured to locate a target damaged node of the target patient based on the evaluation result;

[0035] The personalized program construction module is used to predict the damaged language module based on all the target damaged nodes and construct a personalized training program.

[0036] Optionally, the information acquisition module includes:

[0037] The hypothesis submodule is used to display original evaluation information based on the user's evaluation instruction; the original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes;

[0038] The selection module is configured to determine, based on the user's selection instruction, a current evaluation node obtained based on a hypothesis testing method as current hypothesis information.

[0039] Optionally, the evaluation result includes: evaluation type;

[0040] Optionally, the positioning module includes:

[0041] A first judgment submodule, configured to judge whether the current evaluation node is a critical evaluation node based on the evaluation type;

[0042] A first positioning submodule is configured to, if the current evaluation node is not a critical evaluation node, redetermine a new current evaluation node; and execute a corresponding evaluation process on the target patient using the new current evaluation node;

[0043] The second positioning submodule is configured to use the current evaluation node as a target damaged node if the current evaluation node is a critical evaluation node.

[0044] Optionally, the first judgment submodule includes:

[0045] a first judgment unit, configured to determine that the current evaluation node is not a critical evaluation node when the evaluation type is a first evaluation type; the first evaluation type is used to indicate that the evaluation is normal;

[0046] The second judgment unit is configured to judge whether the current evaluation node is a critical evaluation node based on a criticality judgment strategy when the evaluation type is a second evaluation type; the second evaluation type is used to characterize evaluation anomalies.

[0047] Optionally, the first positioning submodule includes:

[0048] An information flow identification unit, configured to identify the information flow at which the current evaluation node is located;

[0049] The node updating unit is used to determine a new current evaluation node according to the evaluation result of the current evaluation node and the information flow in which it is located.

[0050] Optionally, each evaluation node corresponds to a preset question bank; the preset question bank includes a plurality of test information;

[0051] Optionally, the evaluation module further includes:

[0052] The dialect dictionary library establishment submodule is used to establish a dialect dictionary library based on dialect voice materials;

[0053] The replacement submodule is used to replace the test information with the test information of the dialect version based on the dialect dictionary library, and construct a preset question bank of the dialect version.

[0054] Optionally, also include:

[0055] The updating module is used to update the personalized training program in combination with the training situation of the target patient to obtain a new personalized training program.

[0056] This specification also provides an electronic device, wherein the electronic device includes:

[0057] processor; and,

[0058] A memory storing computer executable instructions, which, when executed, cause the processor to perform any of the above methods.

[0059] This specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0060] This specification also provides a computer program product, wherein the computer program product includes: a computer program / instructions, and when the computer program / instructions are executed by a processor, any of the above methods is implemented.

[0061] In the present application, current hypothesis information is obtained; the current hypothesis information includes: a current evaluation node obtained based on a hypothesis verification method; an evaluation process corresponding to the current evaluation node is executed on the target patient to obtain an evaluation result; the target damaged node of the target patient is located based on the evaluation result; the accuracy and efficiency of the evaluation are improved; based on all the target damaged nodes, the damaged language module is predicted, and a personalized training plan is constructed to improve the training effect and training targeting. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic diagram of the principle of a method for recommending a personalized solution for aphasia provided in an embodiment of this specification;

[0063] Figure 2 A flowchart of a method for recommending a personalized solution for aphasia provided in an embodiment of this specification;

[0064] Figure 3 A schematic diagram of the structure of a personalized solution recommendation system for aphasia provided in an embodiment of this specification;

[0065] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0066] Figure 5 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of this specification. DETAILED DESCRIPTION

[0067] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0068] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, making it easier to fully convey the inventive concept to those skilled in the art. In the figures, the same reference numerals represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0069] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0070] In the description of specific embodiments, the features, structures, characteristics, or other details of the present invention are described to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from practicing the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0071] 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, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0072] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0073] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0074] If the technical solution of this application involves personal information, the product that applies the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of this application involves sensitive personal information, the product that applies the technical solution of this application has obtained the individual's separate consent before processing sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, a clear and prominent sign is set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that they agree to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload their personal information; among which, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0075] Figure 1 This is a schematic diagram of the principle of a method for recommending a personalized solution for aphasia provided in an embodiment of this specification, the method comprising:

[0076] S1 obtains current hypothesis information; the current hypothesis information includes: a current evaluation node;

[0077] S2 executes the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result;

[0078] S3 locates the target damaged node of the target patient based on the evaluation result;

[0079] S4 predicts the damaged language modules based on all the target damaged nodes and builds a personalized training plan.

[0080] Aphasia refers to the loss or impairment of language ability caused by brain damage, a clinical syndrome characterized by dysfunction in one or more aspects of the ability to understand, express, perceive, and organize and apply language symbols. Aphasia is an acquired disorder that can be caused by conditions such as cerebrovascular disease, brain trauma, brain tumors, infections, and central nervous system degeneration.

[0081] As a common complication after brain tissue damage, aphasia seriously affects the patient's language communication ability, significantly limits the patient's social ability, and significantly reduces the patient's quality of life.

[0082] Therefore, rehabilitation training for aphasia should be initiated as early as possible, based on active treatment of the underlying disease. This can improve patients' language comprehension and expression, enhance independent verbal communication skills, and restore their ability to communicate directly with others. Failure to promptly initiate rehabilitation training can lead to complete or partial aphasia, accompanied by neurological deficits such as hemiplegia and hemianopsia.

[0083] Systematic language training is currently considered to be the most effective method for treating aphasia. During the edema period caused by brain injury, some brain cells become paralyzed and "hibernate", and many synapses tend to be interrupted. As the edema subsides, the cells "gradually wake up". After strengthening language function training, the interrupted synapses are tightly connected and the function is quickly restored. If there is no training, the interrupted synapses may lose connection.

[0084] The prognosis of aphasia is closely related to a variety of factors, including lesion size, location, acute phase management, age, education level, timing of rehabilitation intervention, training methods, intensity, cooperation, and family reinforcement training. Aphasia patients can achieve varying degrees of improvement through speech therapy, and some can even return to work.

[0085] Traditional rehabilitation training methods mainly focus on functional recovery, but lack the precise positioning of the specific damaged links in the patient's language processing, resulting in poor rehabilitation effects and low rehabilitation efficiency.

[0086] Based on this, the present invention provides a personalized solution recommendation method for aphasia, such as Figure 2 As shown, it specifically includes:

[0087] S1 obtains current hypothesis information;

[0088] S11 builds a case database;

[0089] The case database stores multiple case information. Each patient corresponds to a case information. Case information includes but is not limited to: attribute information, basic information, all record files, etc.

[0090] Attribute information includes but is not limited to: case number, patient name, and years of education.

[0091] Basic information is used to characterize the patient's basic situation, such as medical history, language background, etc.

[0092] The record file is used to record the patient's medical information, assessment process, and training process. After each assessment and / or training, a record file is generated. In one embodiment of this specification, the record file includes: the recording time and the assessment results of that session.

[0093] In one embodiment of the present specification, a case management module is included; a case management module and a case update module;

[0094] The case management module includes a retrieval submodule and a case deletion submodule. The case deletion submodule is used to delete selected case information based on the user's case deletion instruction. The retrieval submodule is used to filter case information based on the user's case retrieval instruction.

[0095] The case update module includes: a record creation submodule and a record deletion submodule. The record creation submodule is used to generate a blank record file for this evaluation or training; the record deletion submodule is used to delete the selected record file.

[0096] Before examining the target patient, the corresponding case information is retrieved from the case database based on the retrieval submodule. Specifically:

[0097] S12 searches for target case information of a target patient;

[0098] S121 displays a search page to the user and obtains a case search request;

[0099] The user in the present invention may be a person who examines the target patient, a person who operates the system, etc., such as a doctor, a therapist or other relevant professionals.

[0100] S121-1 displays the search page to the user;

[0101] Obtaining a user's start search request and generating a first search instruction;

[0102] Based on the user's first search instruction, displaying a search page to the user;

[0103] The search page includes several search fields, each of which includes search attributes and search areas. Search attributes correspond to search areas in a one-to-one manner. Search attributes include, but are not limited to, case number, patient name, and years of education. The search area allows users to enter or select a search attribute value for the corresponding search attribute. The search area can be an input field to facilitate user input of search attribute values, or it can be a pre-set drop-down menu that automatically generates search attribute values ​​based on user selections. The specific implementation method is not limited.

[0104] S121-2 collects the search attribute value input by the user and generates a case search request;

[0105] After the user fills in / selects the target search attribute value in the corresponding search area on the first search page, clicks Search to generate and send a case search request;

[0106] The case retrieval request includes the attributes to be retrieved and the corresponding target retrieval attribute values;

[0107] S122 searches and displays case information that meets the case search request from the case database;

[0108] S122-1 searches for case information that matches the target search attribute value from the case database according to the case search request;

[0109] In one embodiment of the present disclosure, a user enters a partial case number and / or a full case number of a target patient in the search area corresponding to the case number. Since case numbers correspond one to one with patients, entering the full case number directly locates the case information of the target patient.

[0110] When entering a partial case number, multiple cases may be found. In this case, all cases matching the search attribute are searched in the case database and displayed on the query page for the user to select. Of course, the name of the patient with case information is also displayed to facilitate user selection.

[0111] In another embodiment of the present specification, the user enters the target patient's last name in the search field corresponding to the patient name to perform a search; the user's search request is received, and the case numbers of the retrieved case information are listed based on the search request for the user to select. Alternatively, the user may enter the target patient's full name in the search field corresponding to the patient name to perform a search; the case numbers of the retrieved case information are listed for the user to select.

[0112] In another embodiment of the present specification, the user enters the target patient's years of education in the search area corresponding to the years of education to perform a search; obtains the user's search request, and lists the case numbers of the retrieved case information based on the search request for the user to select.

[0113] In other embodiments of the present specification, it is also possible to directly search without entering a search attribute value in any search area; in this case, since there is no search item, all case numbers will be listed for the user to select.

[0114] S122-2 displays attribute information of case information that meets the search requirements to the user on the query page;

[0115] Obtain case information that meets the search requirements and display its corresponding attribute information on the query page.

[0116] S123 determines target case information based on the user's selection instruction;

[0117] The user selects attribute information on the query page; the case information corresponding to the attribute information selected by the user is used as the target case information, and the target case information is displayed in detail.

[0118] In one embodiment of the present specification, when the user cannot retrieve the case information of the target patient, it means that there may be no past records of the target patient. At this time, new case information of the target patient is created; the basic information of the target patient is obtained and added to the target case information.

[0119] The present invention is based on a friendly human-computer interaction interface, so that users can operate and use the search interface displayed on the human-computer interaction interface.

[0120] S13 creates a new record file in the target case information;

[0121] Since a new evaluation / Nth evaluation is required this time, the record creation submodule is called to create a new record file to record this evaluation.

[0122] S14 displays original evaluation information based on the user's evaluation instruction;

[0123] The dual-stream model of language processing is considered one of the most clinically valuable neural circuits for language processing. As a classic theory of language processing in the brain, the dual-stream model clearly identifies two information flows involved in language processing: the ventral stream and the dorsal stream.

[0124] The ventral stream is responsible for semantic understanding of language and is used to process the meaning of words and sentences. This pathway involves mapping speech representations to word concept representations and is typically associated with left-sided brain regions, with a slight left-hemisphere advantage. The dorsal stream is responsible for speech and repetition and is the sensory-motor interface. This pathway involves mapping speech representations to articulatory motor representations and has a strong left-side advantage, while Broca's area and the anterior insula, located further anterior to the frontal lobe, are the articulatory network.

[0125] In order to provide a more accurate neurological tracing of language disorders in patients with aphasia, aphasia assessment can be performed based on the dual-stream model to analyze which of the two main pathways of language processing has problems, so as to facilitate targeted rehabilitation training.

[0126] S141 constructs original evaluation information based on the dual-stream model of language processing;

[0127] In one embodiment of the present specification, the original evaluation information may be a language function module graph. The original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes;

[0128] Evaluation nodes represent different language function modules. A language task label is set for each evaluation node. The language task label can be set based on actual circumstances and is not specifically limited here.

[0129] In one embodiment of the present specification, language task tags include but are not limited to: spontaneous speech, auditory comprehension, and retelling. In another embodiment of the present specification, language task tags include but are not limited to: language comprehension, speech output, vocabulary representation, and retelling ability.

[0130] Based on the directed connection relationship, the order of each evaluation node is in a sequence. In the same language task, the earlier the evaluation node is in the order, the simpler the language function it evaluates.

[0131] In one embodiment of this specification, original evaluation information is constructed based on information flows. Specifically, based on a first information flow, a plurality of first evaluation nodes and a plurality of first connection relationships are constructed. The first information flow is a ventral flow. Based on a second information flow, a plurality of second evaluation nodes and a plurality of second connection relationships are constructed. The second information flow is a dorsal flow. The first evaluation nodes and the second evaluation nodes may overlap.

[0132] In one embodiment of this specification, publicly available literature or research results are obtained to determine the evaluation nodes and connection relationships involved in each information flow, as well as the language task labels for each evaluation node. Therefore, the specific contents of the evaluation nodes, connection relationships, and language task labels are not limited herein.

[0133] S142 obtains the user's evaluation instruction and displays the original evaluation information.

[0134] When the user wants to evaluate the target patient, the user will create a new record file; after the record file is created, the user sends an evaluation instruction; based on the user's evaluation instruction, the original evaluation information is displayed.

[0135] S15 determines, based on the user's selection instruction, a current evaluation node obtained based on the hypothesis testing method as current hypothesis information.

[0136] The current hypothesis information includes: a current evaluation node;

[0137] To assess the language abilities of aphasic patients and conduct statistical analysis, hypothesis testing can be used to evaluate different language tasks. Specifically, hypothesis testing, a language cognitive processing model developed using cognitive neuropsychology, can help users more accurately identify specific language impairment modules and the extent of the impairment.

[0138] Compared to traditional scale-based methods, hypothesis testing can reveal a patient's language dysfunction in a more in-depth and targeted manner. It examines whether language processing is impaired, as well as the level and cause of impairment. This provides a clear direction for language rehabilitation training, allowing users to target interventions for the patient's specific impaired language modules, significantly improving rehabilitation effectiveness. Hypothesis testing not only assesses a patient's current language impairment but also monitors changes over time. This can be combined with other clinical rehabilitation training methods for targeted treatment, thereby more effectively promoting a patient's language rehabilitation.

[0139] The current evaluation node is determined using a hypothesis verification method in conjunction with the patient's medical information. In one embodiment of this specification, the medical information includes: imaging data and information about damage to the language neural circuit provided by the patient's performance; based on the medical information, the user proposes hypotheses regarding the target damaged node and processing module in the language neural network and determines the corresponding evaluation node; the user selects the corresponding evaluation node in the original evaluation information, and the selected evaluation node is used as the current evaluation node.

[0140] In another embodiment of the present specification, comprising:

[0141] S151 searches for historical evaluation nodes;

[0142] In one embodiment of the present specification, all record files in the target case information are obtained and sorted in descending order according to the recording time; the record file ranked first is obtained, and the target damaged node recorded in the record file is used as the historical evaluation node.

[0143] It is easy to understand that the first record file is the record file most recent to the current time interval.

[0144] S152 combines the original evaluation information and the historical evaluation nodes to display target evaluation information;

[0145] Combined with the historical evaluation nodes and connection relationships, all evaluation nodes before the historical evaluation node are determined as target evaluation information.

[0146] When there is no historical evaluation node, the target evaluation information includes: all evaluation nodes in the original evaluation information.

[0147] S153 obtains the user's selection instruction based on the target evaluation information, determines the current evaluation node, and constructs current hypothesis information;

[0148] The user can select an evaluation node from the target evaluation information and use it as the current evaluation node.

[0149] Of course, the target evaluation information is only a decision aid and does not have decision-making capabilities, and the evaluation node of the non-target evaluation information is not locked; therefore, the user can select the evaluation node of the non-target evaluation information as the current evaluation node based on actual clinical experience.

[0150] In another embodiment of the present specification, imaging data of the target patient is obtained; based on the imaging data of the target patient, the user combines the entity dual-stream model and the language function module map to find the current evaluation node (language function module) to be evaluated through the hypothesis testing method offline, as a means of obtaining current hypothesis information, so as to facilitate the subsequent start of the evaluation process (steps S2-S4, etc.), determine the damaged location of the target patient, and ultimately provide the target patient with a personalized training plan.

[0151] S2 executes the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result;

[0152] Each evaluation node corresponds to a preset question bank; the preset question bank includes a number of test information, and the test information includes: questions and corresponding original answers.

[0153] In one embodiment of the present specification, a Mandarin dictionary is constructed, and a Mandarin version of a preset question bank is constructed by combining the Mandarin dictionary and preset evaluation rules.

[0154] In another embodiment of the present specification, considering that aphasia patients are generally older and have a higher degree of dialectalization, the evaluation results of the Mandarin version of the preset question bank may not be accurate. Therefore, a dialect dictionary library can be established based on dialect voice materials; based on the dialect dictionary library, the test information is replaced with the dialect version of the test information to construct a dialect version of the preset question bank.

[0155] Specifically, taking Shanghainese as an example, the present invention combines the language characteristics, cultural characteristics, and pronunciation characteristics of the Shanghai area with preset evaluation rules to redesign the question bank corresponding to the evaluation process;

[0156] A large amount of Shanghainese audio materials are collected and recorded. The audio materials cover daily life scenarios such as daily communication, medical communication, family life, shopping, restaurant ordering, public transportation, work communication and social gatherings to ensure the comprehensiveness and pertinence of the assessment; incorporating daily life scenarios into the training program can also help patients restore their language ability during the training process while enhancing their communication and social skills in real life.

[0157] Based on Shanghainese phonetic materials, a Shanghainese dictionary database is established.

[0158] Retain the original evaluation logic based on the preset evaluation rules; on this basis, based on the Shanghai dialect dictionary, replace the test information with the Shanghai dialect version of the test information. While ensuring the accuracy and effectiveness of the evaluation results, make it closer to the patient's living environment, consider the language characteristics of Shanghai dialect and the specific needs of the patient, and generate a targeted personalized training plan, thereby improving the training effect.

[0159] In one embodiment of the present specification, in the speech understanding task, design vocabulary understanding and sentence understanding tasks that conform to the pronunciation characteristics of Shanghai dialect. Enable the patient to listen to the vocabulary or sentences in Shanghai dialect and make semantic judgments. This task can cover the unique vocabulary and syntax of Shanghai dialect. For example, design corresponding judgment tasks for the negative words "呒" and "冇".

[0160] In one embodiment of the present specification, in the speech output task, design naming tasks, repetition tasks, and fluency tasks that conform to the speech characteristics of Shanghai dialect. For example, test whether the patient can accurately repeat the unique vocabulary and sentence patterns of Shanghai dialect.

[0161] In one embodiment of the present specification, in the lexical semantics task, use the vocabulary of Shanghai dialect to design tasks to test the patient's vocabulary generation and understanding abilities in a specific language environment.

[0162] The dialect version of the present invention improves the patient's sense of participation and enthusiasm during the evaluation and training process by being closer to the patient's actual life, thereby improving the compliance of treatment.

[0163] S21 Randomly extract test information with a preset quantity from the preset question bank of the current preset node to construct an evaluation plan;

[0164] S22 Display the evaluation plan to the target patient; obtain the feedback information of the target patient;

[0165] In one embodiment of the present specification, display the first question, and after obtaining the feedback information of the target patient, display the next question; until the feedback information of the target patient for the last question is obtained; or stop after obtaining the abort / termination instruction.

[0166] Among them, when it comes to obtaining the speech information of the target patient, utilize advanced speech recognition and synthesis technologies to achieve automatic recognition and conversion of Shanghai dialect speech, so as to improve the efficiency and accuracy of the evaluation and provide a more convenient evaluation experience for the patient.

[0167] S23 Compare the feedback information with the original answer to obtain the evaluation score of the target patient.

[0168] Determine the number of correct answers of the target patient by comparing the feedback information and the original answer;

[0169] In one embodiment of the present specification, the ratio of the number of correctly answered questions to the preset number of questions is used as the answer accuracy rate; and the answer accuracy rate is used as the evaluation score.

[0170] In another embodiment of the present specification, the number of correctly answered questions is used as the evaluation score.

[0171] S24 constructs an evaluation result by combining the evaluation score and the evaluation condition;

[0172] The evaluation results include: evaluation score and evaluation type;

[0173] S241 determines whether the evaluation score is within a preset threshold; if so, execute S242; otherwise, execute S243.

[0174] S242 determines that the assessment type is the first assessment type.

[0175] S243 determines that the assessment type is the second assessment type.

[0176] To improve the evaluation results, users can also manually annotate the target patient's actual speech and generate annotation information. For example, they can note whether the target patient's speech is disorganized, labored, or hollow. Therefore, the evaluation results also include annotation information.

[0177] Preferably, the evaluation result further includes status information, which is used to characterize the performance of the target patient when being evaluated at the evaluation node.

[0178] In one embodiment of the present specification, the state information includes: feedback information of the target patient. In other embodiments of the present specification, the state information also includes: demeanor information of the target patient when being evaluated at the evaluation node, action information of the target patient when being evaluated at the evaluation node, etc.

[0179] Subsequently, the present invention determines the degree of injury based on the evaluation results, providing a basis for personalized training for the patient.

[0180] S3 locates the target damaged node of the target patient based on the evaluation result;

[0181] S31, based on the evaluation type, determines whether the current evaluation node is a critical evaluation node;

[0182] S311: When the evaluation type is the first evaluation type, determining that the current evaluation node is not a critical evaluation node;

[0183] The first assessment type is used to indicate that the assessment is normal;

[0184] When the evaluation type is normal, it means that there is no obvious problem with the current evaluation node. It is necessary to search forward for evaluation nodes with problems based on the current evaluation node.

[0185] S312: when the evaluation type is the second evaluation type, determining whether the current evaluation node is a critical evaluation node based on a criticality judgment strategy;

[0186] The second assessment type is used to characterize assessment abnormalities.

[0187] S312 - 1 determines whether the current evaluation node is the original evaluation node; if so, execute S312 - 2 ; otherwise, execute S312 - 3 .

[0188] Finding the language task label corresponding to the current evaluation node as the current language task label;

[0189] The first evaluation node corresponding to the current language task label is used as the original evaluation node.

[0190] S312-2 sets the current evaluation node as a critical evaluation node;

[0191] If the current evaluation node is an original evaluation node, then determining the current evaluation node as a critical evaluation node;

[0192] Specifically, if the first evaluation node in a language task evaluates abnormally, it essentially indicates that the task cannot be completed with simpler language tasks. It is reasonable to infer that subsequent evaluation nodes are likely to also evaluate abnormally. Therefore, the current evaluation node (i.e., the original evaluation node) is identified as a critical evaluation node.

[0193] S312-3 identifies the evaluation type of the previous evaluation node of the current evaluation node to obtain an identification result; based on the identification result, determines whether the current evaluation node is the critical evaluation node.

[0194] If the current evaluation node is not the original evaluation node, identifying the evaluation type of the previous evaluation node of the current evaluation node to obtain an identification result;

[0195] Based on the identification result, it is determined whether the current evaluation node is the critical evaluation node.

[0196] Specifically, the previous evaluation node directly connected to the current evaluation node in the current language task label is used as the previous evaluation node;

[0197] If the evaluation type of the previous evaluation node is the first evaluation type, the current evaluation node is considered to be a critical evaluation node;

[0198] Specifically, if the previous assessment node corresponds to the first assessment type and the current assessment node corresponds to the second assessment type, and the patient's performance or ability at the current assessment node shows a significant decline or abnormality, the current assessment node is likely where the patient's problems began and can therefore be identified as a critical assessment node.

[0199] If the evaluation type of the previous evaluation node is the second evaluation type, it is determined that the current evaluation type is not a critical evaluation node.

[0200] If the evaluation types of the previous evaluation node and the current evaluation node are both the second evaluation type, it means that the abnormality of the current evaluation node may be a continuation of the abnormal state of the previous evaluation node, rather than the problem occurring for the first time on the current evaluation node. Therefore, the current evaluation node is not a critical point.

[0201] If the evaluation type of the previous evaluation node is empty, that is, it is necessary to evaluate other evaluation nodes before the current evaluation node or directly evaluate the previous evaluation node to find and determine the critical evaluation node.

[0202] S32: if the current evaluation node is not a critical evaluation node, re-determine a new current evaluation node; and execute a corresponding evaluation process for the target patient using the new current evaluation node;

[0203] S321 determines a new current evaluation node;

[0204] In one embodiment of the present specification, it includes:

[0205] (A-1) Collect historical case information of aphasia patients. The historical case information includes: the evaluation sequence of each evaluation node during the evaluation, the evaluation results of each evaluation node, and the damaged information flow.

[0206] (A-2) Construct training samples based on historical case information.

[0207] (A-3) Construct an evaluation node prediction model; input the original evaluation information into the evaluation sequence prediction model for pre-training.

[0208] (A-4) Input the training samples into the evaluation node prediction model to learn how to determine the next evaluation node based on the evaluation type of the current evaluation node; after the learning is completed, the evaluation sequence strategy is obtained.

[0209] (A-5) If the current evaluation node is not a critical evaluation node, a new evaluation node is determined as the current evaluation node based on the evaluation type and evaluation order strategy of the current evaluation node.

[0210] In another embodiment of the present specification, if the current evaluation node is not a critical evaluation node, predicting a new current evaluation node based on the evaluation type of the current evaluation node includes:

[0211] (B-1) determining the prediction object to be selected;

[0212] Among them, when the evaluation type of the current evaluation node is the first evaluation type, it means that the performance of the target patient at the current evaluation node is normal. Therefore, it is necessary to continue to search for the first abnormal evaluation node backward; at this time, the evaluation node after the current evaluation node is used as the candidate evaluation node.

[0213] When the evaluation type of the current evaluation node is the second evaluation type, it means that the performance of the target patient at the current evaluation node is already abnormal. Therefore, it is necessary to continue looking for the first abnormal evaluation node. At this time, the evaluation node before the current evaluation node is used as the candidate evaluation node.

[0214] Sort the candidate evaluation nodes according to the preset order and determine the new current evaluation node; specifically:

[0215] (B-2) Collect historical case information and impaired information flow of historical aphasia patients.

[0216] The historical case information includes: the evaluation results of each evaluation node during the evaluation.

[0217] (B-3) Construct training samples based on historical case information.

[0218] (B-4) Construct a probability prediction model; input the original evaluation information into the evaluation sequence prediction model for pre-training.

[0219] (B-5) Input the training samples into the probability prediction model to obtain the selection probability of each evaluation node. The selection probability can be the percentage of times each evaluation node is selected; the selection probability can also be the probability that the evaluation node is a critical evaluation node.

[0220] (B-6) Arrange the probabilities of the candidate evaluation nodes in descending order based on the selection probabilities; and use the candidate evaluation node that ranks first in the order as the new current evaluation node.

[0221] Of course, the probability prediction model of the present invention can be a decision tree. After obtaining the evaluation result of the current evaluation node, the candidate evaluation nodes and their selection probabilities are determined based on the probability prediction model to facilitate user decision-making.

[0222] In another embodiment of the present specification, all evaluation nodes may be displayed, or the candidate evaluation nodes may be displayed, and the user may manually determine a new current evaluation node;

[0223] Specifically, the damaged information flow of the target patient is determined according to the information flow where the damaged language module is located;

[0224] The user may determine a new current evaluation node based on the evaluation result of the current evaluation node and the information flow of the evaluation node; wherein the user selects an evaluation node in the evaluation interface; and the evaluation node selected by the user is identified and used as the current evaluation node.

[0225] The original assessment information of the present invention can be navigated using an intuitive flowchart, combined with speech characteristics and thinking habits, to provide users with accurate, intuitive and effective assessment methods, so as to more quickly determine the direct cause of language barriers and facilitate subsequent targeted training.

[0226] S322 re-executes S2 after determining the new current evaluation node.

[0227] S33: If the current evaluation node is a critical evaluation node, use the current evaluation node as a target damaged node.

[0228] The present invention uses hypothesis testing to infer whether aphasic patients have impairments in speech comprehension, speech output, vocabulary semantics, speech-to-graph conversion, etc., so as to facilitate users to make further decisions.

[0229] S4 predicts the damaged language modules based on all the target damaged nodes and builds a personalized training plan.

[0230] S41 determines a damaged language module based on the language task label of the target damaged node;

[0231] Identify the language task label of the current evaluation node as the target language task label;

[0232] The language module corresponding to the target language task label is used as the damaged language module:

[0233] The patient may have impairments in multiple language tasks respectively, so the number of target damaged nodes is not limited to one, that is, the number of damaged language modules is not limited to one.

[0234] S42 obtains the evaluation score of the target damaged node and determines the severity of the damaged language module;

[0235] The higher the assessment score, the lower the severity of the impaired language module.

[0236] The severity of the impaired language module is quantified based on the evaluation score. In one embodiment of this specification, when the evaluation score is the accuracy rate of the answer, the error rate of the answer is used as the severity of the impaired language module; where the error rate of the answer = (1-accuracy rate of the answer) × 100%.

[0237] In another embodiment of the present specification, when the evaluation score is the number of correctly answered questions, the severity is determined based on the difference between the preset number of questions and the evaluation score.

[0238] In another embodiment of the present specification, the gears are divided according to preset division conditions; the evaluation scores are mapped to evaluation gears; wherein the evaluation gears can be expressed in the form of: normal, near normal, partially impaired, severely impaired; the evaluation gears can be expressed in the form of: good, poor; the evaluation gears can be expressed in the form of: mild, moderate, severe, etc. The evaluation gears can be expressed in the form of: smooth, not smooth, etc.

[0239] The severity can be presented in the form of percentage, score, level, etc., and is not specifically limited here.

[0240] Specifically, publicly available medical literature and research results may be collected to construct prediction conditions; or users may independently determine or improve prediction conditions, without specific limitation herein.

[0241] In one embodiment of the present specification, the correspondence between language function modules and their severity levels is shown in Table 1:

[0242]

[0243] (Table 1)

[0244] The damaged language module and the severity of the damaged language module are used as evaluation conclusions.

[0245] S43 sends the target evaluation file to the user and obtains the prediction result fed back by the user.

[0246] Target assessment documents include: assessment results and / or assessment conclusions.

[0247] The specific content of the target assessment file can be set according to the actual situation. Users can set it to obtain only the assessment results; or only the assessment conclusions; or both the assessment results and the assessment conclusions according to actual needs.

[0248] Of course, the user can set to obtain all or part of the information in the evaluation results and / or all or part of the information in the evaluation conclusion according to actual needs.

[0249] As mentioned above, the evaluation results include one or more of: evaluation score, evaluation type, status information, and annotation information.

[0250] In one embodiment of the present specification, the evaluation results are retrieved; the target patient's status information and evaluation scores at different evaluation nodes are found and sent to the user, who makes a decision to obtain a prediction result. In one embodiment of the present specification, the prediction result includes: aphasia type.

[0251] S44 searches for the corresponding original training plan based on the prediction result.

[0252] Several training programs are pre-constructed, wherein each aphasia type corresponds to a training program; for different aphasia types, corresponding training programs need to be selected in a targeted manner.

[0253] In the present invention, after manual verification, a prediction result is obtained; the prediction result includes: a target aphasia type.

[0254] A training program corresponding to the target aphasia type is obtained as the training program for the target patient.

[0255] The present invention relies on the basic theories of neuropsychology. Through a comprehensive assessment of the patient's cognitive ability, language function and related neural mechanisms, it predicts the type and severity of aphasia in the target patient, so as to facilitate the construction of a targeted training program.

[0256] In order to improve the applicability and accuracy of the training plan, it also includes: S45 optimizes the original training plan based on the user's supplementary instructions to obtain a personalized training plan;

[0257] Personalized training programs usually include language training, cognitive training and other auxiliary rehabilitation methods, aiming to maximize the patient's language ability and promote the recovery of the patient's language function.

[0258] In one embodiment of the present specification, the user modifies the original training program based on actual experience; of course, other rehabilitation methods can also be added to obtain a final personalized training program; so as to make full use of the plasticity of the brain based on the personalized training program to assist in training patients to recover as soon as possible.

[0259] Other rehabilitation methods include but are not limited to: drug therapy, psychotherapy, and auxiliary therapy.

[0260] Psychological therapy can help patients relieve their emotions and enhance their confidence in recovery; by encouraging patients to participate in social activities, their daily communication skills can be improved.

[0261] Complementary treatments include acupuncture and modern technology. Acupuncture (such as Traditional Chinese Medicine acupuncture) can promote neurological recovery. Modern technology, such as non-invasive neuromodulation (tDCS), can also enhance training effectiveness.

[0262] In a specific scenario, the present invention can also be appropriately adjusted based on new research results and / or clinical needs, thereby improving the adaptability and scalability of the present invention; while reducing the subjectivity in manual evaluation, improving diagnostic efficiency and accuracy.

[0263] S46: updating the personalized training program based on the training status of the target patient to obtain a new personalized training program;

[0264] S461 obtains personalized training plans based on training instructions;

[0265] S462 executes a personalized training program to train the language function of the target patient;

[0266] In one embodiment of the present specification, the personalized training program includes but is not limited to: speech comprehension training, speech production training, and vocabulary and semantics training.

[0267] Among them, speech comprehension training is to restore the function of the ventral stream through auditory training and semantic matching tasks, especially for the vocabulary and sentence structure unique to Shanghainese. For example, after hearing words or sentences in Shanghainese, patients answer related comprehension questions (such as judging the meaning of words, understanding simple sentences, etc.).

[0268] Speech production training helps restore dorsal stream function through naming and repetition training, especially in Shanghainese speech production tasks, helping patients adapt to the syllable and phoneme structure of Shanghainese.

[0269] Lexical semantic training is designed based on the phonetic characteristics of Shanghainese, with corresponding vocabulary comprehension training, such as picture-vocabulary matching tasks, synonym and antonym training, semantic classification training, semantic association training, etc., to help patients understand and generate vocabulary, and thus improve their communication ability in Shanghainese.

[0270] After the training is completed, S463 performs evaluation according to S1-S3 and optimizes the training plan based on the evaluation results.

[0271] Regular evaluations are conducted during the training process to facilitate timely adjustments to the personalized training program. Specifically, the present invention collects the patient's training data, analyzes it, evaluates the patient's progress in real time, and continuously adjusts the personalized training program based on the feedback, after obtaining the patient's consent.

[0272] In one embodiment of the present specification, if the patient responds well to the lexical semantic task, the difficulty of the task can be increased to conduct training on more complex word semantics.

[0273] For patients with poor speech fluency, more speech fluency training can be added to gradually improve the patient's language output speed and accuracy.

[0274] If the patient has difficulty understanding Shanghainese dialect vocabulary, additional training tasks in local phonetics and semantics can be added to help him or her better understand the dialect.

[0275] The present invention can record the patient's assessment data and treatment progress, and help doctors adjust treatment plans through data analysis to achieve dynamic management. After the treatment, follow-up visits are conducted to understand the patient's recovery status and collect feedback.

[0276] In other embodiments of this specification, users can also develop personalized home training plans based on the patient's specific situation and family environment; in order to enable them to meet the needs of home training, the present invention can also display educational content, detailed operating guides and video tutorials through the education module.

[0277] Among them, educational content is used to provide information on basic knowledge, communication skills, psychological support, etc. about aphasia, to help family members better understand and support patients.

[0278] Through detailed operation guides and video tutorials, family members can learn how to assist patients in training, so as to improve patient participation and training results.

[0279] Patients can complete home training by simulating actual communication scenarios, participating in interesting training tasks, and improving their daily communication skills and quality of life, thereby reducing the burden on their families and society.

[0280] To facilitate training tracking, you can also record training logs based on the logging module. The training logs include: the patient's training process, training progress, and changes. Then, call the record creation submodule, create a new record file, and record the training logs in the record file. To facilitate users to keep abreast of the progress of home training, you can also call the training log from the logging module through the feedback module to display the target patient's training process, so that users can keep abreast of the target patient's training status and adjust the training plan.

[0281] Figure 3 This is a schematic diagram of a personalized solution recommendation system for aphasia provided in an embodiment of this specification. The system includes:

[0282] An information acquisition module is used to acquire current hypothesis information; the current hypothesis information includes: a current evaluation node;

[0283] An evaluation module, configured to execute the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result;

[0284] a node positioning module, configured to locate a target damaged node of the target patient based on the evaluation result;

[0285] The personalized program construction module is used to predict the damaged language module based on all the target damaged nodes and construct a personalized training program.

[0286] Optionally, the information acquisition module includes:

[0287] The hypothesis submodule is used to display original evaluation information based on the user's evaluation instruction; the original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes;

[0288] The selection module is configured to determine, based on the user's selection instruction, a current evaluation node obtained based on a hypothesis testing method as current hypothesis information.

[0289] Optionally, the evaluation result includes: evaluation type;

[0290] Optionally, the positioning module includes:

[0291] A first judgment submodule, configured to judge whether the current evaluation node is a critical evaluation node based on the evaluation type;

[0292] A first positioning submodule is configured to, if the current evaluation node is not a critical evaluation node, redetermine a new current evaluation node; and execute a corresponding evaluation process on the target patient using the new current evaluation node;

[0293] The second positioning submodule is configured to use the current evaluation node as a target damaged node if the current evaluation node is a critical evaluation node.

[0294] Optionally, the first judgment submodule includes:

[0295] a first judgment unit, configured to determine that the current evaluation node is not a critical evaluation node when the evaluation type is a first evaluation type; the first evaluation type is used to indicate that the evaluation is normal;

[0296] The second judgment unit is configured to judge whether the current evaluation node is a critical evaluation node based on a criticality judgment strategy when the evaluation type is a second evaluation type; the second evaluation type is used to characterize evaluation anomalies.

[0297] Optionally, the first positioning submodule includes:

[0298] An information flow identification unit, configured to identify the information flow at which the current evaluation node is located;

[0299] The node updating unit is used to determine a new current evaluation node according to the evaluation result of the current evaluation node and the information flow in which it is located.

[0300] Optionally, each evaluation node corresponds to a preset question bank; the preset question bank includes a plurality of test information;

[0301] Optionally, the evaluation module further includes:

[0302] The dialect dictionary library establishment submodule is used to establish a dialect dictionary library based on dialect voice materials;

[0303] The replacement submodule is used to replace the test information with the test information of the dialect version based on the dialect dictionary library, and construct a preset question bank of the dialect version.

[0304] Optionally, also include:

[0305] The updating module is used to update the personalized training program in combination with the training situation of the target patient to obtain a new personalized training program.

[0306] The functions of the system of the embodiment of the present invention have been described in the above method embodiment. Therefore, for details not fully described in this embodiment, please refer to the relevant descriptions in the above embodiment and will not be repeated here.

[0307] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0308] The following describes an electronic device embodiment of the present invention. This electronic device can be considered a physical implementation of the method and apparatus embodiments of the present invention described above. Details described in the electronic device embodiment of the present invention should be considered supplementary to the above-described method or apparatus embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above-described method or apparatus embodiments.

[0309] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 4 The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0310] like Figure 4As shown, the computer device 400 of this exemplary embodiment is in the form of a general-purpose data processing device. Components of the computer device 400 may include, but are not limited to, at least one processor 410, at least one memory 420, a network interface 430, a display unit 440, an input component 450, and the like.

[0311] The memory 420 stores a computer-readable program, which may be a source program or a code of a read-only program. The program may be executed by the processor 410, so that the processor 410 performs the steps of various embodiments of the present invention. For example, the processor 410 may perform the following steps: Figure 1 Steps shown.

[0312] The memory 420 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM) and / or a cache memory unit, and may further include a read-only memory unit (ROM). The memory 420 may also include a program / utility having a set (at least one) of program modules, such as, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment.

[0313] Also included is a bus (not shown) that can represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0314] The computer device 400 may also communicate with one or more external devices (e.g., a keyboard, a display, a network device, a Bluetooth device, etc.) to enable a user to interact with the computer device 400 via these external devices, and / or to enable the computer device 400 to communicate with one or more other data processing devices (e.g., a router, a modem, etc.). Such communication may be performed via a network interface 430, or via a network adapter to one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet). The network adapter may communicate with other modules of the computer device 400 via a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in the computer device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0315] Figure 5 Schematic diagram of a computer readable medium embodiment of the present invention. Figure 5As shown, the computer program can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. When the computer program is executed by one or more data processing devices, the computer-readable medium is enabled to implement the above-mentioned method of the present invention.

[0316] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, and includes several instructions to enable a data processing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention.

[0317] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0318] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0319] In summary, the present invention can be implemented by a method, apparatus, electronic device or computer-readable medium that executes a computer program. In practice, a general-purpose data processing device such as a microprocessor or a digital signal processor (DSP) can be used to implement some or all of the functions of the present invention.

[0320] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A personalized solution recommendation method for aphasia, characterized in that: include: Obtaining current hypothesis information includes: displaying original evaluation information based on a user's evaluation instruction; the original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes; based on the user's selection instruction, determining a current evaluation node obtained based on a hypothesis testing method as current hypothesis information; the current hypothesis information includes: the current evaluation node; Executing the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result; the evaluation result includes: an evaluation type; Locating a target damaged node of the target patient based on the evaluation result, including: determining whether the current evaluation node is a critical evaluation node based on the evaluation type; if the current evaluation node is not a critical evaluation node, re-determining a new current evaluation node; executing a corresponding evaluation process on the target patient using the new current evaluation node; if the current evaluation node is a critical evaluation node, using the current evaluation node as a target damaged node; Based on all the target damaged nodes, the damaged language modules are predicted and a personalized training plan is constructed.

2. A personalized solution recommendation method for aphasia according to claim 1, characterized in that: The determining, based on the evaluation type, whether the current evaluation node is a critical evaluation node includes: When the evaluation type is the first evaluation type, it is determined that the current evaluation node is not a critical evaluation node; the first evaluation type is used to indicate that the evaluation is normal; When the evaluation type is the second evaluation type, whether the current evaluation node is a critical evaluation node is determined based on a criticality judgment strategy; the second evaluation type is used to characterize evaluation anomalies.

3. The personalized solution recommendation method for aphasia according to claim 1, characterized in that: If the current evaluation node is not a critical evaluation node, a new current evaluation node is re-determined, and a corresponding evaluation process is performed on the target patient using the new current evaluation node, including: Identifying the information flow where the current evaluation node is located; A new current evaluation node is determined according to the evaluation result of the current evaluation node and the information flow in which it is located.

4. The personalized solution recommendation method for aphasia according to claim 1, characterized in that: Each evaluation node corresponds to a preset question bank; the preset question bank includes a number of test information; The step of executing the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result further includes: Establish a dialect dictionary based on dialect phonetic materials; Based on the dialect dictionary library, the test information is replaced with the dialect version of the test information to construct a dialect version of the preset question bank.

5. The personalized solution recommendation method for aphasia according to claim 1, characterized in that: Also includes: In combination with the training situation of the target patient, the personalized training program is updated to obtain a new personalized training program.

6. A personalized solution recommendation system for aphasia, characterized in that: include: The information acquisition module is used to obtain current hypothesis information, including: based on the user's evaluation instruction, displaying original evaluation information; the original evaluation information includes: a plurality of evaluation nodes and a plurality of directed connection relationships; each of the connection relationships connects two evaluation nodes; based on the user's selection instruction, determining the current evaluation node obtained based on the hypothesis testing method as the current hypothesis information; the current hypothesis information includes: the current evaluation node; An evaluation module is configured to execute the evaluation process corresponding to the current evaluation node on the target patient to obtain an evaluation result; the evaluation result includes: an evaluation type; a node positioning module, configured to locate a target damaged node of the target patient based on the assessment result, comprising: determining, based on the assessment type, whether the current assessment node is a critical assessment node; if the current assessment node is not a critical assessment node, re-determining a new current assessment node; executing a corresponding assessment process on the target patient using the new current assessment node; and if the current assessment node is a critical assessment node, using the current assessment node as a target damaged node; The personalized program construction module is used to predict the damaged language module based on all the target damaged nodes and construct a personalized training program.

7. An electronic device, wherein: The electronic device includes: processor; and, A memory storing computer executable instructions which, when executed, cause the processor to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 5 is implemented.

Images