Data processing method, device and electronic equipment

Abstract

The present application discloses a data processing method, device and electronic device, the method comprising: obtaining a first data value corresponding to a target text on multiple target indicators; performing a first processing on the first data value to obtain a second data value, the value range of the second data value being negative infinity to positive infinity; performing a normalization processing on the second data value to obtain a third data value corresponding to the target text on each of the target indicators, the normalization processing comprising an inverse tangent processing; and obtaining text quality assessment data of the target text according to the third data value corresponding to the multiple target indicators.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, device and electronic device. Background Art

[0002] With the development of the Internet, there are more and more articles of various types on the Internet. Therefore, it is necessary to conduct quality assessment on these articles.

[0003] At present, there are cases on the Internet where the number of words in articles is increased by plagiarism, copying and pasting multiple paragraphs of content, and there are also cases where articles are automatically generated by machines to take advantage of hot topics, resulting in uneven article quality. The currently commonly used quality assessment schemes that conduct statistical analysis of various indicators in articles still have inaccurate assessments or require a large amount of historical data as a reference. Summary of the invention

[0004] In view of this, the present application provides a data processing method, device and electronic device as follows:

[0005] A data processing method, comprising:

[0006] Obtaining a first data value corresponding to the target text on multiple target indicators;

[0007] Performing a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity;

[0008] Normalizing the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization includes an inverse tangent process;

[0009] According to the third data values ​​corresponding to the multiple target indicators, text quality assessment data of the target text is obtained.

[0010] In the above method, preferably, the third data value is a natural number greater than 0 and less than 1.

[0011] In the above method, preferably, performing a first processing on the first data value to obtain a second data value includes:

[0012] Taking a logarithm of the first data value to obtain a second data value.

[0013] Preferably, the above method further comprises, before taking the logarithm of the first data value:

[0014] The first data value is smoothed by using the statistical value corresponding to the first data value.

[0015] In the above method, preferably, the statistical value corresponding to the first data value is an indicator average value or an indicator median value corresponding to a plurality of preset texts on the target indicator corresponding to the first data value.

[0016] Preferably, the above method further comprises, before obtaining the text quality assessment data of the target text according to the third data value:

[0017] The third data value is processed according to a preset scaling factor so that a value range of the third data value is consistent with a target range.

[0018] In the above method, preferably, obtaining text quality assessment data of the target text according to the third data values ​​corresponding to the multiple target indicators includes:

[0019] According to the weight parameters corresponding to each of the target indicators, at least the third data value is weighted to obtain text quality assessment data of the target text.

[0020] In the above method, preferably, the multiple target indicators include: the number of named entities, the number of new words, text information entropy, the number of text words, the number of text sentences, and the average number of words per sentence.

[0021] A data processing device, comprising:

[0022] A value acquisition unit, used to obtain a first data value corresponding to the target text on multiple target indicators;

[0023] A first processing unit, configured to perform a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity;

[0024] A normalization processing unit, configured to perform normalization processing on the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization processing includes an inverse tangent processing;

[0025] The text evaluation unit is used to obtain text quality evaluation data of the target text according to the third data values ​​corresponding to the multiple target indicators.

[0026] An electronic device, comprising:

[0027] A memory for storing a computer program and data generated by the execution of the computer program;

[0028] A processor is used to execute the computer program to achieve: obtaining a first data value corresponding to a target text on multiple target indicators; performing a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity; performing a normalization processing on the second data value to obtain a third data value corresponding to the target text on each of the target indicators, wherein the normalization processing includes an inverse tangent processing; and obtaining text quality assessment data of the target text according to the third data value corresponding to the multiple target indicators.

[0029] It can be seen from the above technical scheme that in a data processing method, device and electronic device disclosed in the present application, after obtaining the first data value corresponding to the target text on multiple target indicators, the first data value is first processed, and then after obtaining the second data value with a value range of negative infinity to positive infinity, the second data value can be used as the definition domain of the inverse tangent processing to perform inverse tangent processing on the second data value, thereby obtaining a normalized third data value, and finally, the text quality assessment data of the target text can be obtained according to the third data value corresponding to the multiple target indicators. It can be seen that in the present application, the first data value corresponding to the target text on multiple target indicators is processed into a second data value from negative infinity to positive infinity, thereby making the definition domain distribution of the inverse tangent processing negative infinity to positive infinity, thereby making the definition domain distribution more uniform, making the obtained third data value more accurate, and thus the text quality assessment data of the target text finally obtained is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0031] Figure 1 A flowchart of a data processing method provided in Example 1 of the present application;

[0032] Figure 2 A schematic diagram of the structure of a data processing device provided in Embodiment 2 of the present application;

[0033] Figure 3 A schematic diagram of the structure of an electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] refer to Figure 1 As shown, it is a flowchart of a data processing method provided in the first embodiment of the present application, which can be applied to electronic devices capable of calculating data values, such as computers or servers. The technical solution in this embodiment is mainly used to improve the accuracy of text quality assessment.

[0036] Specifically, the method in this embodiment may include the following steps:

[0037] Step 101: Obtain a first data value corresponding to a target text on multiple target indicators.

[0038] The target indicators here may include any one or more of the following: the number of named entities, the number of new words, text information entropy, the number of text words, the number of text sentences, and the average number of words in a single sentence.

[0039] Specifically, in this embodiment, the characters, words, and sentences in the target text can be parsed to obtain the first data values ​​corresponding to the above multiple target indicators. i represents the first data value corresponding to the i-th target indicator, and N represents the total number of target indicators.

[0040] Step 102: Perform a first process on the first data value to obtain a second data value.

[0041] The value range of the second data value is from negative infinity to positive infinity. The first processing is a processing method that can process the first data value into a second data value with a value range from negative infinity to positive infinity.

[0042] Specifically, in this embodiment, the second data value with a value range from negative infinity to positive infinity can be obtained by taking the logarithm of the first data value.

[0043] Furthermore, in this embodiment, before taking the logarithm of the first data value, the first data value can be smoothed using the statistical value corresponding to the first data value, thereby making the second data value obtained after taking the logarithm of the smoothed first data value more evenly distributed within the value range of negative infinity to positive infinity.

[0044] For example, the first data value is divided by the corresponding statistical value of the corresponding target indicator, and the obtained quotient is used as the new first data value to achieve smoothing of the first data value. Thereafter, the logarithm of the smoothed first data value is taken, thereby making the obtained second data value more evenly distributed within the value range of negative infinity to positive infinity.

[0045] Specifically, the statistical value corresponding to the first data value may be an indicator average value or an indicator median value corresponding to a plurality of preset texts on the target indicator corresponding to the first data value.

[0046] The preset text here can be the text of historical articles on one or more selected platforms. That is to say, in this embodiment, relevant texts are pre-selected, and the average values ​​or median values ​​of the indicators of these texts on various target indicators are counted, and then the first data values ​​on the corresponding target indicators are smoothed using the statistical values ​​obtained by these statistics, and then the logarithm of the smoothed first data values ​​is taken, so that the obtained second data values ​​are further evenly distributed in the value range from negative infinity to positive infinity.

[0047] Step 103: normalize the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization process includes an inverse tangent process.

[0048] The value range of the third data value obtained after the normalization process may be 0 to 1, that is, the third data value is a natural number greater than 0 and less than 1.

[0049] Furthermore, in this embodiment, after obtaining the third data value, the third data value may be processed according to a preset scaling factor so that the value range of the third data value is consistent with the target range. The target range here may be preset according to the text evaluation requirements, for example, the target range is in the range of 0-100.

[0050] Based on this, in this embodiment, a corresponding scaling factor is selected according to the ratio between the target range and the original value range of the third data value, and then the third data value is multiplied by the scaling factor to obtain the third data value after the value range is scaled.

[0051] Step 104: Obtain text quality assessment data of the target text according to the third data values ​​corresponding to the multiple target indicators.

[0052] Specifically, in this embodiment, at least the third data value can be weighted according to the weight parameter corresponding to each target indicator to obtain the text quality assessment data of the target text. The weight parameter here can be a natural number between 0 and 1, and the size of the weight parameter represents the importance of the target indicator in the text quality assessment.

[0053] For example, in this embodiment, the third data values ​​corresponding to each target indicator may be weighted and summed according to the weight parameters corresponding to each target indicator to obtain the text quality assessment data of the target text;

[0054] For another example, in this embodiment, the third data values ​​corresponding to each target indicator can be weighted and averaged according to the weight parameters corresponding to each target indicator to obtain the text quality evaluation data of the target text.

[0055] It can be seen from the above technical scheme that in a data processing method provided in Example 1 of the present application, after obtaining the first data value corresponding to the target text on multiple target indicators, the first data value is first processed, and then after obtaining the second data value with a value range of negative infinity to positive infinity, the second data value can be used as the definition domain of the inverse tangent processing to perform inverse tangent processing on the second data value, thereby obtaining a normalized third data value, and finally the text quality assessment data of the target text can be obtained according to the third data value corresponding to the multiple target indicators. It can be seen that in this embodiment, the first data value corresponding to the target text on multiple target indicators is processed into a second data value from negative infinity to positive infinity, thereby making the definition domain distribution of the inverse tangent processing negative infinity to positive infinity, thereby making the definition domain distribution more uniform, making the obtained third data value more accurate, and thus the text quality assessment data of the target text finally obtained is also more accurate.

[0056] refer to Figure 2 , is a schematic diagram of the structure of a data processing device provided in the second embodiment of the present application, which can be configured in an electronic device capable of calculating data values, such as a computer or a server. The technical solution in this embodiment is mainly used to improve the accuracy of text quality assessment.

[0057] Specifically, the device in this embodiment may include the following units:

[0058] A value acquisition unit 201 is used to obtain a first data value corresponding to a target text on multiple target indicators;

[0059] A first processing unit 202 is configured to perform a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity;

[0060] A normalization processing unit 203, configured to perform normalization processing on the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization processing includes an inverse tangent processing;

[0061] The text evaluation unit 204 is used to obtain text quality evaluation data of the target text according to the third data values ​​corresponding to the multiple target indicators.

[0062] It can be seen from the above technical scheme that in a data processing device provided in the second embodiment of the present application, after obtaining the first data value corresponding to the target text on multiple target indicators, the first data value is first processed, and then after obtaining the second data value with a value range of negative infinity to positive infinity, the second data value can be used as the definition domain of the inverse tangent processing to perform inverse tangent processing on the second data value, thereby obtaining a normalized third data value, and finally the text quality assessment data of the target text can be obtained according to the third data value corresponding to the multiple target indicators. It can be seen that in this embodiment, the first data value corresponding to the target text on multiple target indicators is processed into a second data value from negative infinity to positive infinity, thereby making the definition domain distribution of the inverse tangent processing negative infinity to positive infinity, thereby making the definition domain distribution more uniform, making the obtained third data value more accurate, and thus the text quality assessment data of the target text finally obtained is more accurate.

[0063] In one implementation, the third data value is a natural number greater than 0 and less than 1.

[0064] In one implementation, the first processing unit 202 is specifically configured to: take a logarithm of the first data value to obtain a second data value.

[0065] Furthermore, before taking the logarithm of the first data value, the first processing unit 202 is further configured to: perform smoothing processing on the first data value by using the statistical value corresponding to the first data value.

[0066] Preferably, the statistical value corresponding to the first data value is an indicator average value or an indicator median value corresponding to a plurality of preset texts on the target indicator corresponding to the first data value.

[0067] In one implementation, before obtaining the text quality assessment data of the target text according to the third data value, the text assessment unit 204 is further configured to: process the third data value according to a preset scaling factor so that the value range of the third data value is consistent with the target range.

[0068] In one implementation, the text evaluation unit 204 is specifically configured to: perform weighted processing on at least the third data value according to a weight parameter corresponding to each of the target indicators, so as to obtain text quality evaluation data of the target text.

[0069] Preferably, the multiple target indicators include: the number of named entities, the number of new words, text information entropy, the number of text words, the number of text sentences, and the average number of words in a single sentence.

[0070] It should be noted that the specific implementation of each unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0071] refer to Figure 3 , is a schematic diagram of the structure of an electronic device provided in the third embodiment of the present application, and the electronic device can be a computer or a server, etc. The technical solution in this embodiment is mainly used to improve the accuracy of text quality assessment.

[0072] Specifically, the electronic device in this embodiment may include the following structure:

[0073] Memory 301, used to store computer programs and data generated by the execution of the computer programs;

[0074] The processor 302 is used to execute the computer program to achieve: obtaining a first data value corresponding to a target text on multiple target indicators; performing a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity; performing a normalization processing on the second data value to obtain a third data value corresponding to the target text on each of the target indicators, wherein the normalization processing includes an inverse tangent processing; and obtaining text quality assessment data of the target text according to the third data value corresponding to the multiple target indicators.

[0075] It can be seen from the above technical scheme that in an electronic device provided in the third embodiment of the present application, after obtaining the first data value corresponding to the target text on multiple target indicators, the first data value is first processed, and then after obtaining the second data value with a value range of negative infinity to positive infinity, the second data value can be used as the definition domain of the inverse tangent processing to perform inverse tangent processing on the second data value, thereby obtaining a normalized third data value, and finally the text quality assessment data of the target text can be obtained according to the third data value corresponding to the multiple target indicators. It can be seen that in this embodiment, the first data value corresponding to the target text on multiple target indicators is processed into a second data value from negative infinity to positive infinity, thereby making the definition domain distribution of the inverse tangent processing negative infinity to positive infinity, thereby making the definition domain distribution more uniform, making the obtained third data value more accurate, and thus the text quality assessment data of the target text finally obtained is more accurate.

[0076] Taking the quality assessment of texts published on the Internet as an example, this application proposes a technical solution for evaluating the quality of articles (texts) based on density indicators based on multiple dimensions in public opinion scenarios as a standard for information scoring, and based on the relevance to the article, the numerical length indicator of the article, the information entropy size of the article, etc. as calculation indicators. The technical solution proposed in this application can be combined with the actual business direction of public opinion needs, and provide scores (coefficients) and key indicators to facilitate comprehensive calculations with other key indicators required by public opinion (emotion, interaction, influence, etc.); moreover, the technical solution of this application relies on fewer natural language processing models and improves the calculation speed; in addition, the technical solution of this application does not need to rely on manual data annotation training data sets, and can perform incremental calculations without historical data requirements; finally, the technical solution of this application can provide standardized and normalized calculation results, which can assist in quantitative statistics. The specific plan is as follows:

[0077] First, the indicators are evaluated based on the following:

[0078] (1) The longer the article, the richer the content. This can be measured by the number of words, the number of non-stop words, the number of sentences, etc. However, some articles may have many short sentences due to the irregular use of sentence patterns. To eliminate this effect, the number of words in each sentence is increased to balance it.

[0079] (2) The more named entities used in an article, the more likely it is to describe more things and the more information it contains. This can be directly measured by the number of nouns (numerical value) and the number of new words.

[0080] (3) The greater the information entropy of a text, the greater the amount of information it contains.

[0081] (4) Considering that the length or text features of articles published by users on different platforms vary significantly due to usage habits or rules (e.g., users on some social platforms mostly publish short texts, while users on other social platforms can publish longer texts), it is necessary to weaken the absolute impact of different platform factors on the scores and strengthen the influence of the scores within the same platform.

[0082] Based on this, the multi-dimensional density measurement indicators in this application include: the number of named entities (density) and the number of new words (density); statistics of named entities used in the article (the more likely it is to describe more things, the greater the amount of information); full-text information entropy statistics; platform differentiation parameter indicator b value of the source of the article; the number of words in the text; the number of single sentences; the number of paragraphs, etc.

[0083] Based on this, the implementation process of article indicator evaluation in this application is as follows:

[0084] 1. Define the set of indicators required for each text (including but not limited to the number of words in the text, the number of sentences, the average number of words in a sentence, the number of named entities, the number of new words, text information entropy, etc.) and the calculation method of each indicator.

[0085] 2. Sample and count the text data of each platform (such as sampling the data of a certain month), calculate the mean or median value of each indicator above each platform offline, and form an indicator statistical value library.

[0086] 3. Calculate the indicator value of each data online, and use the corresponding indicator value of the corresponding platform in the indicator statistical value library for smoothing during normalization to weaken the differences between different platforms.

[0087] 4. Assign weights to each indicator and perform (linear) weighted calculations to ultimately obtain the content quality score.

[0088] In the specific implementation, for an indicator i in the indicator set, x i is the actual value of the indicator calculated (i.e., the first data value), b i is a smoothing coefficient (i.e., a statistical value), which is smoothed and normalized. Specifically, the present application can be implemented using the following indicator value calculation formula, as shown in formula (1):

[0089]

[0090] The above formula is used to calculate the normalized index value between [0, 1]. The inverse tangent function is calculated after taking the logarithm, and then summed and meaned. It can be multiplied by the total index value as needed (i.e., scaled privacy. For example, if the score value is required to be 100, then y i multiplied by 100).

[0091] Based on the above formula:

[0092] 1. Using the inverse tangent function atan (arctan), the independent variable with a domain of (-∞, +∞() can be mapped to the range of (-π / 2, π / 2), and then through the corresponding mathematical transformation, it can be mapped to the interval (0, 1), which is convenient and clear for calculating indicators.

[0093] As for the index value x, since its value is always positive, in order to obtain a relatively evenly distributed value on (-∞, +∞) for the calculation of the inverse tangent function, it can be transformed by a log function to make the value distribution more even.

[0094] 2. Independent variable x i Divide by b i :When x i >b i , the corresponding logarithmic function range is positive real numbers; when x i <bi , the corresponding logarithmic function range is negative real numbers. This can make the domain of the following inverse tangent function more evenly distributed.

[0095] 3. Calculate b i is the log value of the base, b i It is taken from the indicator statistical value library and is the statistic of the indicator of the platform (such as average, median, etc.).

[0096] 4. Take the inverse tangent and multiply by 2 / π. The range is now [-1, 1]. Add 1 and divide by 2 to change the range to [0, 1].

[0097] 5. For the y calculated above i , perform linear weighted calculation (the weight can be set according to the importance of the indicator), and finally obtain the content quality score S_c, as shown in formula (2):

[0098]

[0099] Based on this, the technical solution of this application is used for machine-generated articles with inconsistent themes, unclear associations, and confusing viewpoints and information. The amount of entities and overall information entropy contained in the articles are often significantly lower than those of high-quality articles. Taking a certain platform as an example, two articles of roughly the same length are compared. Article A is a forwarding lottery, and Article B is a solid article. The score A calculated by the indicator scoring system is much smaller than B. It can be seen that the technical solution of this application can obtain more accurate text quality assessment results.

[0100] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0101] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0103] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, comprising: Obtaining a first data value corresponding to the target text on multiple target indicators; Performing a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity; Normalizing the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization includes an inverse tangent process; Obtaining text quality assessment data of the target text according to the third data values ​​corresponding to the multiple target indicators; wherein the third data value is a natural number greater than 0 and less than 1; The performing a first processing on the first data value to obtain a second data value includes: Taking a logarithm of the first data value to obtain a second data value; Wherein, obtaining text quality assessment data of the target text according to the third data values ​​corresponding to the multiple target indicators includes: According to the weight parameters corresponding to each of the target indicators, at least the third data value is weighted to obtain text quality assessment data of the target text.

2. The method according to claim 1, before taking the logarithm of the first data value, the method further comprises: The first data value is smoothed using the statistical value corresponding to the first data value.

3. According to the method of claim 2, the statistical value corresponding to the first data value is an indicator average value or an indicator median value corresponding to multiple preset texts on the target indicator corresponding to the first data value.

4. The method according to claim 1, before obtaining text quality assessment data of the target text according to the third data value, the method further comprises: The third data value is processed according to a preset scaling factor so that a value range of the third data value is consistent with a target range.

5. The method according to claim 1, wherein the plurality of target indicators include: Number of named entities, number of new words, text information entropy, number of text words, number of text sentences, average number of words per sentence.

6. A data processing device, comprising: A value acquisition unit, used to obtain a first data value corresponding to the target text on multiple target indicators; A first processing unit, configured to perform a first processing on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity; A normalization processing unit, configured to perform normalization processing on the second data value to obtain a third data value corresponding to the target text on each target indicator, wherein the normalization processing includes an inverse tangent processing; A text evaluation unit, configured to obtain text quality evaluation data of the target text according to the third data values ​​corresponding to the plurality of target indicators; wherein the third data value is a natural number greater than 0 and less than 1; The first processing unit is specifically configured to take a logarithm of the first data value to obtain a second data value; The text evaluation unit is specifically used to perform weighted processing on at least the third data value according to the weight parameters corresponding to each of the target indicators, so as to obtain text quality evaluation data of the target text.

7. An electronic device comprising: A memory for storing a computer program and data generated by the execution of the computer program; A processor, configured to execute the computer program to achieve: obtaining a first data value corresponding to a target text on a plurality of target indicators; performing a first process on the first data value to obtain a second data value, wherein the value range of the second data value is from negative infinity to positive infinity; performing a normalization process on the second data value to obtain a third data value corresponding to the target text on each of the target indicators, wherein the normalization process includes an inverse tangent process; obtaining text quality assessment data of the target text according to the third data value corresponding to the plurality of target indicators; wherein the third data value is a natural number greater than 0 and less than 1; The performing a first processing on the first data value to obtain a second data value includes: Taking a logarithm of the first data value to obtain a second data value; Wherein, obtaining text quality assessment data of the target text according to the third data values ​​corresponding to the multiple target indicators includes: According to the weight parameters corresponding to each of the target indicators, at least the third data value is weighted to obtain text quality assessment data of the target text.

Images