CN115391159A - Internet product evaluation method and device, electronic equipment and storage medium - Google Patents
Internet product evaluation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115391159A CN115391159A CN202211130957.9A CN202211130957A CN115391159A CN 115391159 A CN115391159 A CN 115391159A CN 202211130957 A CN202211130957 A CN 202211130957A CN 115391159 A CN115391159 A CN 115391159A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- abnormal information
- score
- internet
- attribute
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of computers and digital medical treatment, and discloses an internet product evaluation method and device, electronic equipment and a storage medium. The evaluation method comprises the following steps: acquiring abnormal information of the internet product within a preset evaluation duration; determining an evaluation attribute corresponding to each of the abnormal information; determining the evaluation score of each evaluation attribute according to the subtraction value corresponding to each abnormal information; and calculating the difference between a preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the internet products. According to the assessment method provided by the embodiment of the application, the obtained assessment total score of the internet products can accurately reflect the high quality and the low quality of the internet products, the assessment result of the internet products is high in accuracy, the assessment objective degree is high, the quality level of the internet products can be accurately reflected, and accurate reference values can be provided for the next improvement of the internet products.
Description
Technical Field
The application relates to the field of computer technology and digital medical treatment, in particular to an internet product evaluation method and device, electronic equipment and a storage medium.
Background
With the rapid development of internet technology, internet products have become an unavailable part in daily life of people, such as APP of WeChat, jingdong, taobao, trembling, safety and health, and the like. These internet products have changed people's way of life, social interaction, and entertainment.
The continuous updating and iteration of the internet products are one of the characteristics of the internet era, and the products can be continuously polished through continuous product and system iteration, so that the user experience is improved. In this process, the system goes through the processes of research, development, modification and release, so that it becomes especially important to know the overall situation of the release quality of an internet product in time. The traditional internet product quality evaluation lacks an objective and accurate evaluation mode, has low accuracy and objectivity on an evaluation result of an internet product, cannot accurately reflect the quality level of the internet product, and cannot provide accurate reference value for the next improvement of the internet product.
Disclosure of Invention
The application aims to provide an internet product evaluation method, an internet product evaluation device, electronic equipment and a storage medium. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of an embodiment of the present application, there is provided an internet product evaluation method including:
acquiring abnormal information of the Internet products within a preset evaluation duration;
determining an evaluation attribute corresponding to each of the abnormal information;
determining the evaluation score of each evaluation attribute according to the corresponding decrement value of each abnormal information;
and calculating the difference between a preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the Internet product.
According to another aspect of embodiments of the present application, there is provided an internet product evaluation apparatus including:
the abnormal information acquisition module is used for acquiring the abnormal information of the Internet products within the preset evaluation duration;
the evaluation attribute determining module is used for determining evaluation attributes corresponding to the abnormal information;
the evaluation score determining module is used for determining the evaluation score of each evaluation attribute according to the corresponding reduction value of each abnormal information;
and the total evaluation score calculating module is used for calculating the difference between the preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the internet product.
According to another aspect of the embodiments of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above evaluation method.
According to another aspect of embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the above-described evaluation method.
The technical scheme provided by one aspect of the embodiment of the application can have the following beneficial effects:
according to the internet product evaluation method provided by the embodiment of the application, the abnormal information of the internet product in the preset evaluation duration is obtained, the evaluation attribute corresponding to each abnormal information is determined, the evaluation score of each evaluation attribute is determined according to the subtraction value corresponding to each abnormal information, the difference value between the preset full score and the sum of all the evaluation scores is calculated, the total evaluation score of the internet product is obtained, the total evaluation score can accurately reflect the quality of the internet product, the accuracy of the evaluation result of the internet product is higher, the objective evaluation degree is high, the quality level of the internet product can be accurately reflected, and the accurate reference value can be provided for the next improvement of the internet product.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application, or may be learned by the practice of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic view illustrating an application environment of an evaluation method of an internet product according to an embodiment of the present application;
FIG. 2 illustrates a flow chart of a method for assessing an Internet product according to some embodiments of the present application;
FIG. 3 illustrates a flow diagram for extracting keywords in some embodiments of the present application;
FIG. 4 is a block diagram illustrating an apparatus for evaluating Internet products according to some embodiments of the present application;
FIG. 5 is a block diagram of an electronic device according to an embodiment of the present application;
FIG. 6 shows a schematic diagram of a computer-readable storage medium of another embodiment of the present application.
The implementation, functional features and advantages of the objects of the present application will be further explained with reference to the accompanying drawings in conjunction with the embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application. 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.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The method for evaluating internet products provided by the embodiment of the application can be applied to the application environment shown in fig. 1, wherein the user terminal communicates with the server terminal through the internet. The server side can receive abnormal information of the internet product sent by the user terminal within a preset evaluation duration, and process and analyze the abnormal information through an internet product evaluation method.
Digital medical internet products such as on-line inquiry applications and the like have been increasingly used in the medical field. In a digital medical service scene, a user terminal of a digital medical Internet product is used for sending abnormal information of the digital medical Internet product within a preset evaluation time, a server side receives the abnormal information, and the abnormal information is processed and analyzed through an evaluation method of the Internet product. The digital medical internet product can be an online inquiry APP, and a user applies for a doctor to perform online inquiry through the online inquiry APP. In an actual application scene, abnormal information generated in the process of using the online inquiry APP by the user is obtained. The abnormal information can comprise the abnormal information of the online inquiry APP and the user poor comment information. The abnormal information of the online inquiry APP comprises login abnormal information, black screen abnormal information, stuck abnormal information, warning abnormal information and other types of information of the online inquiry APP. The user bad comment may be, for example, a comment issued by the user with a low rating after using the online consultation APP.
The user terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, among others. The server side can be implemented by an independent server or a server cluster formed by a plurality of servers. The present application is described in detail below by way of specific examples.
As shown in fig. 2, an embodiment of the present application provides a method for evaluating an internet product, which may include the following steps.
And S10, acquiring abnormal information of the Internet products within a preset evaluation time.
The internet products can be applications like WeChat, taobao APP, jingdong City, mei Tuo APP or digital medical APP. In the embodiment of the application, the abnormal information of the Internet product to be evaluated within the preset evaluation time can be collected. The abnormal information may include abnormal information of the internet product itself and user bad comment information. The abnormal information of the internet product comprises login abnormal information, black screen abnormal information, stuck abnormal information, warning abnormal information and the like of the internet product.
In some embodiments, the internet product to be evaluated may be determined, a preset evaluation duration may be set after the internet product to be evaluated is determined, and the internet product to be evaluated may be released within the preset evaluation duration. The abnormal information of the internet product to be evaluated can be collected and counted according to the preset evaluation duration after the internet product to be evaluated is released.
In some embodiments, the abnormal information of the internet product to be evaluated may be acquired by a network robot or the like. When the abnormal information of the Internet products to be evaluated is collected in a network robot mode, the starting and ending time of the preset evaluation time of the Internet products to be evaluated can be obtained, and according to the starting and ending time of the preset evaluation time and the mark of the Internet products to be evaluated, data information corresponding to the mark of the Internet products to be evaluated is crawled from the Internet, so that the abnormal information of the Internet products to be evaluated is screened out from the data information.
For example, the internet product to be evaluated may be an APP to be evaluated, i.e., an application program. An APP is a computer program that is designed to perform some specific task or tasks. The APP to be evaluated needs to be evaluated before being released and used, and if the preset evaluation duration is 100 days, after the user releases the APP to be evaluated, the abnormal information appearing in the 100-day preset evaluation duration after the APP to be evaluated is released can be obtained through the network robot. A web robot, also called a web crawler, web spider or web page chaser, is a program or script that automatically captures web information according to certain rules.
In some embodiments, the favorable comment information can be acquired according to the user bad comment, so that the advantages of the internet products to be evaluated can be continued and completed subsequently according to the favorable comment information, and the user bad comment is promoted.
And S20, determining evaluation attributes corresponding to each abnormal information.
In the embodiment of the application, the evaluation attribute corresponding to each acquired abnormal information can be determined according to the acquired abnormal information of the internet product to be evaluated within the preset evaluation duration.
In some embodiments, the evaluation attribute of the anomaly information may include: any one or more of a use failure, a user bad comment, a safety warning, and the like.
In some embodiments, determining an evaluation attribute corresponding to each of the anomaly information may include: classifying the acquired abnormal information to obtain the category of the abnormal information; and determining the evaluation attribute corresponding to the category of each abnormal information according to the preset corresponding relation between the category and the evaluation attribute.
For example, the preset evaluation duration may be 100 days, and the abnormality information acquired within the preset evaluation duration of 100 days includes: the method comprises the steps of 5 times of login failure, 2 times of APP flash back, 3 times of user complaints, 2 times of virus attack and 2 times of insufficient memory, determining that the evaluation attribute of abnormal information of the 5 times of login failure and the 2 times of APP flash back is a use fault according to the corresponding relation between the preset category and the evaluation attribute, determining that the evaluation attribute of the abnormal information of the 3 times of user complaints is poor evaluation of a user, and determining that the evaluation attribute of the abnormal information of the 2 times of virus attack and the 2 times of insufficient memory is safe warning.
The abnormal information includes character information in the form of text, for example, text composed of a character comment of the user. For example, the user bad comment includes text information, and a keyword can be acquired by processing the user bad comment. In some embodiments, the keyword of each piece of abnormal information may be obtained by extracting the keyword from the text information, and then the evaluation attribute of each piece of abnormal information may be determined according to the keyword of each piece of abnormal information.
In some embodiments, classifying each of the obtained abnormal information to obtain a category of each of the abnormal information may include: extracting keywords from the acquired text information in each abnormal information to obtain the keywords of each abnormal information; and determining the category corresponding to the keyword of each abnormal information according to a preset keyword category library.
For example, the preset evaluation duration may be 100 days, and the abnormality information acquired within the preset evaluation duration of 100 days includes: after abnormal information appearing in the 100 days is obtained, the abnormal information can be processed, corresponding keywords are extracted from the text information of the abnormal information, and the evaluation attribute of the abnormal information is determined according to the keywords of the abnormal information as follows: the abnormality information corresponding to the use failure includes: accidents of login failure for 3 times and accidents of APP flash back for 2 times occur within 100 days; the abnormality information corresponding to the user's bad comment includes: obtaining complaint information of the user for 3 times within 100 days; the abnormality information corresponding to the safety warning includes: the warning information of virus attack appears 2 times in 100 days, and the warning information of insufficient memory appears 2 times.
In some embodiments, as shown in fig. 3, performing keyword extraction on the obtained text information in each abnormal information to obtain a keyword of each abnormal information may include the following steps:
converting a text of the character information into a graph model, wherein each node in the graph model corresponds to one word in the text; the scores of all nodes in the graph model are calculated through an improved TextRank algorithm in an iterative mode, words corresponding to the nodes with preset numbers before the scores are ranked are used as keywords of the text, and the accuracy of the keywords obtained through the implementation mode is greatly improved. The preset number may be, for example, 5, 8, or 10, and may be specifically set according to actual needs.
The improved TextRank algorithm formula is as follows
Wherein, OW (W) i ) For the optimized weighting factor for node i, in (W) i ) Is a set of nodes pointing to node i, out (W) i ) Is the set of nodes pointed to by node j. d is a damping coefficient, which can prevent the page which is not jumped by clicking a link from depriving the user of the opportunity of browsing downwards, and in the text graph model, there are also nodes without any direction, for example, the value of d can be 0.80, 0.85 or 0.90, and the like, and is specifically set according to the actual needs.
Specifically, converting the text into the graph model may include:
representing text as sentence set T = { S = 1 ,S 2 ,…,S n }, any sentence S i E T as a set of words S i ＝{W 1 ,W 2 ,…,W n }, construct graph model G = (V, E), where V = S 1 ∪S 2 ∪…∪S n When two nodes (words) appear in the same sentence at the same time, there is an edge between the nodes, otherwise there is no edge. When two words are simultaneously located in the same sentence, the two words are called as the same sentence relation.
The influence of the same sentence relation between words on the importance degree score is considered in the TextRank algorithm, but besides the influence of the same sentence relation between words on the importance degree score, the importance degree score of a word is influenced by several factors: word frequency, word length, word position and part of speech. Quantifying the 4 influencing factors, and improving the importance degree score formula in the TextRank algorithm to obtain the improved algorithm formula (1).
Score(W j ) The score of the node j after improvement; OW (W) i ) The optimal weight coefficient for the node i is obtained by quantizing the word frequency, word length, word position and part-of-speech factors, OW (W) i ) Can be expressed as:
OW(W i )＝α×A(W i )+β×B(W i )+γ×C(W i )+δ×D(W i ) (2)
wherein, A (W) i )，B(W i )，C(W i )，D(W i ) α, β, γ, δ are the weight and weight coefficient of the word frequency, word length, word position and part of speech of the node i, respectively, and α + β + γ + δ =1.
The word frequency is an index for measuring the occurrence frequency of words in the text, and the algorithm for extracting the text keywords by using the word frequency is a TFIDF algorithm. TF is the frequency with which words appear in a single text. The IDF reflects the frequency of occurrence of a word in the entire text set (the higher the value, the lower the frequency of occurrence of a word in the entire text set), and the algorithm considers that the higher the frequency of occurrence of a word in a word, the lower the frequency of occurrence in the text set, the greater the influence of the word on the word, and the more likely it is to be a word keyword. The application scenario of the improved algorithm is text keyword extraction,
A(W i )＝Count(W i ,T)/Count(T)。
the length of the word is different, the probability of becoming the keyword is different, and the weight value of the word length is B (W) i ) The setting can be made according to actual statistical data. The first appearance of a word in the first sentence, in the middle of the sentence, in the last sentence or in other positions is also different in the probability of becoming a keyword, and it is generally considered that the probabilities decrease in order. For example, C (W) may be given according to the word appearing at the above position i ) Respectively assigning values as: 1. 0.8, 0.5, 0.3, 0.2. Part of speech weight value D (W) i ) May be set according to actual conditions, for example, the weight values of nouns, verbs, adjectives, adverbs and other parts of speech are set to 0.562, 0.227, respectively,0.122, 0.044 and 0.045.
In the practical application process of the algorithm, besides the damping coefficient d in the above formula, the following parameters affect the efficiency and accuracy of the algorithm: a dynamic window win, an iteration number k and an iteration threshold t.
When a text graph model is constructed, whether two words appear in the same sentence or not needs to be calculated to determine whether edges are connected between nodes corresponding to the two words. In actual operation, a large number of word sets may be generated after a sentence is too long and word segmentation processing is performed, so that the chance of the same sentence between words is increased, the edges are too dense on a graph model and the efficiency of the algorithm and the accuracy of calculation are affected, therefore, the concept of a dynamic window is introduced, a large word set is segmented, and only words located in the same sentence in the window are considered to have the same sentence relation.
The dynamic window win may be expressed as a sentence S i ＝{W 1 ,W 2 ,…,W m For a particular win < m, the sentence is divided into sets: { W 1 ,W 2 ,…,W win }，{W 2 ,W 3 ,…,W win+1 }，……，{W m-win+1 ,W m ,…,W m }。
When the value of the damping coefficient in the formula is less than 1, the algorithm can always be converged by a plurality of iterations, so that the iteration times k and the iteration threshold t can not be set when the algorithm is applied. However, sometimes the iteration is terminated after the algorithm reaches a certain acceptable result, the operation of the algorithm can be terminated early by setting the iteration number k and the iteration threshold t.
When the method is used for extracting the text keywords, the steps of text preprocessing, parameter setting, graph model conversion, initialized node scoring, iterative operation, preset number before score ranking and the like are carried out.
The text preprocessing mainly comprises the steps of cutting words of the text according to sentences and stopping the words. Chinese is different from english in that there is no natural separation symbol (space) between words, and a word must be cut in chinese to change a sentence into a set of words. Stop words refer to words that appear in the text at a high frequency and do not contribute to the semantic information of the text, such as "word" and "like" but "word-like words or conjunctions, numbers, english characters, and so on. The method for removing stop words comprises the steps of establishing a stop word library, traversing the keyword candidate word set and comparing the keyword candidate word set with the stop word library, and deleting the stop word from the candidate word set if the comparison is successful.
The parameter setting refers to the damping coefficient d, the dynamic window size win, and the like mentioned above, and the setting of the dynamic window size needs to be determined through experiments to find a proper win value. Before iterative computation is performed by using the formula, an initial score needs to be assigned to each node, the initial score of the node does not influence the final iterative result, and the initial value of the node is generally 1.
The improved algorithm adds a process of determining the optimized weight coefficients. When text preprocessing is performed, information such as word frequency, word length, word position, word part of speech and the like is labeled.
And S30, determining the evaluation score of each evaluation attribute according to the subtraction value corresponding to each abnormal information.
In the embodiment of the application, the evaluation score of each evaluation attribute can be determined according to the subtraction values corresponding to different abnormal information in each evaluation attribute.
In some embodiments, determining an evaluation score of each evaluation attribute according to the scoring value corresponding to each anomaly information may include: determining target levels corresponding to different abnormal information in each evaluation attribute according to the corresponding relation between preset abnormal information and levels, wherein different target levels correspond to different subtraction values; and acquiring the evaluation score of each evaluation attribute according to the decrement value corresponding to the target level of each abnormal information and the preset weight of each evaluation attribute.
For example, the evaluation attributes may include 3 attributes including use failure, safety warning, user badness, and 4 levels of economic loss of two ten thousand yuan or more, economic loss of two ten thousand yuan or less, customer churn, and no loss in use failure, and the reduction values are 100, 80, 50, and 0, respectively; the safety warnings comprise 4 grades of 3 or more danger warnings, within 3 danger warnings, a serious warning and a slight warning, and the reduction values are respectively 100, 80, 60 and 30; the user bad scores comprise 4 grades of complaint economic loss, performance reduction, general complaint and interface unattractive appearance, and the reduction values are respectively 100, 75, 40 and 20. If a release results in a loss of use by one customer with severe warnings and general complaints, it can be determined that a level 3 use failure, a level 3 safety warning, a level 3 user bad comment is included in the release.
And S40, calculating the difference between the preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the Internet products.
In this embodiment, a difference between a preset full score and a sum of the evaluation scores of the evaluation attributes may be calculated, and the difference is determined as the total evaluation score of the internet product to be evaluated. The total evaluation score is in direct proportion to the quality level of the Internet products, namely the higher the total evaluation score is, the higher the quality level of the Internet products is represented.
By way of example, following the above example, if the release of the APP to be assessed results in a use failure leading to customer loss, with a severe warning, with a general complaint, and if it is determined that the assessment score for the use failure attribute is 50 × 60% =30, the assessment score for the safety warning attribute is 50 × 20% =10, and the assessment score for the user difference attribute is 50 × 30% =15, it is possible to calculate that the sum of the assessment scores for the individual assessment attributes is 60 × 50% +50 × 20% +50 × 30% =55, and determine that the difference between the preset full score and the sum of the assessment attributes is 100- (50 60% +50 × 20%) 50 for the total assessment of the internet product.
In some embodiments, the method of this embodiment may further include:
and S50, generating an evaluation report of the Internet product according to the total evaluation score of the Internet product to be evaluated and the evaluation scores of all the evaluation attributes.
In the embodiment of the application, the quality evaluation report of the internet product to be evaluated can be generated according to the evaluation total score of the internet product to be evaluated and the evaluation scores of all the evaluation attributes.
In some embodiments, generating a quality evaluation report of the internet product to be evaluated according to the total evaluation score and the evaluation scores of the evaluation attributes of the internet product to be evaluated comprises: sequencing the evaluation attributes according to the magnitude sequence of the evaluation scores of the evaluation attributes; generating an evaluation report of the Internet products to be evaluated according to the evaluation total score of the Internet products to be evaluated and the arrangement sequence of each evaluation attribute; the evaluation report comprises at least one of abnormal information, evaluation scores and quality scores of each evaluation attribute.
In some embodiments, the quality evaluation report may include, but is not limited to, anomaly information, evaluation score, quality score, economic loss and the like of each evaluation attribute, so that a problem that the internet product needs to be improved can be determined according to the anomaly information, evaluation score, quality score, economic loss and the like of each evaluation attribute in the quality evaluation report, so as to improve the internet product.
For example, if the quality evaluation report includes that the level corresponding to the virus attack in the security warning information of the APP to be evaluated is 80 and the preset weight is 60%, it may be determined that the problem that the APP to be evaluated needs to be improved is to improve the security of the APP to be evaluated, so that the user may improve the APP to be evaluated according to the warning information to avoid the APP to be evaluated from being attacked by the virus.
According to the method for evaluating the internet products, the abnormal information of the internet products within the preset evaluation duration is obtained, the evaluation attribute corresponding to each abnormal information is determined, the evaluation score of each evaluation attribute is determined according to the decrement value corresponding to each abnormal information, the difference value between the preset full score and the sum of all the evaluation scores is calculated, the evaluation total score of the internet products is obtained, the evaluation total score can accurately reflect the quality of the internet products, the evaluation result of the internet products is high in accuracy and objective evaluation degree, the quality level of the internet products can be accurately reflected, the accurate reference value can be provided for the next improvement of the internet products, the problems existing in the internet products can be prevented and solved in advance, and the quality of the internet products is improved.
Another embodiment of the present application provides an internet product evaluation method, including: acquiring abnormal information of an Internet product to be evaluated within a preset evaluation duration; determining evaluation attributes corresponding to the acquired abnormal information; determining target levels corresponding to different abnormal information in each evaluation attribute according to the corresponding relation between preset abnormal information and levels, wherein different target levels correspond to different subtraction values; determining the evaluation score of each evaluation attribute according to the subtraction value corresponding to the target level of different abnormal information in each evaluation attribute and the preset weight of each evaluation attribute; and calculating a difference value between a preset full score and the sum of the evaluation scores of the evaluation attributes, and determining the difference value as the total evaluation score of the internet products to be evaluated.
In the embodiment of the application, the target levels corresponding to different abnormal information in each evaluation attribute can be determined according to the preset corresponding relation between the abnormal information and the levels, wherein different target levels correspond to different subtraction values.
In the embodiment of the application, the evaluation score of each evaluation attribute can be determined according to the subtraction values corresponding to the target levels of different abnormal information in each evaluation attribute and the preset weight of each evaluation attribute.
For example, the evaluation attributes may include 3 attributes of use failure, safety warning, and user poor evaluation, the 3 attributes are respectively weighted to 50%, 20%, and 30%, wherein the use failure includes 4 levels of economic loss of fifty thousand or more, economic loss of fifty thousand or less, customer loss, and no loss, and the reduction values are respectively 100, 70, 60, and 0; safety warnings include 4 levels of 3 and more hazard warnings, within 3 hazard warnings, severe warning, and mild warning, with respective decremental values of 100, 70, 50, and 20; the user bad comment comprises 4 grades of complaint economic loss, performance reduction, general complaint and unattractive interface, and the reduction values are respectively 100, 80, 50 and 30. If a release of an APP to be evaluated results in a usage failure of one customer churn, with severe warnings, with general complaints, it can be determined that the evaluation score for the usage failure attribute is 60 × 50% =30, the evaluation score for the safety warning attribute is 50 × 20% =10, and the evaluation score for the customer bad attribute is 50 × 30% =15.
In the embodiment of the application, a difference value between a preset full score and the sum of the evaluation scores of the evaluation attributes can be calculated, and the difference value is determined as the total evaluation score of the internet products to be evaluated.
The method of this embodiment may further include: and generating a quality evaluation report of the Internet products to be evaluated according to the evaluation total score of the Internet products to be evaluated and the evaluation scores of all the evaluation attributes.
In the embodiment of the application, the quality evaluation report of the internet product to be evaluated can be generated according to the evaluation total score of the internet product to be evaluated and the evaluation scores of all the evaluation attributes. In some embodiments, the quality assessment report includes information such as anomaly information, assessment scores, quality scores, economic losses, and the like for each assessment attribute.
The method provided by the embodiment of the application can be used for evaluating the quality of the Internet product to be evaluated, and is beneficial to preventing and solving problems in advance so as to improve the quality of the Internet product.
As shown in fig. 4, another embodiment of the present application provides an internet product evaluation apparatus including:
the abnormal information acquisition module is used for acquiring the abnormal information of the Internet products within the preset evaluation duration;
the evaluation attribute determining module is used for determining evaluation attributes corresponding to the abnormal information;
the evaluation score determining module is used for determining the evaluation score of each evaluation attribute according to the corresponding reduction value of each abnormal information;
and the total evaluation score calculating module is used for calculating the difference between a preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the Internet product.
In some embodiments, the evaluation attribute determination module comprises:
the classification unit is used for classifying the acquired abnormal information to obtain the category of the abnormal information;
and the determining unit is used for determining the evaluation attribute corresponding to the category of each piece of abnormal information according to the preset corresponding relation between the category and the evaluation attribute.
In some embodiments, classifying each of the obtained abnormal information to obtain a category of each of the abnormal information includes:
extracting keywords from the acquired text information in each abnormal information to obtain the keywords of each abnormal information;
and determining the category corresponding to the keyword of each abnormal information according to a preset keyword category library.
In some embodiments, extracting keywords from the obtained text information in each piece of abnormal information to obtain the keywords of each piece of abnormal information includes:
converting the text of the character information into a graph model, wherein each node in the graph model corresponds to one word in the text;
and iteratively calculating the importance degree score of each node in the graph model through an improved TextRank algorithm, and taking words corresponding to nodes with preset number before the score ranking as the keywords of the text.
In some embodiments, determining an evaluation score of each evaluation attribute according to the scoring value corresponding to each anomaly information includes:
determining target levels corresponding to different abnormal information in each evaluation attribute according to the corresponding relation between preset abnormal information and levels, wherein different target levels correspond to different subtraction values;
and acquiring the evaluation score of each evaluation attribute according to the decrement value corresponding to the target level of each abnormal information and the preset weight of each evaluation attribute.
In some embodiments, the apparatus may further comprise:
and the evaluation report generation module is used for generating the evaluation report of the Internet products according to the total evaluation score of the Internet products to be evaluated and the evaluation scores of all the evaluation attributes.
In some embodiments, generating a quality evaluation report of the internet product to be evaluated according to the total evaluation score and the evaluation scores of the evaluation attributes of the internet product to be evaluated comprises:
sequencing the evaluation attributes according to the magnitude sequence of the evaluation scores of the evaluation attributes;
generating a quality evaluation report of the Internet products to be evaluated according to the evaluation total score of the Internet products to be evaluated and the arrangement sequence of each evaluation attribute;
the quality evaluation report comprises any one or more of abnormal information, evaluation scores and quality scores of all evaluation attributes.
The evaluation device for the internet products, provided by the embodiment of the application, can acquire abnormal information of the internet products in a preset evaluation time period, determine evaluation attributes corresponding to each abnormal information, determine evaluation scores of each evaluation attribute according to subtraction values corresponding to each abnormal information, and calculate a difference value between a preset full score and the sum of all the evaluation scores to obtain an evaluation total score of the internet products, wherein the evaluation total score can accurately reflect the quality of the internet products, the evaluation result of the internet products is higher in accuracy, the evaluation objective degree is high, the quality level of the internet products can be accurately reflected, and accurate reference values can be provided for the next improvement of the internet products.
Another embodiment of the application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executes the program to implement the method for evaluating an internet product according to any one of the above embodiments.
As shown in fig. 5, the electronic device 10 may include: the system comprises a processor 100, a memory 101, a bus 102 and a communication interface 103, wherein the processor 100, the communication interface 103 and the memory 101 are connected through the bus 102; the memory 101 stores a computer program that can be executed on the processor 100, and the processor 100 executes the computer program to perform the method provided by any of the foregoing embodiments.
The Memory 101 may include a high-speed Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 101 is used for storing a program, and the processor 100 executes the program after receiving an execution instruction, and the method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 100, or implemented by the processor 100.
The electronic equipment provided by the embodiment of the application and the method provided by the embodiment of the application are based on the same inventive concept, and have the same beneficial effects as the method adopted, operated or realized by the electronic equipment.
Another embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method for evaluating an internet product according to any one of the above embodiments.
Referring to fig. 6, a computer readable storage medium is shown as an optical disc 20, on which a computer program (i.e. a program product) is stored, which when executed by a processor, performs the method provided by any of the foregoing embodiments.
It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, or other optical and magnetic storage media, which are not described in detail herein.
The computer-readable storage medium provided by the above-mentioned embodiments of the present application and the method provided by the embodiments of the present application have the same advantages as the method adopted, executed or implemented by the application program stored in the computer-readable storage medium.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, a module may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same component. There may or may not be clear boundaries between the various modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with the examples based on this disclosure. The required structure for constructing such a device will be apparent from the description above. In addition, this application is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best mode of use of the present application.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above-mentioned embodiments only express the embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (10)
1. An evaluation method of an internet product, comprising:
acquiring abnormal information of the Internet products within a preset evaluation duration;
determining an evaluation attribute corresponding to each of the abnormal information;
determining the evaluation score of each evaluation attribute according to the subtraction value corresponding to each abnormal information;
and calculating the difference between a preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the internet products.
2. The method of claim 1, wherein determining an evaluation attribute corresponding to each of the anomaly information comprises:
classifying the acquired abnormal information to obtain the category of the abnormal information;
and determining the evaluation attribute corresponding to the category of each abnormal information according to the preset corresponding relation between the category and the evaluation attribute.
3. The method according to claim 2, wherein the classifying the acquired each anomaly information to obtain a category of each anomaly information includes:
extracting keywords from the acquired text information in each abnormal information to obtain the keywords of each abnormal information;
and determining the category corresponding to the keyword of each abnormal information according to a preset keyword category library.
4. The method according to claim 3, wherein the extracting keywords from the text information in each of the obtained abnormal information to obtain the keywords of each of the abnormal information comprises:
converting the text of the character information into a graph model, wherein each node in the graph model corresponds to one word in the text;
and iteratively calculating the importance degree score of each node in the graph model through an improved TextRank algorithm, and taking words corresponding to a preset number of nodes before the score ranking as the keywords of the text.
5. The method according to claims 1 to 4, wherein the determining the evaluation score of each evaluation attribute according to the corresponding decrement value of each abnormal information comprises:
determining target levels corresponding to different abnormal information in each evaluation attribute according to the corresponding relation between preset abnormal information and the levels, wherein the different target levels correspond to different subtraction values;
and acquiring the evaluation score of each evaluation attribute according to the decrement value corresponding to the target level of each abnormal information and the preset weight of each evaluation attribute.
6. The method of claims 1-4, further comprising:
and generating an evaluation report of the Internet products according to the evaluation total score of the Internet products to be evaluated and the evaluation scores of all the evaluation attributes.
7. The method of claim 6, wherein the generating a quality evaluation report of the internet product to be evaluated according to the total evaluation score and the evaluation scores of the evaluation attributes of the internet product to be evaluated comprises:
sequencing the evaluation attributes according to the magnitude sequence of the evaluation scores of the evaluation attributes;
generating an evaluation report of the Internet products to be evaluated according to the evaluation total score of the Internet products to be evaluated and the arrangement sequence of each evaluation attribute;
the evaluation report comprises at least one of abnormal information, evaluation scores and quality scores of each evaluation attribute.
8. An internet product evaluation apparatus, comprising:
the abnormal information acquisition module is used for acquiring the abnormal information of the Internet products within the preset evaluation duration;
the evaluation attribute determining module is used for determining evaluation attributes corresponding to the abnormal information;
the evaluation score determining module is used for determining the evaluation score of each evaluation attribute according to the decrement value corresponding to each abnormal information;
and the total evaluation score calculating module is used for calculating the difference between the preset full score and the sum of all the evaluation scores to obtain the total evaluation score of the internet product.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program is executable by a processor for implementing the method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211130957.9A CN115391159A (en) | 2022-09-16 | 2022-09-16 | Internet product evaluation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211130957.9A CN115391159A (en) | 2022-09-16 | 2022-09-16 | Internet product evaluation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115391159A true CN115391159A (en) | 2022-11-25 |
Family
ID=84125785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211130957.9A Pending CN115391159A (en) | 2022-09-16 | 2022-09-16 | Internet product evaluation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115391159A (en) |
-
2022
- 2022-09-16 CN CN202211130957.9A patent/CN115391159A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10878004B2 (en) | Keyword extraction method, apparatus and server | |
| US11544459B2 (en) | Method and apparatus for determining feature words and server | |
| US20180308160A1 (en) | Risk assessment method and system | |
| JP7153004B2 (en) | COMMUNITY Q&A DATA VERIFICATION METHOD, APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM | |
| US11755841B2 (en) | Method for updating a knowledge base of a sentiment analysis system | |
| CN108376129B (en) | Error correction method and device | |
| CN110929145A (en) | Public opinion analysis method, public opinion analysis device, computer device and storage medium | |
| CN106874253A (en) | Recognize the method and device of sensitive information | |
| CN113139134B (en) | Method and device for predicting popularity of user-generated content in social network | |
| CN109829151B (en) | Text segmentation method based on hierarchical dirichlet model | |
| RU2759087C1 (en) | Method and system for static analysis of executable files based on predictive models | |
| US11036818B2 (en) | Method and system for detecting graph based event in social networks | |
| CN105405051B (en) | Financial event prediction method and device | |
| CN107527289B (en) | Investment portfolio industry configuration method, device, server and storage medium | |
| CN110417751B (en) | Network security early warning method, device and storage medium | |
| Shi et al. | Segmentation quality evaluation based on multi-scale convolutional neural networks | |
| CN111611786A (en) | Text similarity calculation method and device | |
| WO2022039803A1 (en) | Identifying noise in verbal feedback using artificial text from non-textual parameters and transfer learning | |
| CN111324725B (en) | Topic acquisition method, terminal and computer readable storage medium | |
| CN115481694B (en) | Data enhancement method, device and equipment for training sample set and storage medium | |
| CN111639161A (en) | System information processing method, apparatus, computer system and medium | |
| CN116561320A (en) | Method, device, equipment and medium for classifying automobile comments | |
| CN116225848A (en) | Log monitoring method, device, equipment and medium | |
| CN109522928A (en) | Theme sentiment analysis method, apparatus, electronic equipment and the storage medium of text | |
| CN112818221B (en) | Entity heat determining method and device, electronic equipment and storage medium |
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 |