Method and device for determining cognitive training content, computer device and medium

Abstract

The application discloses a method and device for determining cognitive training content, computer equipment and a medium, and relates to the technical field of intelligent medical treatment. The specific implementation includes: obtaining personal basic information and cognitive condition test results of a first target object, wherein the cognitive condition test results include test results of multiple cognitive domains; inputting the personal basic information and the cognitive condition test results into a training content prediction model, and obtaining a cognitive training scheme suitable for the first target object through the training content prediction model, wherein the cognitive training scheme includes training content of multiple cognitive domains, each training content corresponds to a training duration and a training difficulty level, and the training content prediction model is obtained by training a machine learning component with historical personal basic information, historical cognitive condition test results and corresponding historical cognitive training schemes as samples. The scheme automatically and intelligently determines an accurate, suitable and personalized cognitive training scheme for each first target object.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to the field of smart healthcare technology, and in particular to methods, devices, computer equipment, and media for determining cognitive training content. Background Technology

[0002] Currently, doctors conduct cognitive tests on patients using intelligent electronic systems or traditional paper-and-pen scales. However, cognitive assessment encompasses multiple dimensions, such as memory, executive function, attention, language ability, and visuospatial construction ability. Therefore, doctors use multiple dimensions of testing, requiring significant time and effort to guide patients through the process. The test results serve as data for rehabilitation programs, helping to select appropriate training plans. However, in reality, the complexity of rehabilitation programs due to the numerous testing dimensions often makes it difficult to assess training effectiveness. The problem of selecting suitable training content for patient rehabilitation remains unresolved.

[0003] However, due to the numerous dimensions of cognitive testing and the extensive content within each dimension, coupled with the complexity of patients' conditions, the selection of training programs requires reliance on the doctor's experience, increasing their workload. Furthermore, the varying experience and individual differences among doctors lead to inconsistent standards in the chosen training programs, affecting their accuracy and reliability. Additionally, the inherent inaccuracies and unreliability in program selection necessitate a cyclical process: patients undergo rehabilitation training for a specific period, followed by testing by the doctor. Comparing the pre- and post-training results helps determine if adjustments to the training content are necessary. This cyclical process further extends the patient's training cycle, impacting both the effectiveness and progress of the training. Summary of the Invention

[0004] To address the technical problem of low accuracy in determining training schemes, a method, device, electronic device, and storage medium for determining cognitive training content are provided.

[0005] According to the first aspect, a method for determining cognitive training content is provided, including:

[0006] Obtain the basic personal information and cognitive test results of the first target object, wherein the cognitive test results include test results of multiple cognitive domains;

[0007] The personal basic information and the cognitive test results are input into the training content prediction model. The cognitive training scheme adapted to the first target object is obtained through the training content prediction model. The cognitive training scheme includes training content in multiple cognitive domains. Each training content has a corresponding training duration and training difficulty level. The training content prediction model is obtained by training machine learning components using historical personal basic information, historical cognitive test results and corresponding historical cognitive training schemes as samples.

[0008] According to the second aspect, a device for determining cognitive training content is provided, comprising:

[0009] An information acquisition unit is used to acquire basic personal information and cognitive test results of the first target object, wherein the cognitive test results include test results of multiple cognitive domains;

[0010] The training content determination unit is used to input the personal basic information and the cognitive test results into the training content prediction model, and obtain a cognitive training scheme adapted to the first target object through the training content prediction model. The cognitive training scheme includes training content in multiple cognitive domains, and each training content corresponds to a training duration and a training difficulty level. The training content prediction model is obtained by training machine learning components using historical personal basic information, historical cognitive test results and corresponding historical cognitive training schemes as samples.

[0011] According to a third aspect, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a method such as any embodiment of the method for determining cognitive training content.

[0012] According to a fourth aspect, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method of any embodiment of the method for determining cognitive training content.

[0013] According to the scheme of this application, a training content prediction model is used to automatically and intelligently determine a cognitive training scheme suitable for the first target object based on their basic personal information and cognitive test results. This cognitive training scheme includes training content across multiple cognitive domains, with each training content corresponding to a training duration and difficulty level. This achieves automated and intelligent determination of accurate, suitable, and personalized cognitive training schemes for each first target object, avoiding problems such as the impact of manual selection of training content on the accuracy and reliability of the training scheme selection. This improves the accuracy, reliability, and suitability of the training scheme selection, thereby enhancing training effectiveness, shortening the training cycle, or preventing delays in training progress. Attached Figure Description

[0014] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0015] Figure 1 This is an exemplary system architecture diagram in which some embodiments of this application can be applied;

[0016] Figure 2 This is a flowchart of an embodiment of the method for determining cognitive training content according to this application;

[0017] Figure 3 This is a schematic diagram of an application scenario of the method for determining cognitive training content according to this application;

[0018] Figure 4 This is a schematic diagram of the structure of one embodiment of the cognitive training content determination device according to this application;

[0019] Figure 5 This is a block diagram of an electronic device used to implement the method for determining cognitive training content in the embodiments of this application. Detailed Implementation

[0020] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Figure 1 An exemplary system architecture 100 is shown, which can be applied to an embodiment of the method or apparatus for determining cognitive training content of this application.

[0023] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0024] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as video applications, live streaming applications, instant messaging tools, email clients, social media platform software, etc.

[0025] The terminal devices 101, 102, and 103 here can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays, including but not limited to smartphones, tablets, e-book readers, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., multiple software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are imposed here.

[0026] Server 105 can be a server that provides various services, such as a backend server that supports terminal devices 101, 102, and 103. The backend server can analyze and process the received personal basic information and cognitive test results, and feed back the processing results (such as an adapted cognitive training scheme) to the terminal devices.

[0027] It should be noted that the method for determining cognitive training content provided in this application embodiment can be executed by server 105 or terminal devices 101, 102, 103. Accordingly, the device for determining cognitive training content can be set in server 105 or terminal devices 101, 102, 103.

[0028] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0029] Continue to refer to Figure 2 The flowchart 200 illustrates an embodiment of a method for determining cognitive training content according to this application. The method for determining cognitive training content includes the following steps:

[0030] Step 201: Obtain the basic personal information and cognitive test results of the first target object, wherein the cognitive test results include test results of multiple cognitive domains;

[0031] Step 202: Input the personal basic information and the cognitive test results into the training content prediction model, and obtain a cognitive training scheme adapted to the first target object through the training content prediction model. The cognitive training scheme includes training content in multiple cognitive domains, and each training content corresponds to a training duration and a training difficulty level. The training content prediction model is obtained by training machine learning components using historical personal basic information, historical cognitive test results and corresponding historical cognitive training schemes as samples.

[0032] In some optional implementations of this embodiment, the above-mentioned method for determining cognitive training content automatically and intelligently determines an accurate, suitable, and personalized set of cognitive training schemes including multiple cognitive domains for each first target object. This avoids problems such as the impact on the accuracy and reliability of training scheme selection caused by manual selection of training content. It is beneficial to improve the accuracy, reliability, suitability, and efficiency of training scheme selection, thereby improving training effect, shortening the training cycle, or avoiding delays in training progress.

[0033] In some optional implementations of this embodiment, the cognitive domain may include memory, executive function, attention, language ability, visuospatial construction ability (or visuospatial and structural ability), and reasoning ability, etc.

[0034] In some optional implementations of this embodiment, the above-mentioned cognitive status test results include test results of multiple cognitive domains. The specific presentation form of the test results of each cognitive domain is not specifically limited, as long as it can represent and clearly indicate the cognitive status of the corresponding cognitive domain. For example, it can be in the form of numerical values ​​or in the form of textual descriptions.

[0035] In some optional implementations of this embodiment, each cognitive domain includes one or more test contents. The specific content of the test contents for each cognitive domain is not limited in this application; test contents in the form of video and / or audio, physical tools, etc., as used in the prior art can be used. Each cognitive domain includes one or more training test contents. The specific content of the training contents for each cognitive domain is also not limited in this application; training contents in the form of video and / or audio, etc., as used in the prior art can be used. However, it should be noted that the training contents include question-and-answer content, that is, the training contents include question-and-answer content. During training, the trainee needs to interact and answer the questions. The implementation program or running device of the training contents can determine the correctness of each question based on the answer content (e.g., correct answer, incorrect answer, etc.). It can also count the time taken to answer each question, for example, the time from asking a question to receiving the answer content as the time taken to answer each question, or the time from asking a question to receiving the click operation of the answer as the time taken to answer each question, etc.

[0036] In some optional implementations of this embodiment, each test item within each cognitive domain may include multiple training items of varying training durations and difficulties, such as training items of 10 minutes, 20 minutes, and 30 minutes. Target subjects requiring higher cognitive training difficulty require longer training content. The cognitive training difficulty can be determined based on the target subject's specific cognitive abilities. For example, if the cognitive training difficulty includes different levels such as easy, medium, and difficult, then the easy level could correspond to 10 minutes of training content, the medium level to 20 minutes, and the difficult level to 30 minutes. Different training items may also correspond to different playback frequencies and other information.

[0037] In some optional implementations of this embodiment, in order to improve the performance and accuracy of the training content prediction model so that a suitable cognitive training scheme can be predicted for each first target object, this embodiment proposes to determine the training value of the training content and adjust the training content included in the historical cognitive training scheme according to different preset thresholds and training values, so as to adjust the proportion or weight of the training content with higher fitness in the training samples, thereby improving the training effect of the training content prediction model. For example, the training value of each training content is determined based on the historical time taken by the second target object to answer each question and the historical correct answers to each question when using each training content. The larger the training value, the lower the training fitness of the training content.

[0038] The training content in the historical cognition training scheme with training values ​​greater than the preset threshold is deleted multiple times using different preset thresholds (in order to increase the proportion or weight of training content with high fit in the training samples). The training content included in the historical cognition training scheme is adjusted multiple times. The historical personal basic information, the historical cognition test results and the historical cognition training scheme after each adjustment are input into the machine learning component for training to obtain the training content prediction model.

[0039] In some optional implementations of this embodiment, in order to improve the accuracy and prediction effect of the training content prediction model, this embodiment implements the following steps to repeatedly delete training content in the historical cognition training scheme whose training value is greater than the preset threshold using different preset thresholds, so as to adjust the training content included in the historical cognition training scheme multiple times. The historical personal basic information, the historical cognition test results, and the historical cognition training scheme after each adjustment are input into the machine learning component for training:

[0040] Repeat the following steps:

[0041] Among the training values ​​of each training content in all the current historical cognition training schemes, determine the largest training value, and determine the preset threshold corresponding to the largest training value according to the correspondence between the training value and the preset threshold.

[0042] In all current historical cognitive training schemes, delete training content whose training value is greater than a predetermined preset threshold to obtain the current adjusted historical cognitive training scheme.

[0043] The historical personal basic information, the historical cognitive test results, and the currently adjusted historical cognitive training scheme are input into a linear regression model for training. In the linear regression model, a current linear function is constructed between the historical training time of the historical cognitive training scheme and the historical training score of the historical cognitive training scheme. The slope of the current linear function is determined as the current slope.

[0044] Determine whether the current slope is greater than the previous slope. If not, end the loop and determine the current linear function as the training content prediction model. The previous slope is the slope of the previously constructed linear function. That is, after adjusting the training content included in the historical cognitive training scheme based on the previous preset threshold, the previous linear function is constructed based on the historical training time and historical training score of the adjusted historical cognitive training scheme. This previous linear function is the linear function constructed in the previous step.

[0045] In some optional implementations of this embodiment, during the training of the above-mentioned training content prediction model, the machine learning component can be a neural network model of various network architectures, or a linear model with linear relationships. For example, in this embodiment, in order to improve the prediction accuracy of the training content prediction model, a linear regression model is proposed to obtain the above-mentioned training content prediction model.

[0046] In some optional implementations of this embodiment, during cognitive training using a cognitive training scheme, a shorter training time and a higher training score indicate a better training effect, higher training efficiency, and a higher degree of fit with the trainee. To enable the training content prediction model to accurately determine and predict the cognitive training scheme that best suits the first target object, a formula is proposed for the current linear function relating the historical training time and historical training score of historical cognitive training schemes in the linear regression model, as follows:

[0047] Y = K * X + B

[0048] Where Y represents the historical training score of the historical cognition training scheme; X represents the historical training time of the historical cognition training scheme; K represents the current slope; and B is a constant. When the value of K is the highest, it indicates that the accuracy of the training content prediction model is the highest. Therefore, the training process of the training content prediction model is essentially a process of continuously adjusting the sample data through preset thresholds and training values ​​to determine the maximum value of K.

[0049] In some optional implementations of this embodiment, in order to accurately determine the training value of each training content, this embodiment proposes to determine the training value of each training content based on the historical time taken to answer each question and the historical correct answers for each question when training the second target object with each training content, including:

[0050] The training value for each training content is determined by using a decision tree based on the historical time taken to answer each question during training for the second target object and the historical correct answers for each question.

[0051] In some optional implementations of this embodiment, the historical time taken by the trainee to answer each question and the historical correct answers are obtained when cognitive training is performed using each training content through decision tree analysis. The historical time taken to answer each question and the historical correct answers are mapped one-to-one with the non-leaf nodes of the decision tree, and the training value of each training content is mapped with the leaf nodes of the decision tree to obtain the training value of each training content.

[0052] In some optional implementations of this embodiment, in order to obtain effective sample data for training the above-mentioned training content prediction model, the following method is proposed to select historical cognitive training schemes as samples:

[0053] When multiple alternative historical cognition training schemes are determined based on the historical personal basic information and the test results of the historical cognition of the second target object, the second target object is trained alternately using two alternative historical cognition training schemes to obtain the historical training time and historical training score of each alternative historical cognition training scheme.

[0054] Based on the historical training time and historical training score of each candidate historical cognition training program, the fit value of each candidate historical cognition training program is determined. The smaller the fit value, the higher the fit of the historical cognition training program.

[0055] Based on the fit values ​​of multiple alternative historical cognition training schemes, the alternative historical cognition training scheme with the smallest fit value is determined as the historical cognition training scheme for the second target object.

[0056] Specifically, for example, given four alternative historical cognition training schemes (a, b, c, and d), schemes a and b are first selected for alternating cognitive training of the second target object. After training, the training score and training time for the second target object are displayed respectively. The fit values ​​of the two alternative historical cognition training schemes (a and b) are compared; the scheme with the lower fit value has a relatively higher fit. When scheme a is a better fit, scheme b is filtered out and replaced with scheme c. Then, schemes a and c are alternately trained, and so on, until the scheme with the highest fit is selected as the historical cognition training scheme for the second target object.

[0057] In some optional implementations of this embodiment, in order to improve the effectiveness of the adaptation value and enable the adaptation value to accurately represent the adaptation degree of each scheme, this embodiment proposes to determine the adaptation value of each candidate historical cognitive training scheme based on the historical training time and historical training score of each candidate historical cognitive training scheme, including:

[0058] Weights are assigned to the historical training time and the historical training score. The historical training time is multiplied by its own weight to obtain a first product. The historical training score is multiplied by its own weight to obtain a second product. The sum of the first product and the second product is determined as the adaptation value. The weight of the historical training time is greater than the weight of the historical training score.

[0059] In some optional implementations of this embodiment, the historical training time can be the actual time taken from the start to the end of cognitive training, or it can be the average or minimum historical time taken to answer each question in each training content included in the historical cognitive training scheme. The historical training score can be the number of correct answers in the historical correct cases for each question in each training content included in the historical cognitive training scheme.

[0060] In some optional implementations of this embodiment, the aforementioned basic personal information and historical basic personal information can be basic personal information, such as age, gender, education level, cognitive status, medical history, contact information, etc.

[0061] In some optional implementations of this embodiment, in order to improve the accuracy of determining and predicting cognitive training schemes, it is proposed that the above-mentioned cognitive test results and historical cognitive test results should include tests of each cognitive domain as shown in Table 1 below, and the test of each cognitive domain should include the test contents shown in Table 1. For example, for the cognitive domain test of memory, it should include 11 test contents, namely working memory, object recognition, associative memory, digit breadth ascending order, digit breadth descending order, spatial breadth, episodic memory test, visual graphics task, delayed recall-object recognition, delayed recall-episodic memory, and delayed recall-visual graphics.

[0062] Table 1

[0063]

[0064] In some optional implementations of this embodiment, the first target object and the second target object may be the same person or different people. The first target object and the second target object may be any person who needs cognitive training, for example, a person with cognitive impairment problems caused by different reasons such as age, disease, or brain injury.

[0065] The following details the process of training a content prediction model, which includes the following steps:

[0066] Step 1: Doctors and other personnel establish an electronic file (i.e., the above-mentioned historical personal basic information) based on the patient's (i.e., the second target subject) cognition, including: age, gender, education, current medical history, and contact information.

[0067] Step 2: Doctors and other personnel conduct comprehensive or rapid cognitive tests on patients (the tests include cognitive domains such as memory, executive function, visuospatial and structural abilities, and reasoning ability). After the tests, detailed tests are conducted on individual cognitive domains based on the results (the test content for each cognitive domain can be automatically matched using the existing system). After matching, the patient takes the test. After the test is completed, a report (i.e., the historical cognitive test results mentioned above) and a cognitive training plan (i.e., the historical cognitive training plan mentioned above, which is obtained by matching the individual cognitive domain test results with the cognitive training plan) are generated.

[0068] Step 3: Since different cognitive training programs may be used for the same patient, the training effects will vary. Therefore, when multiple cognitive training programs (a, b, c, d) are obtained based on the patient's electronic records and test results, programs a and b can be used alternately for a certain period of time in a certain proportion. This allows for comparison of the fit between programs a and b for the patient. The program with the lower training score (i.e., the lower fit value) is selected. When program a is a better fit, program b is discarded and replaced with program c. Programs a and c are then used alternately for training. The better fit program is then selected from programs a and c. This process is repeated until the most suitable training program is obtained and used as the patient's cognitive training program. The cognitive training programs for each patient constitute the training sample data for the above-mentioned training content prediction model.

[0069] Step 4: During the training of the prediction model, increase the weights of training schemes with higher fit in the sample data. For example, after selecting the most suitable training scheme for each patient, the patient uses this training scheme for training. During training, the training scheme records the time between each click as the reaction time (i.e., the historical time taken by the patient to answer each question in the above test content), and records the result of each answer (i.e., the historical correctness of the patient's answers to each question in the above test content). After all training schemes are completed, the training score and training time of the training scheme will be displayed. First, use decision trees to analyze the reaction time and answer results, and then select the training content with the longest reaction time and the worst answer result, that is, the training content with the largest training value, which is denoted as Z. Then, linear regression is used to analyze the training time and training score, constructing a linear function Y = K*X + B, where X is the training time and Y is the training score. Based on the results of 7 training sessions per week, the values ​​of K and B are obtained. A larger K value indicates shorter training time, higher scores, better training effect, and higher training efficiency, i.e., higher fitness. A preset threshold is determined by the maximum training value Z. Training content with values ​​greater than the preset threshold is then removed from the training scheme to adjust the training content included in the scheme. This adjusts the weights of training schemes with higher fitness in the sample data. The adjusted training scheme is then used to construct the linear function Y = K*X + B. This process of adjusting the training scheme and constructing the linear function Y = K*X + B is repeated multiple times until the K value is maximized. Training is then stopped. The linear function with the maximum K value is the training content prediction model obtained above.

[0070] Step 5: Using real user data obtained from steps 1-3 and real user training data from a large number of real users as sample data, select a portion of the sample data to adjust and validate the training content prediction model, and obtain the trained target model. This model can then be used to determine and predict suitable cognitive training schemes for different primary target objects.

[0071] See also Figure 3 , Figure 3 This is a schematic diagram illustrating an application scenario of the cognitive training content determination method according to this embodiment. Figure 3 In the application scenario, the execution entity 301 obtains the basic personal information 302 and cognitive test results 303 of the first target object, wherein the cognitive test results include test results of multiple cognitive domains. The execution entity 301 inputs the basic personal information and the cognitive test results into a training content prediction model, and obtains a cognitive training scheme 304 adapted to the first target object through the training content prediction model. The cognitive training scheme includes training content for multiple cognitive domains, each training content corresponding to a training duration and a training difficulty level. The training content prediction model is obtained by training machine learning components using historical basic personal information, historical cognitive test results, and corresponding historical cognitive training schemes as samples.

[0072] Further reference Figure 4 As an implementation of the methods shown in the above figures, this application provides an embodiment of a device for determining cognitive training content, which is similar to... Figure 2 Corresponding to the method embodiment shown, in addition to the features described below, the device embodiment may also include [features related to...]. Figure 2 The method embodiments shown have the same or corresponding features or effects. This device can be specifically applied to various electronic devices.

[0073] like Figure 4 As shown, the cognitive training content determination device 400 of this embodiment includes an information acquisition unit 401 and a training content determination unit 402. The information acquisition unit 401 is configured to acquire basic personal information and cognitive test results of a first target object, wherein the cognitive test results include test results for multiple cognitive domains. The training content determination unit 402 is configured to input the basic personal information and the cognitive test results into a training content prediction model, and obtain a cognitive training scheme adapted to the first target object through the training content prediction model. The cognitive training scheme includes training content for multiple cognitive domains, each training content corresponding to a training duration and a training difficulty level. The training content prediction model is obtained by training machine learning components using historical basic personal information, historical cognitive test results, and corresponding historical cognitive training schemes as samples.

[0074] In this embodiment, the specific processing of the information acquisition unit 401 and the training content determination unit 402 of the cognitive training content determination device 400, and the resulting technical effects, can be referred to respectively. Figure 2 The relevant descriptions of steps 201 and 202 in the corresponding embodiments will not be repeated here.

[0075] In some optional implementations of this embodiment, the training content for each cognitive domain includes question-and-answer content, the historical cognitive training scheme includes training content for multiple cognitive domains, and the sample further includes the historical time taken by the second target object to answer each question when training with each training content, the historical correctness of answering each question, the historical training time of each historical cognitive training scheme, and the historical training score of each historical cognitive training scheme; the above device further includes:

[0076] The training value determination unit is configured to determine the training value of each training content based on the historical time taken to answer each question and the historical correctness of answering each question when the second target object is trained with each training content, wherein the larger the training value, the lower the training fit of the training content.

[0077] The training unit is configured to repeatedly delete training content in the historical cognition training scheme whose training value is greater than the preset threshold using different preset thresholds, so as to adjust the training content included in the historical cognition training scheme multiple times. The historical personal basic information, the historical cognition test results, and the historical cognition training scheme after each adjustment are input into the machine learning component for training to obtain the training content prediction model.

[0078] In some optional implementations of this embodiment, the training unit is configured to repeatedly execute the following steps:

[0079] Among the training values ​​of each training content in all the current historical cognition training schemes, determine the largest training value, and determine the preset threshold corresponding to the largest training value according to the correspondence between the training value and the preset threshold.

[0080] In all current historical cognitive training schemes, delete training content whose training value is greater than a predetermined preset threshold to obtain the current adjusted historical cognitive training scheme.

[0081] The historical personal basic information, the historical cognitive test results, and the currently adjusted historical cognitive training scheme are input into a linear regression model for training. In the linear regression model, a current linear function is constructed between the historical training time of the historical cognitive training scheme and the historical training score of the historical cognitive training scheme. The slope of the current linear function is determined as the current slope.

[0082] Determine whether the current slope is greater than the previous slope. If not, end the loop and determine the current linear function as the training content prediction model, where the previous slope is the slope of the previously constructed linear function.

[0083] In some optional implementations of this embodiment, the training value determination unit is configured to determine the training value of each training content by using a decision tree based on the historical time taken to answer each question when the second target object is trained with each training content and the historical correct answers to each question.

[0084] In some optional implementations of this embodiment, the apparatus further includes:

[0085] The alternating training unit is configured to, when multiple alternative historical cognition training schemes are determined based on the historical personal basic information and the test results of the historical cognition of the second target object, use two alternative historical cognition training schemes to perform alternating training on the second target object, and obtain the historical training time and historical training score of each alternative historical cognition training scheme.

[0086] The adaptation value determination unit is configured to determine the adaptation value of each candidate historical cognitive training scheme based on the historical training time and historical training score of each candidate historical cognitive training scheme. The smaller the adaptation value, the higher the adaptation degree of the historical cognitive training scheme.

[0087] The scheme selection unit is configured to determine the historical cognitive training scheme with the smallest fit value as the historical cognitive training scheme for the second target object based on the fit values ​​of multiple alternative historical cognitive training schemes.

[0088] In some optional implementations of this embodiment, the adaptation value determination unit is configured to: assign weights to the historical training time and the historical training score respectively; multiply the historical training time by its own weight to obtain a first product; multiply the historical training score by its own weight to obtain a second product; and determine the sum of the first product and the second product as the adaptation value, wherein the weight of the historical training time is greater than the weight of the historical training score.

[0089] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0090] like Figure 5The diagram shown is a block diagram of an electronic device for determining cognitive training content according to an embodiment of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0091] like Figure 5 As shown, the electronic device includes one or more processors 501, a memory 502, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 501 as an example.

[0092] The memory 502 is the non-transitory computer-readable storage medium provided in this application. The memory stores instructions executable by at least one processor to cause at least one processor to perform the method for determining cognitive training content provided in this application. The non-transitory computer-readable storage medium of this application stores computer instructions for causing a computer to perform the method for determining cognitive training content provided in this application.

[0093] Memory 502, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for determining cognitive training content in the embodiments of this application (e.g., appendix). Figure 4 The information acquisition unit 401 and training content determination unit 402 are shown. The processor 501 executes various functional applications and data processing of the server by running non-transient software programs, instructions and modules stored in the memory 502, that is, it implements the cognitive training content determination method in the above method embodiment.

[0094] Memory 502 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the electronic device according to the method for determining cognitive training content. Furthermore, memory 502 may include high-speed random access memory and may also include non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. In some embodiments, memory 502 may optionally include memory remotely located relative to processor 501, and these remote memories can be connected to the electronic device for determining the method of cognitive training content via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0095] The electronic device for determining cognitive training content may further include an input device 503 and an output device 504. The processor 501, memory 502, input device 503, and output device 504 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0096] Input device 503 can receive input digital or character information, as well as key signal inputs related to user settings and function control of the video frame processing electronic device, such as touch screens, keypads, mice, trackpads, touchpads, joysticks, one or more mouse buttons, trackballs, joysticks, etc. Output device 504 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The display device may include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device may be a touch screen.

[0097] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] These computational programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0100] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0101] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0103] The units described in the embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an information acquisition unit and a training content determination unit. The names of these units do not necessarily limit the specific unit; for example, the information acquisition unit may also be described as a "unit for acquiring information."

[0104] In another aspect, this application also provides a computer-readable medium, which may be included in the apparatus described in the above embodiments; or it may exist independently and not assembled into the apparatus. The computer-readable medium carries one or more programs, which, when executed by the apparatus, cause the apparatus to: acquire basic personal information and cognitive test results of a first target object, wherein the cognitive test results include test results for multiple cognitive domains; input the basic personal information and the cognitive test results into a training content prediction model; and obtain a cognitive training scheme adapted to the first target object through the training content prediction model, wherein the cognitive training scheme includes training content for multiple cognitive domains, each training content corresponding to a training duration and a training difficulty level, wherein the training content prediction model is obtained by training machine learning components using historical basic personal information, historical cognitive test results, and corresponding historical cognitive training schemes as samples.

[0105] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for determining cognitive training content, the method comprising: Obtain the basic personal information and cognitive test results of the first target object, wherein the cognitive test results include test results of multiple cognitive domains; The personal basic information and the cognitive test results are input into the training content prediction model. The cognitive training scheme adapted to the first target object is obtained through the training content prediction model. The cognitive training scheme includes training content for multiple cognitive domains. Each training content has a corresponding training duration and training difficulty level. The training content prediction model is obtained by training machine learning components using historical personal basic information, historical cognitive test results and corresponding historical cognitive training schemes as samples. The training content for each cognitive domain includes question-and-answer content. The historical cognitive training scheme includes training content for multiple cognitive domains. The sample also includes the historical time taken by the second target object to answer each question when training with each training content, the historical correctness of each question, the historical training time for each historical cognitive training scheme, and the historical training score for each historical cognitive training scheme. The machine learning component is trained using historical personal basic information, historical cognitive test results, and corresponding historical cognitive training schemes as samples to obtain the training content prediction model, including: Based on the historical time taken to answer each question and the historical correctness of each question when the second target object is trained with each training content, the training value of each training content is determined, wherein the larger the training value, the lower the training fit of the training content. The training content in the historical cognition training scheme with training values ​​greater than the preset threshold is deleted multiple times using different preset thresholds, so as to adjust the training content included in the historical cognition training scheme multiple times. The historical personal basic information, the historical cognition test results and the historical cognition training scheme after each adjustment are input into the machine learning component for training to obtain the training content prediction model.

2. The method according to claim 1, wherein, Based on the historical time taken to answer each question and the historical correct answers for each question when training each training content on the second target object, the training value for each training content is determined, including: The training value of each training content is determined by using a decision tree based on the historical time taken to answer each question and the historical correct answers for each question during training for the second target object. The historical time taken to answer each question and the historical correct answers for each question are mapped one-to-one with the non-leaf nodes of the decision tree, and the training value of each training content is mapped to the leaf nodes of the decision tree.

3. The method according to any one of claims 1 to 2, wherein, Also includes: When multiple alternative historical cognition training schemes are determined based on the historical personal basic information and the test results of the historical cognition of the second target object, the second target object is trained alternately using two alternative historical cognition training schemes to obtain the historical training time and historical training score of each alternative historical cognition training scheme. Based on the historical training time and historical training score of each candidate historical cognition training scheme, the fit value of each candidate historical cognition training scheme is determined. The larger the fit value, the higher the fit of the historical cognition training scheme. Based on the fit values ​​of multiple alternative historical cognition training schemes, the alternative historical cognition training scheme with the largest fit value is determined as the historical cognition training scheme for the second target object.

4. The method according to claim 3, wherein, Based on the historical training time and historical training score of each alternative historical cognition training program, determine the fit value of each alternative historical cognition training program, including: Weights are assigned to the historical training time and the historical training score. The historical training time is multiplied by its own weight to obtain a first product. The historical training score is multiplied by its own weight to obtain a second product. The sum of the first product and the second product is determined as the adaptation value. The weight of the historical training time is greater than the weight of the historical training score.

5. A device for determining cognitive training content, the device comprising: An information acquisition unit is used to acquire basic personal information and cognitive test results of the first target object, wherein the cognitive test results include test results of multiple cognitive domains; The training content determination unit is used to input the personal basic information and the cognitive test results into the training content prediction model, and obtain a cognitive training scheme adapted to the first target object through the training content prediction model. The cognitive training scheme includes training content of multiple cognitive domains, and each training content corresponds to a training duration and a training difficulty level. The training content prediction model is obtained by training machine learning components with historical personal basic information, historical cognitive test results and corresponding historical cognitive training schemes as samples. The training content for each cognitive domain includes question-and-answer content. The historical cognitive training scheme includes training content for multiple cognitive domains. The sample also includes the historical time taken by the second target object to answer each question when training with each training content, the historical correctness of each question, the historical training time for each historical cognitive training scheme, and the historical training score for each historical cognitive training scheme. The device also includes: The training value determination unit is configured to determine the training value of each training content based on the historical time taken to answer each question and the historical correctness of answering each question when the second target object is trained with each training content, wherein the larger the training value, the lower the training fit of the training content. The training unit is configured to repeatedly delete training content in the historical cognition training scheme whose training value is greater than the preset threshold using different preset thresholds, so as to adjust the training content included in the historical cognition training scheme multiple times. The historical personal basic information, the historical cognition test results, and the historical cognition training scheme after each adjustment are input into the machine learning component for training to obtain the training content prediction model.

6. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-4.

Images