CN110008229B - Method for identifying long-term memory language unit information based on computer - Google Patents
Method for identifying long-term memory language unit information based on computer Download PDFInfo
- Publication number
- CN110008229B CN110008229B CN201910291418.5A CN201910291418A CN110008229B CN 110008229 B CN110008229 B CN 110008229B CN 201910291418 A CN201910291418 A CN 201910291418A CN 110008229 B CN110008229 B CN 110008229B
- Authority
- CN
- China
- Prior art keywords
- long
- unit information
- language unit
- term memory
- language
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000007787 long-term memory Effects 0.000 title claims description 60
- 230000015654 memory Effects 0.000 claims description 40
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000012552 review Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 206010027175 memory impairment Diseases 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Debugging And Monitoring (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a method and a system for recognizing language unit information which is memorized for a long time based on a computer.
Description
Technical Field
The invention belongs to the technical field of application of a language fast learning and memory method in memory science in a computer environment, which is a branch of informatics, and particularly relates to a method and a system for recognizing language unit information which is formed into long-term memory by a language learner based on a computer.
Background
The difficulty of language learning is that not only is a learner required to learn and memorize a great deal of language unit information, but also the learner often needs to review the same language unit information for a plurality of times to remember the language unit information more firmly, namely, the long-term memory in the memory is formed. In the process of learning and memorizing the language unit information, a learner often has difficulty in quickly and effectively recognizing and excluding the language unit information which has been memorized for a long time because of no effective auxiliary tool, so that repeated learning is performed on the information which has been memorized for a long time, thereby wasting a great deal of time and energy. Before learning a group of language unit information, the language unit information which has formed long-term memory is identified and excluded, so that the language unit information is identified and appears or does not appear in the learning process, and the learner always concentrates on the identification and the memorization of the language unit information which does not form long-term memory. The method is developed and realized by computer technology, so that the learner can greatly improve the efficiency of language learning and memory by learning by means of a computer software system. The method is also one of the main methods for improving the language learning and memory under the theory of the optimal mode of the language learning and memory.
As the former has few mention on the study of the long-term memory parameters and the application of the memory recognition system is not seen in the similar technical products in China at present, the technology currently involved in the invention is to set the long-term memory parameters by utilizing the computer technology and preliminarily determine the setting and application rules of the memory recognition method and system, such as the determination of the long-term memory parameter algorithm; further, in the case of considering the system operation speed, the recognition system stability, the reliability in balance, the long-term memory parameters and the like of the individual learner are determined by modeling with tools such as big data, machine learning, deep learning and the like. The specific and accurate content settings also need to be summarized through a great deal of detailed experimentation and practice, but this is a useful start anyway for further exploration of improving the efficiency of language learning.
Disclosure of Invention
The recognition technology based on the computer for long-term memory is characterized in that a long-term memory parameter is preset in a system, the parameter is average review times required by people to learn and memorize language unit information so as to form long-term memory, and under the condition of considering the running speed of the system, the stability and the reliability of the recognition system in a balanced manner, a model is built by using tools such as big data, machine learning, deep learning and the like so as to calculate the long-term memory parameter of an individual learner. Then, when the language unit information to be learned and memorized is selected each time, the language unit information which has formed the correct memory times and exceeds the long-term memory parameter, namely the language unit information which has formed the long-term memory and is defined by the invention is identified, so that the language unit information is distinguished to be presented or not presented in the subsequent learning process.
In order to solve the problems, the invention is realized according to the following technical scheme:
s1, setting a long-time memory parameter and a computer long-time memory identification system:
and setting a historical database, wherein the historical data of the language unit information checked by the learner after each learning comprises correct and incorrect language unit information records, date and time of checking, judging results of whether the answer is correct or not and the like.
Setting a long-time memory parameter, namely learning and memorizing language unit information by people to form average minimum number of long-time memories, wherein the parameter is a positive integer; and then, under the condition of considering the running speed of the system, the stability and the reliability of the identification system in balance, building a model by utilizing tools such as big data, machine learning, deep learning and the like so as to calculate the long-time memory parameters of the individual learners.
And setting a recognition selection module, recognizing according to the long-term memory parameters, and selecting language unit information which does not form long-term memory to enter a temporary list or recognizing the language unit information which does form long-term memory.
S2, the identification and selection module identifies according to the long-time memory parameters: if the number of times that the language unit information is accumulated in the history database is smaller than the long-time memory parameter, the language unit information is selected to enter a temporary list or is otherwise identified; conversely, if a certain language unit information is accumulated in the history database for a correct number of times greater than or equal to the long-term memory parameter, the language unit information is not selected to enter the temporary list or is not otherwise identified. In the process of accumulating the correct information corresponding to a certain language unit information in the historical database, the invention takes a day as a unit to count, namely, the system only counts 1 day, namely, 1 time no matter how many times the learner learns and memorizes the same language unit information in the same day, namely, 24 hours. It is to be noted that the present invention is preferably used in the present invention by taking days as a statistical unit for long-term memory, but it is not excluded that the statistics be performed within 1 day. Therefore, the above embodiments are merely examples of the present invention, and are not intended to limit the scope of the present invention as defined in the appended claims.
S3, generating a temporary list, wherein the temporary list is temporarily generated by the system through the recognition and selection module according to the long-time memory parameters and the historical data in the historical database and selecting corresponding information from the language information base and the topic information base.
Further, since the former has little mention about the long-term memory parameter defined by the invention, the value of the parameter is described by lacking convincing theory and practice, and the value of the parameter can only be deduced by the number of review points in the long-term memory period which are developed and summarized by the former in the Eben-Stokes curve principle. The definition and calculation method of the long-term memory obtained by the experimental basis and the research conclusion of the Egnotor on the memory and the forgetting are different from the statistics and calculation method of the long-term memory defined by the invention, so the invention deduces the value of the parameter according to the number of review points in the long-term memory period which are summarized by the former development in the Egnotor forgetting curve principle, and the value of the parameter is more reasonable and more convincing to be determined by further experiments and practices.
Compared with the prior art, the invention has the beneficial effects that:
1. the difficulty of language learning is that language learners not only learn and memorize a large amount of language unit information, but also can memorize each language unit information repeatedly for a plurality of times to form firm memory, namely long-term memory. According to the study theory of the Ebinhaos and the predecessor about memory and forgetfulness, the number of review memories required for the memory of a certain object to reach the degree of long-term memory varies according to different conditions of people, but in general, a certain rule is circulated. If the number of times of the review required for forming the long-term memory from the start of the memorization of the language unit information, namely the long-term memory parameter defined by the invention, can be determined, the learner can not stop the review when memorizing because the memory degree does not reach the parameter yet, so that the long-term memory is not formed, and the learner can not use the language unit information because of weak memory when the language unit information needs to be applied; or the learning is continued after the memory degree of the language unit information exceeds the required review times, time and energy are wasted and even excessive learning is caused. Aiming at the problems, the invention sets the long-term memory parameters to represent the times that people generally need to review the learning memory of the language unit information to the long-term memory degree, and then identifies or eliminates the language unit information which has formed the long-term memory through the long-term memory identification system, so that the learner always concentrates on the learning memory of the language unit information which does not form the long-term memory, thereby saving the learning time and improving the learning efficiency.
2. In the daily learning process, in order to improve the efficiency of language learning by using the long-term memory parameter and the recognition method thereof, before recording and counting the massive language unit information and repeatedly reviewing the difficult-to-determine time, the learner is relied on to manually perform a great deal of work, and the problem can be easily solved by means of the computer technology, so that the learning efficiency is maximized.
The method for recognizing the long-term memory language unit information based on the computer is suitable for assisting a learner in a native language to learn and memorize any foreign language or regional language, is also suitable for the learner in the native language to learn various local languages in the native language, and is also suitable for the learner in the native language to learn the native language.
Drawings
FIG. 1 is a diagram of a computer-based method and system for identifying long-term memory language units information in accordance with the present invention;
FIG. 2 is a schematic diagram and flow chart of the invention applied in a computer automated cycle screening system;
FIG. 3 is a diagram of inferred data sources for an exemplary embodiment of the present invention for long term memory parameter values;
the specific embodiment is as follows:
the present invention relates to a computer-based method and system for identifying language units information that a language learner has formed long term memory (fig. 1). In addition, to more clearly illustrate the structure and application of the present invention, the method and system of the present invention are specifically illustrated in conjunction with an automatic cycle screening system (fig. 2):
1. a language information base 100 is established, which includes a plurality of language unit information and corresponding language unit information or related information.
2. A question information base 105 is established, which should include information such as question making requirements, language unit information, and the like.
3. A history database 110 is established which holds history data of the language unit information checked after each learning of the learner, and is used as a basis for recognizing the long-term memory.
4. The present invention concludes from the previous development of the figure 3 by the man in the Ebinhao forgetting curve of the summarized number of review points in the long-term memory period by setting the long-term memory parameter 120 to a value of 6. The inference process is as follows: in fig. 3, since the period f0- > f3 is counted in days in the course of accumulating a certain language unit information according to the present invention, since the period f0- > f3 is counted 1 time from the initial memory to 15 days in total from the time of keeping in mind that the long time memory is reached, that is, the system counts only 1 day, that is, 1 time, regardless of how many times the learner has performed learning and memory for the same language unit information in the same day, that is, 24 hours, the period f0- > f3 is counted 1 time, plus 5 times of f4- > f8, and thus counted 6 times in total. As mentioned above, the data in FIG. 3 are most of the data shown in the theory of memory and forgetting at present, and therefore should be representative, and should be convinced from this; however, the definition and calculation method of the long-term memory obtained by the experimental basis and the research conclusion of the Aibingham on the memory and the forgetting are different from the statistical and calculation method of the long-term memory defined by the invention, so the invention deduces that the value of the parameter is 6 according to the number of review points in the long-term memory period which is summarized by the previous development in the Aibingham forgetting curve principle, which is only taken as an example, is more reasonable, and has more convincing value to be determined by further experiments and practices.
In addition, under the condition of balancing the running speed of the system, the stability and the reliability of the identification system, the long-time memory parameters of the individual learners can be determined by establishing a model by utilizing tools such as big data, machine learning, deep learning and the like, so that the parameters are more accurate for the individual and the learning efficiency can be improved.
5. The identification selection module 130 performs identification according to the long-term memory parameters: if the number of times that the language unit information is accumulated in the history database is smaller than the long-time memory parameter, the language unit information is selected to enter a temporary list or is otherwise identified; conversely, if a certain language unit information is accumulated in the history database for a correct number of days greater than or equal to the long-term memory parameter, the language unit information is not selected to enter the temporary list or is not otherwise identified. In the process of accumulating the correct information corresponding to a certain language unit information in the historical database, statistics is carried out by taking a day as a unit, namely, the system only counts 1 day, namely, 1 time no matter how many times the learner carries out learning and memorizing on the same language unit information in the same day, namely, 24 hours. It is noted that the day is taken as the statistical unit of the long-term memory parameter, which is a preferred embodiment of the present invention, but it is not excluded that the statistical scheme is performed within 1 day, so the above scheme is only an exemplary embodiment of the present invention and is not intended to limit the present invention, and the scope of the present invention is defined by the claims.
6. A temporary list 140 is generated, wherein the temporary list is temporarily generated by the system through the recognition and selection module according to the long-term memory parameters and the data reserved in the history database, and then selecting corresponding information from the language information base and the topic information base, and is abbreviated as temporary list.
7. The setting checking module 150 compares the answer information recorded in the temporary list inputted by the user with the corresponding language units maintained in the language information library, judges whether to be correct or not, and records the result in the temporary list, and the recorded content also includes date and time for making a correct or not judgment.
8. The history data adding module 160 is provided to add the language unit information record including the correct and the incorrect answer each time the learner inputs in the temporary list to the history database 110, and to add the date and time of the answer input and the result of the answer correctness determination to the history database.
In summary, steps 100 through 140 are embodiments of the present invention; steps 150 to 160 return to step 110, which is a specific embodiment of the learner checking the system after each test, and storing the checked language unit information into the history database; the steps 140 to 210 and back to 140 are the setting mode and flow of the circulation screening system, which are not described herein.
The above description is only exemplary of the present invention and is not intended to limit the present invention, therefore, the protection scope of the present invention is defined by the claims.
Claims (2)
1. A computer-based method for identifying language units information that a language learner has formed long-term memory, comprising the main steps of:
s1, setting a long-time memory parameter and a computer long-time memory identification system
A history database that holds history data of the language unit information checked after each learning of the learner;
a long-term memory parameter, which is the average minimum number of times that people learn and memorize language unit information to form long-term memory, defined by the claim, wherein the parameter is a positive integer; under the condition of considering the running speed of the system, the stability and the reliability of the identification system in balance, the long-time memory parameters of the individual learners can be further determined by establishing a model by utilizing tools such as big data, machine learning, deep learning and the like;
the recognition and selection module is used for recognizing according to the long-term memory parameters, selecting language unit information which does not form long-term memory to enter a temporary list or recognizing the language unit information which does form long-term memory;
s2, the identification and selection module identifies according to the long-time memory parameters: if the number of times that the language unit information is accumulated in the history database is smaller than the long-time memory parameter, the language unit information is selected to enter a temporary list or is additionally marked; conversely, if the number of times that a certain language unit information is accumulated in the history database is greater than or equal to the long-term memory parameter, the language unit information is not selected to enter the temporary list or is not additionally identified;
s3, generating a temporary list, wherein the temporary list is temporarily generated by the system through the recognition and selection module for recognizing whether the language unit information to be learned has formed long-term memory according to the long-term memory parameters and the historical data in the historical database, and selecting corresponding information from the language information base or the question information base.
2. The method according to claim 1, wherein the verified language unit information is characterized in that the learner checks and judges whether a correct memory is formed by the system after learning and memorizing the language unit information each time, and the information is verified language information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910291418.5A CN110008229B (en) | 2019-04-10 | 2019-04-10 | Method for identifying long-term memory language unit information based on computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910291418.5A CN110008229B (en) | 2019-04-10 | 2019-04-10 | Method for identifying long-term memory language unit information based on computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008229A CN110008229A (en) | 2019-07-12 |
| CN110008229B true CN110008229B (en) | 2023-05-16 |
Family
ID=67171193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910291418.5A Active CN110008229B (en) | 2019-04-10 | 2019-04-10 | Method for identifying long-term memory language unit information based on computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008229B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192393A (en) * | 2021-04-28 | 2021-07-30 | 上海松鼠课堂人工智能科技有限公司 | Intelligent English word memory recitation management control method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1696992A (en) * | 2005-04-11 | 2005-11-16 | 陈耀庭 | Method for looking for personal optimal review cycle |
| CN101201812A (en) * | 2006-12-14 | 2008-06-18 | 英业达股份有限公司 | System and method for executive auxiliary learning of language word by computer |
| CN102054376A (en) * | 2009-11-11 | 2011-05-11 | 林汉忠 | Word memory learning system |
| CN103413478A (en) * | 2013-07-09 | 2013-11-27 | 复旦大学 | Word memory intelligent learning method and system thereof |
| CN104992390A (en) * | 2015-07-24 | 2015-10-21 | 龙剑辉 | Fast memory method for language learning based on automatic cycle screening system of computer |
| JP2017201342A (en) * | 2016-05-02 | 2017-11-09 | 良一 春日 | Language Learning Robot Software |
-
2019
- 2019-04-10 CN CN201910291418.5A patent/CN110008229B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1696992A (en) * | 2005-04-11 | 2005-11-16 | 陈耀庭 | Method for looking for personal optimal review cycle |
| CN101201812A (en) * | 2006-12-14 | 2008-06-18 | 英业达股份有限公司 | System and method for executive auxiliary learning of language word by computer |
| CN102054376A (en) * | 2009-11-11 | 2011-05-11 | 林汉忠 | Word memory learning system |
| CN103413478A (en) * | 2013-07-09 | 2013-11-27 | 复旦大学 | Word memory intelligent learning method and system thereof |
| CN104992390A (en) * | 2015-07-24 | 2015-10-21 | 龙剑辉 | Fast memory method for language learning based on automatic cycle screening system of computer |
| JP2017201342A (en) * | 2016-05-02 | 2017-11-09 | 良一 春日 | Language Learning Robot Software |
Non-Patent Citations (1)
| Title |
|---|
| 运用记忆规律探讨英语词汇学习;李华英等;《中国电力教育》;20130510(第14期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008229A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929918B (en) | 10kV feeder fault prediction method based on CNN and LightGBM | |
| CN107273688A (en) | Equipment life and health degree monitoring method and system based on primary fault data | |
| CN111460728A (en) | Method and device for predicting residual life of industrial equipment, storage medium and equipment | |
| CN103399280B (en) | Based on the cycle life of lithium ion battery Forecasting Methodology of NSDP-AR model | |
| US20220327398A1 (en) | Technology maturity judgment method and system based on science and technology data | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN110008229B (en) | Method for identifying long-term memory language unit information based on computer | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN116306863A (en) | Collaborative knowledge tracking modeling method and system based on contrast learning | |
| CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
| CN115311218A (en) | Circuit board reliability prediction method and circuit board stress accelerated life experiment method | |
| CN110837566A (en) | Dynamic construction method of knowledge graph for CNC (computerized numerical control) machine tool fault diagnosis | |
| CN117290462B (en) | Intelligent decision system and method for large data model | |
| CN109635008B (en) | Equipment fault detection method based on machine learning | |
| CN108985618B (en) | Grading system for improving skill level of people | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN115719139A (en) | Dispatching self-checking system for power grid dispatching operation management | |
| CN109902352A (en) | A kind of transient rotor angle stability analysis of key Characteristic Extraction method and system | |
| CN115577890A (en) | Intelligent quality management method, electronic device and storage medium | |
| CN110689168B (en) | Power load prediction method and prediction device | |
| CN113807462A (en) | AI-based network equipment fault reason positioning method and system | |
| CN111143774B (en) | Power load prediction method and device based on influence factor multi-state model | |
| CN114664074A (en) | Test method and system of Bluetooth remote controller | |
| CN110659356B (en) | Information matching method, device and storage medium | |
| CN114034978B (en) | Automatic model detection method and system for distribution network project |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |