CN115082098A

CN115082098A - Evaluation information processing method and apparatus, storage medium, and electronic device

Info

Publication number: CN115082098A
Application number: CN202110272118.XA
Authority: CN
Inventors: 杜静
Original assignee: Beijing Dianzhi Technology Co ltd
Current assignee: Beijing Dianzhi Technology Co ltd
Priority date: 2021-03-12
Filing date: 2021-03-12
Publication date: 2022-09-20

Abstract

The disclosure belongs to the technical field of computers, and relates to an evaluation information processing method and device, a storage medium and electronic equipment. The method comprises the following steps: the service provider sends a score calculation request generated by a trigger operation acting on the service provider; the service using end receives the score calculation request, acquires evaluation index information and an index hierarchical structure generated by the evaluation index information from the Hadoop cluster, and performs weight generation processing on the evaluation index information to obtain index weight; performing matrix construction processing on the evaluation index information to obtain an evaluation matrix, and performing fuzzy conversion processing on the index weight and the evaluation matrix to obtain an index evaluation result; performing index aggregation calculation on the index evaluation result and the index weight by using a Spark cluster to obtain a target evaluation result, performing score conversion calculation on the target evaluation result to obtain a target evaluation score, and sending the target evaluation score; and the service provider receives and displays the target evaluation score. The calculation of the bid evaluation score in the present disclosure is accurate and efficient.

Description

Evaluation information processing method and apparatus, storage medium, and electronic device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an evaluation information processing method, an evaluation information processing apparatus, a computer-readable storage medium, and an electronic device.

Background

For the evaluation of the provided service, goods and other objects, the factors influencing the satisfaction degree of the user are very many, but the influence is different. The evaluation information processing method generally used is to perform a one-time questionnaire investigation and then perform independent analysis on each question.

However, the calculation and evaluation results of the satisfaction evaluation method are difficult to find a uniform measurement standard due to subjective cognition of different teams and different roles, the sense of acceptance of other users is low, and factors affecting each link of satisfaction evaluation are difficult to be comprehensively covered by a single-level index analysis mode. Moreover, the user usually uses the fuzzy language evaluation which is difficult to measure, so that a scientific and quantitative conclusion is difficult to draw, evaluation work in practice is influenced, and a quantitative evaluation score cannot be quickly and accurately displayed to a service provider.

In view of the above, there is a need in the art to develop a new evaluation information processing method and apparatus.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

An object of the present disclosure is to provide an evaluation information processing method, an evaluation information processing apparatus, a computer-readable storage medium, and an electronic device, which overcome technical problems of consistency, quantification, accuracy, and high efficiency of evaluation information processing due to limitations of related art, at least to some extent.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to a first aspect of embodiments of the present invention, there is provided an evaluation information processing method including:

the method comprises the steps that a service provider sends a score calculation request to a service user, wherein the score calculation request is generated through a trigger operation acting on the service provider;

the service using end receives the score calculation request, acquires evaluation index information and an index hierarchical structure generated by the evaluation index information from a Hadoop cluster, and performs weight generation processing on the evaluation index information according to the index hierarchical structure to obtain index weight;

performing matrix construction processing on the evaluation index information to obtain an evaluation matrix, and performing fuzzy conversion processing on the index weight and the evaluation matrix to obtain an index evaluation result of the evaluation index information;

performing index aggregation calculation on the index evaluation result and the index weight by using a Spark cluster to obtain a target evaluation result, performing score conversion calculation on the target evaluation result by using the Spark cluster to obtain a target evaluation score, and sending the target evaluation score to the service provider;

and the service provider receives the target evaluation score and displays the target evaluation score.

In one exemplary embodiment of the present invention,

the method for acquiring evaluation index information from a Hadoop cluster and generating an index hierarchy by the evaluation index information comprises the following steps:

obtaining evaluation index information and hierarchical structure index information corresponding to the evaluation index information from a Hadoop cluster;

and carrying out hierarchical structure generation processing on the evaluation index information and the hierarchical structure index information to obtain an index hierarchical structure.

In one exemplary embodiment of the present invention,

the performing weight generation processing on the evaluation index information according to the index hierarchical structure to obtain an index weight includes:

performing index relative comparison on the evaluation index information and the hierarchical structure index information in the index hierarchical structure to determine a relative weight, and performing weight sorting processing on the relative weight to construct a judgment matrix;

and carrying out assignment calculation on the judgment matrix to obtain a weight calculation result, and carrying out normalization processing on the weight calculation result to obtain an index weight corresponding to the evaluation index information.

In one exemplary embodiment of the present invention,

the assigning calculation of the judgment matrix to obtain a weight calculation result includes:

obtaining a detection coefficient corresponding to the evaluation index information and the hierarchical structure index information, and detecting and calculating the judgment matrix to obtain a consistency index;

carrying out consistency calculation on the inspection coefficient and the consistency index to obtain an inspection result, and obtaining a result threshold corresponding to the inspection result;

and if the test result is smaller than the result threshold value, performing characteristic root calculation on the judgment matrix to obtain a weight calculation result.

In an exemplary embodiment of the present invention, the matrix constructing the evaluation index information to obtain an evaluation matrix includes:

determining evaluation factor information corresponding to the evaluation index information, and carrying out evaluation frequency statistics on the evaluation index information and the evaluation factor information to obtain the evaluation frequency of the evaluation index information appearing in the evaluation factors;

and carrying out fuzzy statistical calculation on the evaluation times to obtain a time calculation result, and carrying out single-factor fuzzy evaluation processing on the time calculation result to generate an evaluation matrix.

In an exemplary embodiment of the present invention, the performing score conversion on the target evaluation result by using the Spark cluster to obtain a target evaluation score includes:

acquiring a factor score corresponding to the evaluation factor information;

and performing score conversion on the target evaluation result and the factor score by using the Spark cluster to obtain a target evaluation score.

In an exemplary embodiment of the present invention, the performing an index aggregation calculation on the index evaluation result and the index weight determination by using a Spark cluster to obtain a target evaluation result includes:

performing polymerization treatment on the index evaluation result to obtain a polymerization matrix;

and carrying out fuzzy synthesis calculation on the aggregation matrix and the index weight by utilizing a Spark cluster to determine a target evaluation result.

According to a second aspect of the embodiments of the present invention, there is provided an evaluation information processing apparatus including:

the system comprises a request sending module, a score calculating module and a score calculating module, wherein the request sending module is configured to send a score calculating request to a service using end through a service providing end, and the score calculating request is generated through a triggering operation acting on the service providing end;

the score calculation module is configured to receive the score calculation request through a service using end, acquire evaluation index information and an index hierarchical structure generated by the evaluation index information from a Hadoop cluster, and perform weight generation processing on the evaluation index information according to the index hierarchical structure to obtain index weight;

and the score display module is configured to receive the target evaluation score through the service provider and display the target evaluation score. According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus including: a processor and a memory; wherein the memory has stored thereon computer-readable instructions which, when executed by the processor, implement the evaluation information processing method of any of the above-described exemplary embodiments.

According to a fourth aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the evaluation information processing method in any of the above-described exemplary embodiments.

As can be seen from the foregoing technical solutions, the evaluation information processing method, the evaluation information processing apparatus, the computer storage medium, and the electronic device in the exemplary embodiments of the present invention have at least the following advantages and positive effects:

in the method and the device provided by the exemplary embodiment of the disclosure, on one hand, an index hierarchical structure of evaluation index information is generated, a multi-level structure is provided for an index analysis mode, and the evaluation index information of each link influencing evaluation information processing is comprehensively covered; and on the other hand, the index weight of the evaluation index information is determined, so that the evaluation of the satisfaction degree keeps consistency under the action of multiple factors, the sense of identity of each link is obtained, further, the target evaluation result is calculated to determine the target evaluation score, the fuzzy quantitative calculation of the evaluation result is realized, the user can quickly and accurately obtain the macroscopic and quantitative satisfaction degree score, the whole evaluation process is more objective and fair, and the basis of long-term monitoring and comparison is provided.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

Fig. 1 schematically illustrates a flow chart of an evaluation information processing method in an exemplary embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow diagram of a method of generating a hierarchy of metrics in an exemplary embodiment of the disclosure;

FIG. 3 schematically illustrates a model structure diagram of the ACSI model in an exemplary embodiment of the present disclosure;

fig. 4 is a schematic structural diagram schematically illustrating an index hierarchy in an application scenario of evaluation information processing of a technical solution provider in an exemplary embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of a method of determining weights of metrics in an exemplary embodiment of the disclosure;

FIG. 6 is a schematic diagram illustrating a structure of an index hierarchy converted in an exemplary embodiment of the present disclosure;

FIG. 7 is a flow chart diagram schematically illustrating a method of calculating a weight calculation result in an exemplary embodiment of the present disclosure;

fig. 8 is a schematic diagram showing a configuration of an index weight in an application scenario of evaluation information processing by a technical solution provider in an exemplary embodiment of the present disclosure;

FIG. 9 schematically illustrates a flow diagram of a method of generating an evaluation matrix in an exemplary embodiment of the disclosure;

FIG. 10 schematically illustrates a flow chart of a method of determining a target evaluation result in an exemplary embodiment of the disclosure;

FIG. 11 schematically illustrates a flow chart of a method of deriving a target rating score in an exemplary embodiment of the disclosure;

fig. 12 is a flowchart schematically illustrating an evaluation information processing method in an application scenario in an exemplary embodiment of the present disclosure;

fig. 13 schematically shows a configuration diagram of an evaluation information processing apparatus in an exemplary embodiment of the present disclosure;

fig. 14 schematically illustrates an electronic device for implementing the rating information processing method in an exemplary embodiment of the present disclosure;

fig. 15 schematically illustrates a computer-readable storage medium for implementing the evaluation information processing method in an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

The terms "a," "an," "the," and "said" are used in this specification to denote the presence of one or more elements/components/parts/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. other than the listed elements/components/etc.; the terms "first" and "second", etc. are used merely as labels, and are not limiting on the number of their objects.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities.

Aiming at the problems in the related art, the disclosure provides an evaluation information processing method applied to a terminal. Fig. 1 shows a flowchart of an evaluation information processing method, which, as shown in fig. 1, comprises at least the following steps:

s110, the service provider sends a score calculation request to the service user, wherein the score calculation request is generated through a trigger operation acting on the service provider;

and S120, the service using end receives the score calculation request, acquires evaluation index information and an index hierarchical structure generated by the evaluation index information from the Hadoop cluster, and performs weight generation processing on the evaluation index information according to the index hierarchical structure to obtain index weight.

And S130, performing matrix construction processing on the evaluation index information to obtain an evaluation matrix, and performing fuzzy conversion processing on the index weight and the evaluation matrix to obtain an index evaluation result of the evaluation index information.

And S140, carrying out index aggregation calculation on the index evaluation result and the index weight by using the Spark cluster to obtain a target evaluation result, carrying out score conversion calculation on the target evaluation result by using the Spark cluster to obtain a target evaluation score, and sending the target evaluation score to the service provider.

And S150, the service provider receives the target evaluation score and displays the target evaluation score.

In the exemplary embodiment of the present disclosure, on one hand, an index hierarchical structure of evaluation index information is generated, a multi-level structure is provided for an index analysis manner, and evaluation index information of each link affecting evaluation information processing is comprehensively covered; and on the other hand, the index weight of the evaluation index information is determined, so that the evaluation of the satisfaction degree keeps consistency under the action of multiple factors, the acceptance of each link is obtained, further, the target evaluation result is calculated to determine the target evaluation score, the fuzzy quantitative calculation of the evaluation result is realized, the user can quickly and accurately obtain the macroscopic and quantitative satisfaction degree score, the whole evaluation process is more objective and fair, and the basis of long-term monitoring and comparison is provided.

The following describes each step of the evaluation information processing method in detail.

In step S110, the service provider sends a score calculation request, which is generated by a trigger operation acting on the service provider, to the service consumer.

In an exemplary embodiment of the present disclosure, the service provider is a terminal used by a technical solution provider, and the service user is a terminal used by a user such as an enterprise user.

In an application scene that an enterprise user performs satisfaction evaluation on a technical solution provider, the enterprise user can initiate technical service requirements, the technical solution provider can provide different teams for the enterprise user to form pre-sales support, technical development, after-sales service, business operation and the like, assistance is performed on each link of technical implementation and technical landing, development of system requirements given to enterprise customers is completed, and stable operation of the system is guaranteed.

Therefore, after the technical solution provider provides technical service support to the enterprise user, a value calculation request can be sent to the service using end through the service providing end so as to request the service using end for the service evaluation value supported by the technical service, namely the target evaluation value.

In particular, the score calculation request may be generated by the technical solution provider through a triggering operation acting on the service provider.

For example, a technical solution provider may trigger a touch operation such as a click or a long press on a service provider through a touch medium such as a finger, so as to send a score calculation request to a service consumer. In addition, the technical solution provider may also send the score calculation request through other triggering operations, which is not limited in this exemplary embodiment.

In step S120, the service user receives the score calculation request, obtains evaluation index information and an index hierarchy generated from the evaluation index information from the Hadoop cluster, and performs weight generation processing on the evaluation index information according to the index hierarchy to obtain an index weight.

In an exemplary embodiment of the disclosure, after the service using end receives a score calculation request sent by the service providing end, evaluation index information may be obtained from the Hadoop cluster, and a corresponding index hierarchical structure may be generated according to the evaluation index information.

The Hadoop cluster is built based on Hadoop and can store evaluation index information and the like.

The evaluation index information may be each index for evaluating the service satisfaction with the service provider or the like by the user. In different application scenarios, the evaluation index information may be various indexes applicable to the application scenario, and this exemplary embodiment is not particularly limited in this respect. Further, a corresponding index hierarchy structure may be generated from the evaluation index information.

In an alternative embodiment, fig. 2 shows a flow diagram of a method of generating a hierarchy of metrics, as shown in fig. 2, the method comprising at least the steps of: in step S210, evaluation index information and hierarchical structure index information corresponding to the evaluation index information are acquired from the Had oop cluster.

The hierarchical structure Index information may be a structure variable in an ACSI (American Customer satisfacton Index) model.

The ACSI model is a macroscopic index for measuring output quality, and comprehensively evaluates the satisfaction degree level of users on the basis of products, services, consumption processes, application processes and the like. In addition, only the expansion and contraction change of data correlation is carried out in the execution process of the AC SI model, or the process of fuzzification conversion from qualitative analysis to quantitative analysis is carried out, so that the characteristics of the data are not influenced.

FIG. 3 shows a model structure diagram of the ACSI model, which has 6 structural variables, as shown in FIG. 3, and customer satisfaction is the final desired target variable. The selection of 6 structural variables in the ACSI model is based on the theory of client behavior, each structural variable includes one or more observed variables, and the observed variables can be obtained by collecting data through actual investigation.

In the ACSI model, the observation variables are evaluation index information, and the hierarchy index information is 6 structural variables of customer expectation, perceived quality, perceived value, customer complaint, customer loyalty, and customer satisfaction.

Wherein customer expectations refer to an estimate of a user's quality of a product or service before purchasing and using the product or service; the perceived quality refers to the actual feeling of the product or service after the user uses the product or service, including the feeling of product customization, namely, the feeling of meeting the personal demand degree, the feeling of product reliability and the feeling of product quality overall; the perception value reflects the subjective feeling of the user on the benefit obtained by the user after the quality and the price of the product or the service are integrated; the customer complaints refer to the acceptance of the fair and fair disclosure of the customers in the complaint handling process; customer loyalty refers to the likelihood of a user making repeated purchases and the ability to tolerate price changes, manifested as a user's repeated purchases of the product or service or recommendations to other customers, etc.

In step S220, the evaluation index information and the hierarchical structure index information are subjected to hierarchical structure generation processing to obtain an index hierarchical structure.

After determining the evaluation index information and the hierarchy structure index information, a corresponding index hierarchy may be generated in accordance with the evaluation index information and the hierarchy structure index information.

In an application scene that an enterprise user performs satisfaction evaluation on a technical solution provider, the enterprise user can initiate technical service requirements, the technical solution provider provides different teams comprising pre-sale support, technical development, after-sale service, business operation and the like, assistance is performed on each link of technical implementation and technical landing, development of system requirements given to enterprise customers is completed, and stable operation of the system is guaranteed.

Thus, the evaluation index information that an enterprise user can evaluate a technical solution provider in this process may include attitude (personnel), initiative (personnel), cognition (brand), experience (product/activity), communication comprehension ability (personnel), professional skills (personnel), problem solving method (service), problem solving timeliness (service), problem solving effect (service), degree of demand matching (product), price (product/activity), commitment achievement (service), functional richness (product), stability (product), performance (product), security (product), credibility (personnel), rationality (service), fairness (service), timeliness (service), renewal/repurchase (customer), extended use (customer), and dissemination (customer).

In order to generate an index Hierarchy according to evaluation index information in an application scenario of satisfaction evaluation of a technical solution provider and a Hierarchy index of an ACSI model, a Hierarchy analysis method (AHP) may be used. The AHP method can solve the problem of multi-level and multi-criterion, and a hierarchical structure is formed according to the membership degree relation of various factors.

Fig. 4 is a schematic structural diagram of an index hierarchy in an application scenario of evaluation information processing of a technical solution provider, as shown in fig. 4, the index hierarchy includes 3 levels, and the highest level only includes one level index, i.e. customer satisfaction; the middle layer comprises 5 secondary indexes, namely customer expectation, perceived quality, perceived value, customer complaints and customer loyalty; the bottom layer includes evaluation index information under the secondary indexes of the respective intermediate layers.

In the exemplary embodiment, the index hierarchy is generated according to the evaluation index information and the hierarchy index information, so that a data basis can be provided for the subsequent determination of the user satisfaction degree, and the method is suitable for the qualitative or qualitative and quantitative decision analysis condition.

After the index hierarchy is determined, an index weight of the evaluation index information may be determined according to the index hierarchy.

Fig. 5 shows a flow chart of a method of determining an index weight, as shown in fig. 5, the method at least comprising the steps of: in step S510, relative index comparison is performed on the evaluation index information and the hierarchical structure index information in the index hierarchical structure to determine a relative weight, and weight sorting processing is performed on the relative weight to construct a judgment matrix.

In order to determine the index weight of the evaluation index information according to the index hierarchical structure, the index hierarchical structure can be converted into a second-level index and a third-level index of corresponding dimensionality.

Fig. 6 is a schematic structural diagram of an index system obtained by converting an index hierarchy, as shown in fig. 6, the index system is obtained by converting evaluation index information and a hierarchy index according to the index hierarchy. Wherein the index system relates to 6 dimensions, brand, commerce, payment, website products, services and public praise. And under the 6 dimensions, the 6 variables of the AC SI model are also divided into secondary indexes under different dimensions, and the evaluation index information is a tertiary index under the secondary indexes.

Under the index system, a judgment matrix for pairwise comparison of the secondary index and the tertiary index is constructed according to a 1-9 scale method given by American famous operational research scientist Sundi. Specifically, after pairwise comparison of each index, the relative quality sequence of each evaluation index information and each hierarchical structure index is scheduled according to the 9-quantile ratio, and a judgment matrix A of the evaluation index information and the hierarchical structure index is constructed in sequence. Specifically, the determination matrix a is represented by formula (1):

wherein the importance of the ith element and the jth element relative to a certain element in the previous layer is compared, and a quantized relative weight a is used _ij A description is given. Thus, the elements in matrix a have the following relationships:

determine a in the matrix _ij The values of (c) can be referred to the proposal of Satty, i.e., the values are assigned on a scale. a is _ij Between 1-9 and its inverse.

Wherein when a _ij When the value is 1, the element i and the element j have the same importance for the element of the previous layer; when a is _ij Element i is slightly more important than element j when 3; when a is _ij When 5, element i is more important than element j; when a is _ij Element i is much more important than element j when 7; when a is _ij When 9, element i is extremely important than element j; a is a _ij 2n, 1,2,3,4, the importance of element i and element k being between a and k _ij ＝2n-1，a _ij 2n + 1.

According to the index hierarchy or the corresponding index system, 6 judgment matrixes A can be constructed.

In step S520, the judgment matrix is subjected to assignment calculation to obtain a weight calculation result, and the weight calculation result is subjected to normalization processing to obtain an index weight corresponding to the evaluation index information.

In an alternative embodiment, fig. 7 shows a flowchart of the steps of a method for calculating the weight calculation result, as shown in fig. 7, the method at least includes the following steps: in step S710, a check coefficient corresponding to the evaluation index information and the hierarchical structure index information is obtained, and the determination matrix is checked and calculated to obtain a consistency index.

In order to check the consistency between the importance of each piece of evaluation index information and the importance of each piece of hierarchical structure index information, and avoid the occurrence of a contradiction condition that a is more important than b and b is more important than c, but c is more important than a, the consistency check can be performed on the evaluation index information and the hierarchical structure index information.

Therefore, the verification coefficient RI in the application scenario of evaluation information processing to the technical solution provider can be acquired. Specifically, the checking coefficient RI is shown in table 1:

table 1 and the consistency index can also be checked and calculated according to equation (3):

wherein n is the dimension of the judgment matrix A, lambda _max Is the maximum characteristic root of the judgment matrix A.

In step S720, consistency calculation is performed on the check coefficient and the consistency index to obtain a check result, and a result threshold corresponding to the check result is obtained.

After the verification coefficient and the consistency index are determined, consistency calculation may be performed on the verification coefficient and the consistency index according to equation (4):

the check result is used for consistency check of the evaluation index information and the hierarchical structure index information, and therefore, the check result is a random consistency ratio CR.

Further, a result threshold value in an application scenario of evaluation information processing by a technical solution provider may also be acquired. Generally, the result threshold is 0.1, and the size of the result threshold may also be set according to other application scenarios, which is not particularly limited in this exemplary embodiment.

In step S730, if the test result is smaller than the result threshold, the feature root of the determination matrix is calculated to obtain a weight calculation result.

After the verification result and the result threshold are obtained, the verification result and the result threshold may be compared. When the comparison result is that the inspection result is smaller than the result threshold value, the consistency of the judgment matrix A is determined to pass the inspection, and the judgment matrix can be further calculated to determine a weight calculation result; otherwise, the judgment matrix A does not meet the consistency, and the judgment matrix A can be reset.

There are three ways of calculating the weight calculation result for the decision matrix passed by the consistency check, which are the sum method, the root method (geometric mean method), and the feature root method, respectively. For example, when the calculation method is a feature root method, the feature root calculation may be performed according to formula (5):

AW＝λ _max W (5)

wherein λ is _max And W is the eigenvector corresponding to the maximum characteristic root for judging the maximum characteristic root of the matrix A.

In the present exemplary embodiment, by performing consistency check on the evaluation index information and the hierarchical structure index information, it is possible to determine the setting reasonability of the determination matrix, and to ensure the reasonability and accuracy of the user evaluation information processing from the viewpoint of the determination matrix.

Since the weight calculation result may have a negative value, the weight calculation result may be further normalized to use the normalized result as the index weight of the evaluation index information.

Specifically, fig. 8 is a schematic diagram showing the index weight configuration in an application scenario of evaluation information processing by a technical solution provider, and as shown in fig. 8, not only the index weight of the evaluation index information but also the index weight of the hierarchical index information may be determined. Therefore, when a multi-level index hierarchy is constructed, the index weight determined from the index hierarchy may include both the index weight of the evaluation index information and the index weight of the hierarchy index information.

In the exemplary embodiment, the index weight corresponding to the evaluation index information can be determined according to the constructed judgment matrix, the calculation logic is meticulous and accurate, and the evaluation effect and the accuracy of the subsequent user evaluation information processing are ensured.

In step S130, a matrix construction process is performed on the evaluation index information to obtain an evaluation matrix, and a fuzzy transformation process is performed on the index weight and the evaluation matrix to obtain an index evaluation result of the evaluation index information.

In an exemplary embodiment of the disclosure, the user generally applies fuzzy language which is difficult to quantify, such as very satisfied, general, unsatisfied, and very unsatisfied, to evaluate each item of evaluation index information, and it is difficult to draw a scientific and quantitative conclusion, which affects evaluation work in an application scenario. The fuzzy evaluation method can convert qualitative evaluation into quantitative evaluation to obtain a relatively accurate comprehensive evaluation result.

In an alternative embodiment, fig. 9 shows a flow diagram of a method of generating an evaluation matrix, as shown in fig. 9, the method at least comprising the steps of: in step S910, the evaluation factor information corresponding to the evaluation index information is determined, and the evaluation times of the evaluation index information and the evaluation factor information are counted to obtain the evaluation times of the evaluation index information appearing in the evaluation factor information.

When the evaluation of each item of evaluation index information by the user is obtained, the pairs can be sequentially obtainedImage set O ═ O ₁ ,o ₂ ,…,o _l The factor set U is/U ₁ ,u ₂ ,…,u _m And comment set V ═ V ₁ ,v ₂ ,…,v _n }。

The object set is the content of a questionnaire for obtaining user evaluation, the factor set is evaluation index information, and the comment set is user evaluation and is generally very satisfied, general, unsatisfied and very unsatisfied. Thus, the content of both the factor set and the comment set is from the object set.

And the content in the comment set is the evaluation factor information corresponding to the evaluation index information. Further, in order to generate the evaluation matrix, the evaluation index information and the evaluation factor information in the content of the questionnaire can be subjected to evaluation frequency statistics to obtain the evaluation frequency of the evaluation index information appearing in each evaluation factor information.

The number of evaluations was f _ij ，f _ij For the ith evaluation index information to be evaluated as the jth evaluation factor v _j The number of evaluations of (2). For example, f ₅₁ The number of times i-5 was evaluated as being very satisfactory j-1 for stability.

In step S920, a number calculation result is obtained by performing fuzzy statistical calculation on the evaluation number, and a single-factor fuzzy evaluation process is performed on the number calculation result to generate an evaluation matrix.

After the evaluation times of the evaluation index information appearing in the evaluation factors are obtained, fuzzy statistical calculation can be performed on the rating times to obtain a time calculation result.

Specifically, the calculation can be performed according to formula (6):

further, an evaluation matrix R may be generated according to the number settlement result, specifically:

and obtaining an evaluation matrix R of fuzzy comprehensive evaluation through each single element fuzzy evaluation, wherein the ith row in the R reflects the membership degree of the ith evaluation index information of the evaluated object to each evaluation factor information in the evaluation set, and the jth column reflects the degree of each evaluation index information of the evaluated object to the jth evaluation factor information in each evaluation factor in the evaluation set. Wherein r is _ij It can be determined by fuzzy statistical methods, i.e. equation (6).

In the exemplary embodiment, an evaluation matrix can be generated by calculating the evaluation times of the evaluation index information appearing in the evaluation factor information, the qualitative evaluation is converted into the quantitative evaluation, and a data basis is provided for determining the user satisfaction according to the quantitative evaluation.

Further, an index evaluation result of the evaluation index information may be determined according to the index weight and the evaluation matrix.

Specifically, the weight vector of the factor set evaluation index information is the weight calculation result W, and W/W is obtained ₁ ,w ₂ ,…,w _m Satisfy 0 ≦ w _i ≤1,

Further, fuzzy conversion is carried out on each evaluation index information according to a formula (8) to obtain an index evaluation result of the three-level evaluation index information:

wherein the content of the first and second substances,

representing a generalized fuzzy synthesis algorithm, B _s (s is 1, …, m) is the fuzzy comprehensive evaluation of the s-th element of the evaluation object, and the maximum b is the maximum b by utilizing the principle of the maximum membership degree _sj Corresponding evaluation factor v _j Is the best evaluation result, and W _m Namely W.

According to reality in application sceneAccording to the actual requirement, a specific solution b can be selected _sj (j ═ 1,2, …, n). The common fuzzy operators comprise an M (· V) model, an M (·, +) model and an M (· V) model. In order to take account of the influence of various evaluation index information, a weighted average type M (, +) model can be selected for calculation, that is, the model is

Other models may be selected for calculation according to actual requirements, which is not particularly limited in this exemplary embodiment.

In step S140, a Spark cluster is used to perform index aggregation calculation on the index evaluation result and the index weight to obtain a target evaluation result, and a Spark cluster is used to perform score conversion calculation on the target evaluation result to obtain a target evaluation score, so as to send the target evaluation score to the service provider.

In one exemplary embodiment of the present disclosure, after the index evaluation result and the index weight are obtained, a target evaluation result may be determined according to the index evaluation result and the index weight.

In an alternative embodiment, fig. 10 shows a flow chart of a method for determining a target evaluation result, as shown in fig. 10, the method at least comprises the following steps: in step S1010, an aggregation process is performed on the index evaluation result to obtain an aggregation matrix.

In order to comprehensively evaluate the secondary indexes, the evaluation results of each index of the tertiary indexes can be aggregated to obtain an aggregation matrix. I.e. from B ₁ ,B ₂ ,…,B _m Obtaining U ═ U ₁ ,u ₂ ,..,u _m The aggregation matrix of (9) is shown in formula (9):

in step S1020, fuzzy synthesis calculation is performed on the aggregation matrix and the index weight using the Spark cluster to determine a target evaluation result.

If u ₁ ,u ₂ ,..,u _m Has a weight vector of W _U ＝[a ₁ … a _m ]Then, the target evaluation result of what is represented by U, i.e., Customer satisfaction (CSI for short), is:

wherein the weight vector W _U The weight in (3) is the weight index corresponding to the hierarchical structure index of the secondary index in the weight indexes.

Also, the fuzzy synthesis calculation process may be implemented in a Spark cluster.

The Spark cluster is built based on Spark, and can perform index aggregation calculation on the target evaluation result and the index weight by utilizing the capability of the Spark cluster for performing rapid calculation on mass data to obtain the target evaluation result. And when the Spark cluster is used for calculation, a target evaluation result can be obtained by adopting the calculation of a machine learning algorithm, and a corresponding model is reserved.

In the exemplary embodiment, aggregation processing and fuzzy synthesis calculation are performed on each index evaluation result, a target evaluation result corresponding to a secondary index can be determined, the secondary evaluation result can be determined through synthesis processing from the lowest layer to the middle layer, the determination mode is simple and accurate, and the method is suitable for any multi-level rating result synthesis scene.

Further, a comprehensive target evaluation score can be obtained according to the target evaluation result.

In an alternative embodiment, fig. 11 shows a flow chart of a method for obtaining a target rating score, as shown in fig. 11, the method at least comprises the following steps: in step S1110, a factor score corresponding to the evaluation factor information is acquired.

For the application scenarios where the evaluation factor information includes very satisfactory, general, unsatisfactory, and very unsatisfactory, the factor scores corresponding to the evaluation factor information may be set to 100,80,60,40, and 20, respectively, that is, V ═ very satisfactory, general, unsatisfactory, and very unsatisfactory } -/100, 80,60,40, and 20. In addition, other factor scores may be set according to actual situations, and this exemplary embodiment is not particularly limited in this respect.

In step S1120, score conversion is performed on the target evaluation result and the factor score by using the Spark cluster to obtain a target evaluation score.

Further, to determine the target evaluation score, score conversion calculation may be performed according to equation (11):

CSI＝B _u ×V (11)

wherein, the CSI is the target evaluation score.

In the exemplary embodiment, the target evaluation score of the user on the evaluation object can be determined by calculating the factor score and the target evaluation result, so that the conversion from the qualitative evaluation to the quantitative evaluation is realized, the whole evaluation score is more objective and fair, and a basis for long-term monitoring and comparison is provided.

In addition, corresponding scores of the hierarchical structure indexes under the application scene of evaluating information processing of a technical solution provider can be sequenced, and the satisfaction degrees of the 5 hierarchical structure indexes are determined, so that information display under the specific demand scene is clearer.

Obviously, the multi-level fuzzy comprehensive evaluation is to perform synthesis operation repeatedly in sequence, and guide and determine a final target evaluation score from the lowest level to the highest level.

In step S150, the service provider receives the target evaluation score and displays the target evaluation score.

In an exemplary embodiment of the present disclosure, the service provider receives a target evaluation score calculated by the service consumer according to the score calculation request, and may display the target evaluation score on the service provider for viewing by the technical solution provider.

The evaluation information processing method in the embodiment of the present disclosure is described in detail below with reference to an application scenario.

Fig. 12 is a flowchart illustrating an evaluation information processing method in an application scenario, and as shown in fig. 12, in step S1210, an evaluation index hierarchical relationship is established using an ACSI model. That is, the index hierarchy of the evaluation index information is established.

In step S1220, the correspondence between the three-level index and the questionnaire question is confirmed.

In step S1230, the importance comparison result of each evaluation factor affecting the satisfaction with respect to each index is confirmed and retrieved, and a comparison matrix is formed. I.e. the decision matrix.

In step S1240, the index weight is calculated by applying the contrast matrix and using the feature root method.

In step S1250, the evaluation object set, the comment set, and the factor set in the questionnaire are determined.

In step S1260, the evaluation score of each index is calculated by the fuzzy comprehensive evaluation matrix. That is, the evaluation score of each evaluation index information is calculated by the evaluation matrix.

In step S1270, the overall satisfaction evaluation score is calculated by combining the evaluation weights of the respective indices.

That is, the overall evaluation information processing score is calculated by combining the evaluation index information and the index weight of the hierarchical structure index.

In the application scenario of the present disclosure, on one hand, an index hierarchical structure of evaluation index information is generated, a multi-level structure is provided for an index analysis mode, and evaluation index information of each link influencing evaluation information processing is comprehensively covered; and on the other hand, the index weight of the evaluation index information is determined, so that the evaluation measure of the satisfaction degree keeps consistency under the action of multiple factors, the acceptance of each link is obtained, further, the target evaluation result is calculated to determine the target evaluation score, the fuzzy quantitative calculation of the evaluation result is realized, a user can accurately and quickly obtain the macroscopic and quantitative satisfaction degree score, the whole evaluation process is more objective and fair, and the basis of long-term monitoring and comparison is provided.

Further, in an exemplary embodiment of the present disclosure, an evaluation information processing apparatus is also provided. Fig. 13 shows a schematic configuration diagram of an evaluation information processing apparatus, and as shown in fig. 13, an evaluation information processing apparatus 1300 may include: a request sending module 1310, a score calculating module 1320, and a score displaying module 1330. Wherein:

a hierarchy module 1310 configured to send a score calculation request to a service consumer through a service provider, the score calculation request being generated by a trigger operation acting on the service provider;

the index evaluation module 1320 is configured to receive a score calculation request through the service using end, acquire evaluation index information and an index hierarchical structure generated by the evaluation index information from the Hadoop cluster, and perform weight generation processing on the evaluation index information according to the index hierarchical structure to obtain an index weight;

performing index aggregation calculation on the index evaluation result and the index weight by using a Spark cluster to obtain a target evaluation result, performing score conversion calculation on the target evaluation result by using the Spark cluster to obtain a target evaluation score, and sending the target evaluation score to a service provider;

a rating score module 1330 configured to receive, by the service provider, the target rating score and display the target rating score.

The details of the evaluation information processing apparatus 1300 are described in detail in the corresponding evaluation information processing method, and therefore are not described herein again.

It should be noted that although several modules or units of the evaluation information processing apparatus 1300 are mentioned in the above detailed description, such division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

An electronic device 1400 according to such an embodiment of the invention is described below with reference to fig. 14. The electronic device 1400 shown in fig. 14 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 14, the electronic device 1400 is embodied in the form of a general purpose computing device. The components of the electronic device 1400 may include, but are not limited to: the at least one processing unit 1410, the at least one memory unit 1420, the bus 1430 that connects the various system components (including the memory unit 1420 and the processing unit 1410), and the display unit 1440.

Wherein the storage unit stores program code that is executable by the processing unit 1410, such that the processing unit 1410 performs steps according to various exemplary embodiments of the present invention described in the above section "exemplary methods" of the present specification.

The storage unit 1420 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)1421 and/or a cache memory unit 1422, and may further include a read only memory unit (ROM) 1423.

Storage unit 1420 may also include a program/utility 1424 having a set (at least one) of program modules 1425, such program modules 1425 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1430 may be any type of bus structure including a memory cell bus or memory cell controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1400 can also communicate with one or more external devices 1600 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1400, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1400 to communicate with one or more other computing devices. Such communication can occur via an input/output (I/O) interface 1450. Also, the electronic device 1400 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 1460. As shown, the network adapter 1460 communicates with the other modules of the electronic device 1400 via the bus 1430. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, to name a few.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above-mentioned "exemplary methods" section of the present description, when said program product is run on the terminal device.

Referring to fig. 15, a program product 1500 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. An evaluation information processing method, characterized by comprising:

2. The method according to claim 1, wherein the obtaining evaluation index information from a Hadoop cluster and an index hierarchy generated from the evaluation index information comprises:

3. The method according to claim 2, wherein the performing a weight generation process on the evaluation index information according to the index hierarchical structure to obtain an index weight includes:

4. The method according to claim 3, wherein the performing the assignment calculation on the determination matrix to obtain a weight calculation result includes:

5. The method according to claim 1, wherein the matrix construction processing of the evaluation index information to obtain an evaluation matrix includes:

determining evaluation factor information corresponding to the evaluation index information, and counting the evaluation times of the evaluation index information and the evaluation factor information to obtain the evaluation times of the evaluation index information appearing in the evaluation factor information;

6. The method according to claim 5, wherein performing score conversion calculation on the target evaluation result using the Spark cluster to obtain a target evaluation score includes:

acquiring a factor value corresponding to the evaluation factor information;

7. The method according to claim 1, wherein performing index aggregation calculation on the index evaluation result and the index weight determination by using a Spark cluster to obtain a target evaluation result includes:

8. An evaluation information processing apparatus, comprising:

and the score display module is configured to receive the target evaluation score through the service provider and display the target evaluation score.

9. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the evaluation information processing method according to any one of claims 1 to 7.

10. An electronic device, comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to execute the evaluation information processing method of any one of claims 1 to 7 via execution of the executable instructions.