CN114004549A - Behavior ability evaluation method of evolutionary object - Google Patents
Behavior ability evaluation method of evolutionary object Download PDFInfo
- Publication number
- CN114004549A CN114004549A CN202111656380.0A CN202111656380A CN114004549A CN 114004549 A CN114004549 A CN 114004549A CN 202111656380 A CN202111656380 A CN 202111656380A CN 114004549 A CN114004549 A CN 114004549A
- Authority
- CN
- China
- Prior art keywords
- behavior
- factor
- value
- result
- english
- 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.)
- Pending
Links
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The application discloses a behavior ability evaluation method of an evolutionary object. The method for evaluating the behavior ability of the evolutionary object comprises the following steps: acquiring the description of the behavior result of the evolutionary object in the environment presentation scene; unitizing the behavior result to form a behavior result sequence; and generating a behavior ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence so as to represent the behavior ability of the evolutionary object. Therefore, the behavior result sequence is obtained by unitizing the behavior result, and the behavior ability evaluation value is further obtained, so that the evaluation accuracy can be effectively improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a behavior ability evaluation method of an evolutionary object.
Background
The current AI lot, can be rated from both grammatical and lexical spelling. The analysis method based on grammar and lexical can be used for classifying input contents, and providing word segmentation, part-of-speech tagging, named entity recognition, basic language element positioning, composition scoring, comment suggestion and intelligent error correction based on big data and user behaviors, so that targeted composition guidance opinions are provided for users, and understanding and analysis of a machine on basic texts are comprehensively supported. For example, the content may be tagged as words, phrases, keywords, and the processed output may be used for subsequent testing or searching, etc. The keyword extraction method is used for carrying out structuralization processing on information contained in the text and integrating the extracted information together in a unified form. Word segmentation and part-of-speech definition, word segmentation technology and dictionary service are combined, and word part-of-speech is checked, searched and labeled.
In the process of realizing the prior art, the inventor finds that:
the AI-based assessment results are relatively unilateral and difficult to apply directly to actual classrooms. The analysis process of the return values is not transparent to the respective AI providers. For example: in the scoring link, each supplier has a score system; in the reviewing link, extension is performed on the basis of a circulating fixed telephone operation; the evaluation based on AI and the expectation of the teaching and research on the actual situation have a big difference, and can only be used as a basic value, and can meet the classroom requirement after deep processing.
Therefore, it is necessary to provide a related technical solution for improving the accuracy of the performance capability evaluation.
Disclosure of Invention
The embodiment of the application provides a related technical scheme for improving the accuracy of behavior ability evaluation, and aims to solve the technical problem that an evaluation result based on AI is relatively unilateral.
The application provides a behavior ability evaluation method of an evolutionary object, which comprises the following steps:
acquiring the description of the behavior result of the evolutionary object in the environment presentation scene;
unitizing the behavior result to form a behavior result sequence;
and generating a behavior ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence so as to represent the behavior ability of the evolutionary object.
Further, the result values of the behavior result sequence include:
at least one of a correctness factor for characterizing the behavior result, a sequential reasonableness factor for the behavior result sequence, a complexity factor for the behavior result, or a complexity factor for the behavior result sequence.
Further, the result value of the behavior result sequence also comprises a transition relation factor between behavior results.
Further, the sequential reasonability factor of the behavior result sequence is obtained according to the following mode:
enumerating a set of all behavior result sequences for the environment presentation scenario;
and determining the sequential reasonableness factor of the behavior result sequence according to the behavior result sequence of the evolution type object in the environment presentation scene and the corresponding score of each behavior result sequence in the set of all the behavior result sequences.
Further, according to the result value and the weight value of the behavior result sequence, a behavior ability evaluation value of the evolutionary object is generated to characterize the behavior ability of the evolutionary object, which specifically includes:
and according to the result value and the weight value of the behavior result sequence, carrying out weighted summation to generate a behavior ability evaluation value of the evolutionary object.
Further, the behavior ability evaluation method is used for evaluating English exercise ability of the author.
Further, the result values of the behavior result sequence include:
a correctness factor for spelling a word;
writing a word order reasonableness factor of a sentence;
a complexity factor of spelling a word;
a complexity factor of the written sentence.
Further, the result value of the behavior result sequence further includes:
a transitional relationship factor for characterizing the logical relationship between sentences.
Further, the word order reasonability factor of the behavior result sequence is obtained according to the following mode:
enumerating a set of all word orders for a given proposition;
and determining the language order reasonableness factor of the author according to the language order of the author and the scores corresponding to the language orders in all the language order sets.
Further, according to the result value and the weight value of the behavior result sequence, a behavior ability evaluation value of the evolutionary object is generated to characterize the behavior ability of the evolutionary object, which specifically includes:
according to at least one of the correctness factor of the spelling word, the word order reasonableness factor of the written sentence, the complexity factor of the spelling word and the complexity factor of the written sentence and the corresponding weight value, the English application ability evaluation value of the author is generated by weighting and summing
The embodiment provided by the application has at least the following beneficial effects:
the behavior result sequence is obtained by unitizing the behavior result, and the behavior ability evaluation value is further obtained, so that the evaluation accuracy can be effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flowchart of a method for evaluating behavioral abilities of an evolved object according to an embodiment of the present application;
FIG. 2 is a flow chart of a manner of obtaining sequential rationality factors for a sequence of behavioral results provided by an embodiment of the present application;
fig. 3 is a flowchart of another obtaining manner of sequential reasonableness factors of a behavior result sequence provided in this embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a method for evaluating behavioral ability of an evolutionary object provided by the present application includes the following steps:
s100: acquiring the description of the behavior result of the evolutionary object in the environment presentation scene;
s200: unitizing the behavior result to form a behavior result sequence;
s300: and generating a behavior ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence so as to represent the behavior ability of the evolutionary object.
It should be noted that an evolutionary object is understood herein to be an object whose individual abilities may change over time. Preferably, the evolutionary object refers to an individual student who performs English sentence making test. An environment presentation scenario herein may be understood as a specific environment determined according to a specific complexity level, presentation manner, and related requirements. Preferably, the environment presentation scenario herein refers to an english sentence making topic for a student to make english sentence making. The behavior result can be understood as corresponding information feedback of the evolutionary object for the environment presentation scene. Preferably, the action result refers to an english sentence submitted by the individual student after answering according to the english sentence making question. The unitization can be understood as the splitting and refining of the behavior result according to the corresponding rule. The action result sequence can be understood as arrangement data obtained by arranging the split and refined action results according to corresponding rules. The result value here can be understood as the evaluation score corresponding to each element in the action result sequence. The weight value here can be understood as a weight proportion value corresponding to each element in the action result sequence. The weight refers to the importance degree of a certain factor or index relative to a certain event, which is not only the percentage of the certain factor or index, but also the relative importance degree of the factor or index, which tends to contribute to or importance. The behavior ability evaluation value can be understood as an evaluation score of the evolutionary object when the scene is presented corresponding to the environment. In a specific application scenario, the method for evaluating the behavioral ability of the evolutionary object provided by the application can be used in an automatic correction scenario of English composition or English sentences. For example, an English sentence obtained after a student makes a sentence according to requirements is obtained, and the English sentence corresponds to a specific English sentence making writing scene; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating a final evaluation score of the English sentence according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evolutionary object refers to a student who makes English sentences according to requirements; the behavior result refers to English sentences obtained after the students make sentences according to requirements; the environment presentation scene refers to a specific English sentence making scene; the unitization corresponds to splitting and thinning; the behavior result sequence refers to English sentence component arrangement data divided according to sentence components; the result value corresponds to the evaluation score; the weight value refers to a weight proportion value; the performance rating value refers to the final rating score. Obviously, the evaluation score can represent the behavior ability of the student in the current English sentence making scene. The behavior result is unitized, and corresponding capability evaluation is carried out by combining the weight value, so that the accuracy of the evaluation result can be effectively improved.
Further, in a preferred embodiment provided herein, the result value of the behavior result sequence includes:
at least one of a correctness factor for characterizing the behavior result, a sequential reasonableness factor for the behavior result sequence, a complexity factor for the behavior result, or a complexity factor for the behavior result sequence.
It should be noted that the correctness factor herein may be understood as an attribute value for characterizing the correctness of the behavior result, the order reasonableness factor may be understood as an attribute value for characterizing the dependency relationship between elements in the behavior result sequence and the reasonableness of the relationship structure, the complexity factor may be understood as an attribute value for characterizing the complexity of the behavior result, and the complexity factor may be understood as an attribute value for characterizing the complexity of the serialized behavior result sequence. In a specific application scenario, the method and the device can be used for an automatic correction scenario of English sentences. For example, an english sentence after sentence making by a student is obtained, and the english sentence corresponds to a specific english sentence making writing scene; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating the evaluation score of the English sentence of the student according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evaluation scores here include a score for representing the degree of correctness of the student's english sentence, a score for representing the dependence between elements in the english sentence component arrangement data and the reasonability of the relationship structure, a score for representing the degree of complexity of the student's english sentence, and a score for representing the degree of complexity of the english sentence component arrangement data. The correctness factor here corresponds to a score for characterizing how correct the student's english sentence is. The sequence reasonableness factor here is a score representing the dependency relationship between elements in the english sentence component arrangement data and the reasonableness of the relationship structure. The complexity factor here corresponds to a score that is used to characterize the complexity of a student's english sentence. The complexity factor here corresponds to a score that characterizes the complexity of the english sentence component arrangement data. Obviously, the accuracy of the evaluation result can be further improved by using the result value of the more refined behavior result sequence.
Specifically, in a preferred embodiment provided by the present application, the result value of the behavior result sequence further includes a transition relation factor between behavior results.
It is to be understood that the transition relation factor between the behavior results herein can be understood as an attribute value for characterizing the context transition relation of the content in the behavior results. In a specific application scenario, the method and the device can be used for an automatic correction scenario of English sentences. For example, obtaining an English sentence submitted by a student according to a question requirement, wherein the English sentence corresponds to a specific English sentence making writing scene; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating the evaluation score corresponding to the English sentence according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evaluation scores include a score for representing the correctness of the english sentence of the student, a score for representing the dependencies between the elements and the reasonability of the relationship structure in the arrangement data of the components of the english sentence, a score for representing the complexity of the english sentence of the student, a score for representing the complexity of the arrangement data of the components of the english sentence, and a score for representing the front-back transition relationship of the contents in the english sentence of the student. The transition relation factor between the behavior results corresponds to the score of the front-back transition relation of contents in the English sentences representing students. Obviously, by further refining the result value of the behavior result sequence, the corresponding evaluation is more pertinent, and the accuracy of the evaluation result can be effectively improved.
Further, referring to fig. 2, in a preferred embodiment provided in the present application, the sequential reasonableness factor of the behavior result sequence is obtained according to the following manner:
S301A: enumerating a set of all behavior result sequences for the environment presentation scenario;
S302A: and determining the sequential reasonableness factor of the behavior result sequence according to the behavior result sequence of the evolution type object in the environment presentation scene and the corresponding score of each behavior result sequence in the set of all the behavior result sequences.
It is to be understood that the sequential rationality factor can be understood as an attribute value used to characterize the inter-element dependencies and relationship structure rationality within the behavior result sequence. An environment presentation scenario may be understood as a specific environment determined according to a specific complexity, presentation manner, and related requirements. The behavior result sequence can be understood as arrangement data obtained by arranging the split and refined behavior results according to corresponding rules. An evolutionary object is understood herein to be an object whose individual abilities may change over time. In a specific application scenario, the method and the device can be used for an automatic correction scenario of English sentences. Preferably, the sequential rationality factor refers to a score for representing dependency relationships among elements in the arrangement data of the components of the english sentence and the rationality of the relationship structure, the environment presentation scenario refers to an english sentence creation topic for a student to write an english sentence, the behavior result sequence refers to arrangement data of the components of the english sentence divided according to the components of the sentence, and the evolutionary object refers to the student who performs the english sentence creation according to the requirement. For example, for an english sentence making question used for a student to write an english sentence making, enumerating all possible english sentence component arrangement data corresponding to the english sentence making question to obtain a sentence set; enumerating the value corresponding to each sentence in the obtained sentence set according to the corresponding English sentence component arrangement data obtained after the student makes the sentence on the English sentence making question, and determining the rationality value of the English sentence corresponding to the student. Preferably, the score corresponding to each sentence herein is an evaluation value assigned according to the dependency relationship and the structural rationality of the relationship. Obviously, the possibility of presenting all behavior result sequences corresponding to the scene by the environment is determined in an enumeration mode, and corresponding scores are pre-distributed according to the sequence reasonableness, so that the accuracy of the finally determined sequence reasonableness factor can be effectively improved.
Specifically, in a preferred embodiment provided by the present application, generating a behavior ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence to characterize the behavior ability of the evolutionary object specifically includes:
and according to the result value and the weight value of the behavior result sequence, carrying out weighted summation to generate a behavior ability evaluation value of the evolutionary object.
It should be noted that the behavior result sequence herein can be understood as arrangement data obtained by arranging the split and refined behavior results according to the corresponding rule. The result value here can be understood as the evaluation score corresponding to each element in the action result sequence. The weight value here can be understood as a weight proportion value corresponding to each element in the action result sequence. The weighted summation here is understood to be the summation of the evaluation scores according to the respective weighting ratios. An evolutionary object is understood herein to be an object whose individual abilities may change over time. The behavior ability evaluation value can be understood as an evaluation score of the evolutionary object when the scene is presented corresponding to the environment. In a specific application scenario, the method and the device can be used for an automatic correction scenario of English composition or English sentences. For example, english sentences provided by students on request of titles are acquired. The English sentence corresponds to a specific English sentence making scene; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and adding and summing the evaluation scores corresponding to the sentence components according to the weight proportion values according to the evaluation scores corresponding to the sentence components in the arrangement data and the weight proportion values to generate the final evaluation score of the English sentence. The evolutionary object refers to a student who makes English sentences according to requirements; the behavior result refers to English sentences obtained after the students make sentences according to requirements; the environment presentation scene refers to a specific English sentence making scene; the unitization corresponds to splitting and thinning; the behavior result sequence refers to English sentence component arrangement data divided according to sentence components; the result value corresponds to the evaluation score; the weight value refers to a weight proportion value; the performance rating value refers to the final rating score. Obviously, the evaluation score can represent the behavior ability of the student in the current English sentence making scene. The behavior results are unitized, and corresponding capability evaluation is carried out by combining weighted summation, so that the evaluation result is more scientific and reasonable.
Further, in a preferred embodiment provided by the present application, the behavioral ability evaluation method is used for evaluating english exercise ability of an author.
It can be understood that english is a language that is commonly used in daily life. Particularly in the field of education, english has become a very popular discipline. Along with the attention of people on the English operational capability, more and more people need to judge the English operational capability of the people, and especially higher requirements are gradually put forward on the judgment accuracy. In a specific application scenario, the behavior ability evaluation method provided by the application is used for evaluating English application ability of an author. Specifically, the method can be applied to automatic correction scenes of English composition or English sentences. For example, according to the question requirement, the author makes a corresponding English sentence and answers, and gives an English sentence answered by the author; acquiring English sentences of authors, wherein the English sentences correspond to English sentence making scenes required by questions; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating a final evaluation score of the English sentence according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evolution type object refers to an author making English sentences according to requirements, the behavior result refers to English sentences obtained after the author makes sentences according to the requirements, the environment presentation scene refers to a specific English sentence making scene, the unitization corresponds to splitting and refining, the behavior result sequence refers to English sentence component arrangement data divided according to sentence components, the result value corresponds to an evaluation score, the weight value refers to a weight proportion value, and the behavior ability evaluation value refers to a final evaluation score. Obviously, the evaluation score can represent the English exercise ability of the author in the current English sentence making scene. By unitizing English sentences and carrying out corresponding English application capability evaluation by combining the weight values, the accuracy of evaluation results can be effectively improved.
Specifically, in a preferred embodiment provided herein, the result values of the behavior result sequence include:
a correctness factor for spelling a word;
writing a word order reasonableness factor of a sentence;
a complexity factor of spelling a word;
a complexity factor of the written sentence.
It is understood that english is a relatively common language worldwide, and its syntax is often just as legal. In particular, the evaluation of the English exercise capacity can be performed from multiple angles, such as multiple dimensions of words, sentences, chapters, spellings, logicality, topic relevance and the like. In a specific application scenario, the behavior ability evaluation method provided by the application is used for evaluating English application ability of an author. Specifically, the method can be applied to automatic correction scenes of English composition or English sentences. For example, according to the question requirement, the author makes a corresponding English sentence and answers, and gives an English sentence answered by the author; acquiring English sentences of authors, wherein the English sentences correspond to English sentence making scenes required by questions; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating a final evaluation score of the English sentence according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evaluation scores here include a score for characterizing the correctness of the spelled word, a score for the justification of the word order of the written sentence, a score for the complexity of the spelled word, and a score for the complexity of the written sentence. The correctness factor of the spelled word is corresponding to a score for representing the correctness of the spelled word, and specifically can refer to a score for representing the wrong spelling of an English word; the word order reasonableness factor of the written sentence corresponds to the value of the word order reasonableness of the written sentence, and specifically can refer to the value representing the wrong word order of the English sentence; the complexity factor of the spelling word corresponds to the value of the complexity of the spelling word, and specifically can refer to the value representing the difficulty degree of the English word; the complexity factor of the written sentence corresponds to a score of the complexity of the written sentence, and may specifically refer to a score representing the difficulty level of the sentence pattern of the english sentence. The evolution type object refers to an author making English sentences according to requirements, the behavior result refers to English sentences obtained after the author makes sentences according to the requirements, the environment presentation scene refers to a specific English sentence making scene, the unitization corresponds to splitting and refining, the behavior result sequence refers to English sentence component arrangement data divided according to sentence components, the result value corresponds to an evaluation score, the weight value refers to a weight proportion value, and the behavior ability evaluation value refers to a final evaluation score. Obviously, by further refining the result value of the behavior result sequence, the English operation capability of the author in the current English sentence making scene can be represented more scientifically and reasonably.
Further, in a preferred embodiment provided herein, the result value of the behavior result sequence further includes:
a transitional relationship factor for characterizing the logical relationship between sentences.
It can be understood that in english, the logical relationship between sentences is very important, and the front-back logical relationship between sentences can directly affect the reading experience of the whole english reading. In the present application, the result value is further refined by introducing a transition relation factor in the result value of the behavior result sequence. From the perspective of more comprehensive influence factors, relevant important parameters of an author on English operation capacity are abstracted, and evaluation data are further close to the real situation. The logical relationship between sentences here can be understood as the context transition relationship of the content in the behavior result. In a specific application scenario, the behavior ability evaluation method provided by the application is used for evaluating English application ability of an author. Specifically, the method can be applied to automatic correction scenes of English composition or English sentences. For example, according to the question requirement, the author makes a corresponding English sentence and answers, and gives an English sentence answered by the author; acquiring English sentences of authors, wherein the English sentences correspond to English sentence making scenes required by questions; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and generating a final evaluation score of the English sentence according to the evaluation score and the weight proportion value corresponding to each sentence component in the arrangement data. The evaluation scores here include a score for indicating the correctness of the spelled word, a score for indicating the justification of the word order in which the sentence is written, a score for indicating the complexity of the spelled word, a score for indicating the complexity of the written sentence, and a score for indicating the logical relationship between the sentences. The correctness factor of the spelled word corresponds to a score for representing the correctness of the spelled word, the word order reasonableness factor of the written sentence corresponds to a score for the word order reasonableness of the written sentence, the complexity factor of the spelled word corresponds to a score for the complexity of the spelled word, the complexity factor of the written sentence corresponds to a score for the complexity of the written sentence, and the transition relation factor corresponds to a score for representing the logical relationship between the sentences. The evolution type object refers to an author making English sentences according to requirements, the behavior result refers to English sentences obtained after the author makes sentences according to the requirements, the environment presentation scene refers to a specific English sentence making scene, the unitization corresponds to splitting and refining, the behavior result sequence refers to English sentence component arrangement data divided according to sentence components, the result value corresponds to an evaluation score, the weight value refers to a weight proportion value, and the behavior ability evaluation value refers to a final evaluation score. By introducing the value for representing the logical relationship between sentences and further refining the result value of the behavior result sequence, the English operation capability of the author in the current English sentence making scene can be represented more scientifically and reasonably.
Specifically, referring to fig. 3, in a preferred embodiment provided in the present application, the word order reasonableness factor of the behavior result sequence is obtained according to the following manner:
S301B: enumerating a set of all word orders for a given proposition;
S302B: and determining the language order reasonableness factor of the author according to the language order of the author and the scores corresponding to the language orders in all the language order sets.
It is understood that the word order reasonableness factor can be understood as an attribute value used for characterizing the interdependencies and structural reasonableness of the relationship between elements in the behavior result sequence. The behavior result sequence can be understood as arrangement data obtained by arranging the split and refined behavior results according to corresponding rules. In a specific application scenario, the method and the device can be used for an automatic correction scenario of English sentences. Preferably, the word order reasonableness factor here corresponds to a score used for representing the dependency relationship between elements and the reasonableness of the relationship structure in the arrangement data of the english sentence components, and the behavior result sequence here refers to the arrangement data of the english sentence components divided by the sentence components. For example, for a proposition of an english sentence making for an author to write an english sentence making, enumerating all possible word orders corresponding to the proposition of the english sentence making to obtain a sentence set; and enumerating the value corresponding to each sentence in the obtained sentence set according to the corresponding English sentence word order obtained after the author makes the sentence of the English sentence making proposition, and determining the rationality value of the English sentence word order corresponding to the author. Preferably, the score corresponding to each sentence corresponds to one evaluation value assigned according to the dependency relationship and the relationship structure rationality. Obviously, the possibility of all the word orders corresponding to the propositions is determined in an enumeration mode, and corresponding scores are pre-distributed according to the word order reasonableness, so that the accuracy of the finally determined word order reasonableness factor can be effectively improved.
Further, in a preferred embodiment provided by the present application, a behavior ability evaluation value of the evolved object is generated according to the result value and the weight value of the behavior result sequence, so as to characterize the behavior ability of the evolved object, which specifically includes:
and weighting and summing to generate an English operation ability evaluation value of the author according to at least one of the correctness factor of the spelling word, the word order reasonableness factor of the written sentence, the complexity factor of the spelling word and the complexity factor of the written sentence and the corresponding weight value.
It is to be appreciated that in evaluating English exercise capacity, the evaluation can be made from a number of angles. Specifically, the evaluation of the english operation ability can be performed from a plurality of points of view, such as spelling of words, word order of sentences, difficulty of words, difficulty of sentences, and the like. In a specific application scenario, the behavior ability evaluation method provided by the application is used for evaluating English application ability of an author. Specifically, the method can be applied to automatic correction scenes of English composition or English sentences. For example, according to the question requirement, the author makes a corresponding English sentence and answers, and gives an English sentence answered by the author; acquiring English sentences of authors, wherein the English sentences correspond to English sentence making scenes required by questions; splitting and refining the English sentence according to sentence components such as subjects, predicates, objects, table languages, determinants, subjects, complements, collocations and the like in English to obtain English sentence component arrangement data divided according to the sentence components; and adding and summing the evaluation scores corresponding to the sentence components according to the weight proportion values to generate the final evaluation score of the English sentence according to the evaluation scores corresponding to the sentence components in the arrangement data and the weight proportion values. Here, the evaluation score includes at least one of a score for indicating correctness of the spelled word, a score for word order reasonableness of the written sentence, a score for complexity of the spelled word, and a score for complexity of the written sentence. The correctness factor of the spelled word is corresponding to a score for representing the correctness of the spelled word, and specifically can refer to a score for representing the wrong spelling of an English word; the word order reasonableness factor of the written sentence corresponds to the value of the word order reasonableness of the written sentence, and specifically can refer to the value representing the wrong word order of the English sentence; the complexity factor of the spelling word corresponds to the value of the complexity of the spelling word, and specifically can refer to the value representing the difficulty degree of the English word; the complexity factor of the written sentence corresponds to a score of the complexity of the written sentence, and may specifically refer to a score representing the difficulty level of the sentence pattern of the english sentence. The evolutionary object here refers to an author who makes english sentences on demand. The behavior result refers to an English sentence obtained after the author makes a sentence according to the requirement. The environment presentation scene refers to a specific English sentence making scene. The unitization corresponds to split refinement. The action result sequence refers to english sentence component arrangement data divided by sentence components. The result value corresponds to the evaluation score. The weight value refers to a weight proportion value. The performance rating value refers to the final rating score. Obviously, the evaluation score can represent the English exercise ability of the author in the current English sentence making scene. The English sentence is unitized, relevant influence factors are further refined, corresponding English application capability evaluation is carried out by combining the weight value, and the accuracy of the evaluation result can be further improved.
The embodiment provided by the application has at least the following beneficial effects: the behavior result sequence is obtained by unitizing the behavior result, and the behavior ability evaluation value is further obtained, so that the accuracy of behavior ability evaluation can be effectively improved.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A behavior ability evaluation method of an evolutionary object is characterized by comprising the following steps:
acquiring the description of the behavior result of the evolutionary object in the environment presentation scene;
unitizing the behavior result to form a behavior result sequence;
and generating a behavior ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence so as to represent the behavior ability of the evolutionary object.
2. The method for evaluating the behavioral competence of an evolutionary object of claim 1, wherein the result value of the behavior result sequence comprises:
at least one of a correctness factor for characterizing the behavior result, a sequential reasonableness factor for the behavior result sequence, a complexity factor for the behavior result, or a complexity factor for the behavior result sequence.
3. The method for evaluating the behavioral ability of an evolutionary object as claimed in claim 2, wherein the result value of the sequence of behavior results further comprises a transition relation factor between the behavior results.
4. The method for evaluating the behavioral competence of an evolutionary object of claim 2, wherein the sequential reasonableness factor of the behavior result sequence is obtained as follows:
enumerating a set of all behavior result sequences for the environment presentation scenario;
and determining the sequential reasonableness factor of the behavior result sequence according to the behavior result sequence of the evolution type object in the environment presentation scene and the corresponding score of each behavior result sequence in the set of all the behavior result sequences.
5. The method for evaluating the behavioral ability of an evolutionary object according to claim 1, wherein the step of generating a behavioral ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence to characterize the behavioral ability of the evolutionary object specifically comprises:
and according to the result value and the weight value of the behavior result sequence, carrying out weighted summation to generate a behavior ability evaluation value of the evolutionary object.
6. The method of claim 1, wherein the method is used for evaluating English exercise ability of an author.
7. The method for evaluating the behavioral competence of an evolutionary object of claim 6, wherein the result value of the behavior result sequence comprises:
a correctness factor for spelling a word;
writing a word order reasonableness factor of a sentence;
a complexity factor of spelling a word;
a complexity factor of the written sentence.
8. The method for evaluating the behavioral ability of an evolutionary object as claimed in claim 7, wherein the result value of the behavior result sequence further comprises:
a transitional relationship factor for characterizing the logical relationship between sentences.
9. The method for evaluating the behavioral competence of an evolutionary object according to claim 7, wherein the word order reasonableness factor of the behavioral result sequence is obtained as follows:
enumerating a set of all word orders for a given proposition;
and determining the language order reasonableness factor of the author according to the language order of the author and the scores corresponding to the language orders in all the language order sets.
10. The method for evaluating the behavioral ability of an evolutionary object according to claim 7, wherein the step of generating a behavioral ability evaluation value of the evolutionary object according to the result value and the weight value of the behavior result sequence to characterize the behavioral ability of the evolutionary object specifically comprises:
and weighting and summing to generate an English operation ability evaluation value of the author according to at least one of the correctness factor of the spelling word, the word order reasonableness factor of the written sentence, the complexity factor of the spelling word and the complexity factor of the written sentence and the corresponding weight value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656380.0A CN114004549A (en) | 2021-12-31 | 2021-12-31 | Behavior ability evaluation method of evolutionary object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656380.0A CN114004549A (en) | 2021-12-31 | 2021-12-31 | Behavior ability evaluation method of evolutionary object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114004549A true CN114004549A (en) | 2022-02-01 |
Family
ID=79932384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111656380.0A Pending CN114004549A (en) | 2021-12-31 | 2021-12-31 | Behavior ability evaluation method of evolutionary object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004549A (en) |
-
2021
- 2021-12-31 CN CN202111656380.0A patent/CN114004549A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147436B (en) | Education knowledge map and text-based hybrid automatic question-answering method | |
| Frankenberg-Garcia | Training translators to use corpora hands-on: Challenges and reactions by a group of thirteen students at a UK university | |
| US20110270883A1 (en) | Automated Short Free-Text Scoring Method and System | |
| Tack et al. | Human and automated CEFR-based grading of short answers | |
| Dumal et al. | Adaptive and automated online assessment evaluation system | |
| Idris et al. | Identifying students’ summary writing strategies using summary sentence decomposition algorithm | |
| Maheen et al. | Automatic computer science domain multiple-choice questions generation based on informative sentences | |
| Atapattu et al. | Automated extraction of semantic concepts from semi-structured data: Supporting computer-based education through the analysis of lecture notes | |
| Antoniadis et al. | NLP-based scripting for CALL activities | |
| Riza et al. | Natural language processing and levenshtein distance for generating error identification typed questions on TOEFL | |
| Goulart | Register variation in L1 and L2 student writing: A multidimensional analysis | |
| Virani et al. | Automatic Question Answer Generation using T5 and NLP | |
| Liou et al. | Language supports for journal abstract writing across disciplines | |
| Malhar et al. | Deep learning based Answering Questions using T5 and Structured Question Generation System’ | |
| Zhu et al. | YUN111@ Dravidian-CodeMix-FIRE2020: Sentiment Analysis of Dravidian Code Mixed Text. | |
| CN114004549A (en) | Behavior ability evaluation method of evolutionary object | |
| Han et al. | Japanese sentence pattern learning with the use of illustrative examples extracted from the web | |
| Sawaguchi et al. | Exploring the use of make+ noun collocations by Japanese EFL learners through a bilingual essay corpus | |
| Chung et al. | An annotated news corpus of Malaysian Malay | |
| Potthast et al. | Improving cloze test performance of language learners using web n-grams | |
| Mukherjee et al. | The role of surface, semantic and grammatical features on simplification of Spanish medical texts: A user study | |
| Iftene et al. | Grammar-based automatic extraction of definitions and applications for Romanian | |
| Pieterse | Mapping and modelling word-final n-deletion in Dutch using Twitter data | |
| Kasmaji et al. | Employing natural language processing to analyse grammatical error in a simple Japanese sentence | |
| Almuntashiri et al. | Arabic Auto-CON: Automated Arabic Concordancer Construction from Arabic Corpus |
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 |