CN113450010A

CN113450010A - Method and device for determining evaluation result of data object and server

Info

Publication number: CN113450010A
Application number: CN202110767930.XA
Authority: CN
Inventors: 施红梅; 王茹楠; 瞿伟
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-07-07
Filing date: 2021-07-07
Publication date: 2021-09-28

Abstract

The specification provides a method, a device and a server for determining an evaluation result of a data object. Based on the method, when the target data object needs to be objectively evaluated, a target comment set containing evaluation parameters of a plurality of comment objects aiming at a plurality of characteristics of the target data object can be obtained; then according to a preset construction rule, a target comment set is utilized to construct and obtain a plurality of feature matrixes for the target data object; each feature matrix corresponds to one evaluation dimension; each characteristic matrix comprises an evaluation statistical vector of the characteristics under the corresponding evaluation dimension; and determining the evaluation result of the target data object by utilizing the plurality of characteristic matrices according to a preset processing rule and combining a plurality of preset characteristic weight matrices and a preset evaluation dimension weight matrix which are determined in advance according to a fuzzy comprehensive evaluation method. Therefore, the target data object can be intelligently evaluated automatically and objectively, and a relatively high-reference-value and relatively reliable evaluation result is obtained.

Description

Method and device for determining evaluation result of data object and server

Technical Field

The specification belongs to the technical field of artificial intelligence, and particularly relates to a method, a device and a server for determining an evaluation result of a data object.

Background

In various scenes related to work and life, users often need to obtain more accurate and objective evaluation results for certain object objects. For example, when a user selects to purchase a certain commodity on a website, the overall evaluation of the commodity is determined by integrating comments of different consumers on the website for the commodity; and determining whether to purchase the commodity according to the overall evaluation. For another example, when a user determines the quarterly bonus of an employee, the evaluation of the employee by a plurality of different responsible persons in the company is integrated to determine the contribution evaluation result of the employee; and determining the specific quarter bonus of the employee according to the contribution evaluation result.

However, when a user specifically evaluates a certain object, the user often faces a plurality of different evaluations of the object by a plurality of different reviewers at the same time. In this case, it is often difficult for the user to obtain a relatively objective evaluation result with a relatively high reference value.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The specification provides a method, a device and a server for determining an evaluation result of a data object, so that the target data object can be evaluated automatically and objectively intelligently, and a relatively reliable evaluation result with a relatively high reference value can be obtained.

An embodiment of the present specification provides a method for determining an evaluation result of a data object, including:

acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions;

according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions;

determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

In some embodiments, the target comment set includes a plurality of comment sentences provided by a plurality of comment objects respectively for target data objects.

In some embodiments, constructing a plurality of feature matrices for a target data object according to a preset construction rule by using the target comment set includes:

extracting evaluation parameters aiming at a plurality of characteristics of the target data object according to the plurality of evaluation sentences;

counting the evaluation parameters of the plurality of characteristics to obtain evaluation statistical results of the plurality of characteristics;

and according to a preset construction rule, constructing a plurality of feature matrixes aiming at the target data object by utilizing the evaluation statistical results of the plurality of features.

In some embodiments, constructing a plurality of feature matrices for the target data object using the evaluation statistics of the plurality of features according to a preset construction rule includes:

constructing a current feature matrix of the plurality of feature matrices in the following manner:

screening out the evaluation statistical results of the current characteristics belonging to the current evaluation dimension from the evaluation statistical results of the characteristics; wherein the current feature matrix corresponds to a current evaluation dimension;

determining statistical values of different types of evaluation parameters aiming at the current characteristics according to the evaluation statistical results of the current characteristics;

determining an evaluation statistical vector of the current feature according to the statistical values of different types of evaluation parameters aiming at the current feature;

and combining the evaluation statistical vectors of the current features to construct and obtain the current feature matrix.

In some embodiments, determining an evaluation result of the target data object according to a preset processing rule by using a plurality of feature matrices, a plurality of preset feature weight matrices, and a preset evaluation dimension weight matrix includes:

performing preset function operation according to the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix to obtain corresponding operation results;

and carrying out normalization processing on the operation result to obtain an evaluation result of the target data object.

In some embodiments, performing a predetermined function operation according to the plurality of feature matrices, the plurality of predetermined feature weight matrices, and the predetermined evaluation dimension weight matrix includes:

and (3) performing preset function operation according to the formula:

wherein D is the result of the operation, A_iIs a preset feature weight matrix, R, corresponding to the evaluation dimension numbered i_iThe characteristic matrix corresponding to the evaluation dimension with the number i is shown, A is a preset evaluation dimension weight matrix, and n is the number of the evaluation dimension.

In some embodiments, the method further comprises:

acquiring a historical evaluation record;

according to the historical evaluation records, constructing and obtaining a first-level judgment comparison matrix aiming at a plurality of evaluation dimensions and a plurality of second-level judgment comparison matrices aiming at a plurality of characteristics under each evaluation dimension through hierarchical analysis;

determining a preset evaluation dimension weight matrix meeting the requirements according to the first-stage judgment comparison matrix; and determining a plurality of preset characteristic weight matrixes which meet the requirements according to the plurality of second-stage judgment comparison matrixes.

In some embodiments, the target data object comprises at least one of: commodity objects, employee objects, user objects, enterprise objects.

In some embodiments, where the target data object comprises an employee object, the evaluation dimension comprises: basic information dimensions, job level dimensions, job performance dimensions.

An embodiment of the present specification further provides an apparatus for determining an evaluation result of a data object, including:

the acquisition module is used for acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions;

the construction module is used for constructing and obtaining a plurality of feature matrixes for the target data object by utilizing the target comment set according to a preset construction rule; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions;

the determining module is used for determining an evaluation result of the target data object by utilizing the plurality of feature matrixes, the plurality of preset feature weight matrixes and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

Embodiments of the present specification also provide a server, including a processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the following: acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions; according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions; determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

Embodiments of the present specification also provide a computer-readable storage medium having stored thereon computer instructions, which when executed by a computer device, implement: acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions; according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions; determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

The specification provides a method, a device and a server for determining an evaluation result of a data object. Based on the method, when objective evaluation of the target data object is needed, a target comment set containing evaluation parameters of a plurality of comment objects aiming at a plurality of characteristics of the target data object can be obtained; then according to a preset construction rule, a target comment set is utilized to construct and obtain a plurality of feature matrixes for the target data object; each feature matrix corresponds to one evaluation dimension; each feature matrix comprises evaluation statistical vectors of a plurality of features under the corresponding evaluation dimension; and determining the evaluation result of the target data object based on the statistical level by using the plurality of feature matrices and combining a plurality of preset feature weight matrices and a preset evaluation dimension weight matrix which are determined in advance according to a fuzzy comprehensive evaluation method according to a preset processing rule. Therefore, the target data object can be intelligently evaluated automatically and objectively, and a relatively reliable evaluation result with relatively high reference value is obtained.

Drawings

In order to more clearly illustrate the embodiments of the present specification, the drawings needed to be used in the embodiments will be briefly described below, and the drawings in the following description are only some of the embodiments described in the specification, and it is obvious to those skilled in the art that other drawings can be obtained based on the drawings without any inventive work.

Fig. 1 is a flowchart illustrating a method for determining an evaluation result of a data object according to an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a server according to an embodiment of the present disclosure;

fig. 3 is a schematic structural composition diagram of an evaluation result determination device for a data object provided in an embodiment of the present specification;

fig. 4 is a schematic diagram of an embodiment of a determination method for an evaluation result of a data object, which is provided by the embodiments of the present specification, in a scenario example.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Referring to fig. 1, an embodiment of the present disclosure provides a method for determining an evaluation result of a data object. The method is particularly applied to the server side. In specific implementation, the method may include the following:

s101: acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions;

s102: according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions;

s103: determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

By the embodiment, a plurality of feature matrices corresponding to various evaluation dimensions for the target data object can be constructed and obtained according to the target comment set of the target data object; and then, according to the plurality of feature matrices, a plurality of preset feature weight matrices and a preset evaluation dimension weight matrix which are determined according to a fuzzy comprehensive evaluation method in advance are combined to accurately and objectively evaluate the target data object, so that a relatively reliable evaluation result with a relatively high reference value is obtained.

In some embodiments, the method for determining the evaluation result of the data object may be specifically applied to a server side of a business data processing system. In this embodiment, the server may specifically include a background server that is applied to a data processing system side and is capable of implementing functions such as data transmission and data processing. Specifically, the server may be, for example, an electronic device having data operation, storage function and network interaction function. Alternatively, the server may be a software program running in the electronic device and providing support for data processing, storage and network interaction. In the present embodiment, the number of servers is not particularly limited. The server may specifically be one server, or may also be several servers, or a server cluster formed by several servers.

In some embodiments, the target data object may be specifically understood as a data object to be evaluated. The target data objects may specifically be different types of data objects corresponding to different application scenarios.

Specifically, the target data object includes at least one of: commodity objects, employee objects, user objects, business objects, and the like.

Of course, it should be noted that the above listed target data objects are only an exemplary illustration. In an implementation, the target data object may also include other types of data objects in other application scenarios according to specific application scenarios and processing requirements. The present specification is not limited to these.

Through the embodiment, the determination method for the evaluation result of the data object provided by the implementation of the description can be popularized and applied to various different application scenes so as to evaluate various target data objects of different types more accurately and objectively.

In some embodiments, the target comment set of the target data object may specifically include evaluation parameters given by a plurality of comment objects for a plurality of features of the target data object, respectively. Wherein each feature belongs to an evaluation dimension.

Specifically, taking an evaluation scenario of the contribution degree of the employee object as an example, the target data object may be an employee object to be evaluated for the contribution degree. Correspondingly, the evaluation dimension may specifically include: basic information dimensions, job level dimensions, job performance dimensions.

Further, one or more next-level specific features may also be included for each evaluation dimension. For example, in an evaluation scenario of contribution of employee objects, the features belonging to the basic information dimension may specifically include: work age information, academic calendar information, and the like; the features belonging to the job rating dimension may specifically include: job level, skill level, etc.; the features belonging to the job performance dimension may specifically include: prize winning records, assessment records, and the like.

Through the embodiment, different comment objects can comprehensively evaluate the target data object aiming at specific characteristics under different evaluation dimensions based on different evaluation dimensions, and accordingly a richer target comment set can be obtained.

In some embodiments, the comment objects may be different types of data objects corresponding to different application scenarios. For example, in an evaluation scenario of contribution of an employee object, the comment object may be specifically a superior leader of the employee object. For another example, in an evaluation scene of an actor performance, the comment object may be a comment authority responsible for scoring the performance. For another example, in an evaluation scenario of a commodity, the comment object may specifically be a consumer who has purchased the commodity before and left the commodity on a website, and the like.

Of course, it should be noted that the above listed comment objects are only a schematic illustration. In specific implementation, the comment object may further include other types of data objects in other application scenarios according to specific application scenarios and processing requirements. The present specification is not limited to these.

In some embodiments, the evaluation parameters of the reviewer for the features of the target data object may specifically include: the reviewer evaluates parameters numerically and/or textually for a particular feature of the target data object.

For example, the evaluation parameters for the feature assessment records in the job performance dimension may be: 100 (a numerical evaluation parameter used in a quantitative manner to characterize monthly job scores) may also be: very good (a textual evaluation parameter used in a qualitative way to characterize monthly performance).

In some embodiments, the target comment set may specifically include a plurality of comment sentences provided by a plurality of comment objects respectively for the target data object.

Wherein each evaluation statement is provided by a corresponding one of the comment objects. Each evaluation statement may specifically include an evaluation parameter given by the corresponding comment object for each feature of the target data object.

Through the embodiment, the evaluation sentences containing the evaluation parameters given by the comment object for the characteristics of the target data object can be obtained and utilized to construct the target comment set which meets the requirements for the target data object.

In some embodiments, the evaluation statement may include a numerical evaluation statement. Specifically, the evaluation parameter for each feature of the target data object included in the evaluation sentence may be a numerical evaluation parameter.

For example, the numerical evaluation statement of the comment object 1 for the target data object may be expressed as: [ assessment record: 100, respectively; and (4) job level: 6, skill level: 7]. The numerical evaluation statement of the comment object 2 for the same target data object can be expressed as: [ assessment record: 95; and (4) job level: 6, skill level: 8], and the like.

In some embodiments, the above-described evaluation sentences may also include text-type evaluation sentences. Specifically, the evaluation parameter for each feature of the target data object included in the evaluation sentence may be a text-type evaluation parameter.

For example, in the target comment set, the evaluation sentence of the target data object by the comment object 3 may be "XXX book monthly job assessment is excellent, job title is high worker, skill level is eight", or the like.

By the embodiment, the text type evaluation sentences and/or the numerical type evaluation sentences can be obtained to construct the target comment set aiming at the target data object, so that a richer and more comprehensive target comment set can be obtained.

In some embodiments, the above-mentioned constructing a plurality of feature matrices for a target data object by using the target comment set according to a preset construction rule may include the following contents in specific implementation:

s1: extracting evaluation parameters aiming at a plurality of characteristics of the target data object according to the plurality of evaluation sentences;

s2: counting the evaluation parameters of the plurality of characteristics to obtain evaluation statistical results of the plurality of characteristics;

s3: and according to a preset construction rule, constructing a plurality of feature matrixes aiming at the target data object by utilizing the evaluation statistical results of the plurality of features.

By the embodiment, a plurality of feature matrices which are based on statistics, have good effects and are suitable for subsequent operation processing can be constructed by fully utilizing the evaluation parameters contained in the target comment set according to the preset construction rule.

In some embodiments, in implementation, multiple evaluation sentences may be obtained from a target set of comments; then, for each evaluation sentence, an evaluation parameter for a plurality of features of the target data object is extracted.

Specifically, when extracting evaluation parameters for a plurality of features of a target data object for a single evaluation statement, for a numerical evaluation statement, in a specific processing, a feature field (e.g., a field "assessment record") may be retrieved and located in the evaluation statement; based on the feature field, the numerical data (e.g., the number "100") of the feature field is extracted as an evaluation parameter for the feature (e.g., the assessment record) of the target data object.

For a text type evaluation statement, a pre-trained semantic recognition model can be called to process the evaluation statement to obtain a corresponding semantic recognition result; and extracting evaluation parameters aiming at each characteristic of the target data object according to the semantic recognition result.

With the above-described embodiment, the evaluation parameters of the plurality of comment objects for each of the plurality of features of the target data object can be extracted from the plurality of evaluation sentences.

In some embodiments, when the evaluation parameters of the plurality of features are specifically counted, taking the evaluation parameter of any current feature in the unified plurality of features as an example, different types of the evaluation parameters of the current feature may be determined in advance according to the extracted evaluation parameter of the current feature. For example, for the assessment recording features, there are 6 different types, respectively: 100. 95, 90, 85, 80, 75.

Further, the ratio of the number of the evaluation parameters of different types of the current features to the total number is counted as a statistical value of the evaluation parameters of different types. For example, for the assessment record feature 100, the number of evaluation parameters is 30 (it can be understood that the number of review objects giving an evaluation parameter of 100 to the feature is 30), the total number is 100 (it can be understood that the total number of review objects giving an evaluation parameter to the feature is 100), and then the statistical value of the evaluation parameter of the type of 100 is determined to be 30/100 ═ 0.3. Similarly, it can be determined that: the statistical values for evaluation parameters of the type 95 are: 0.1; the statistical values for evaluation parameters of the type 90 are: 0.1; 85 the statistical values of this type of evaluation parameters are: 0.2; 80 the statistical values of this type of evaluation parameters are: 0.1; the statistical values of evaluation parameters of the type 75 are: 0.2.

in a similar manner, statistical values of different types of evaluation parameters in each feature may be calculated to obtain an evaluation statistical result of each feature in the plurality of features.

In addition, the evaluation dimensionality to which each feature belongs can be determined according to a preset membership rule. And then constructing a feature matrix corresponding to the evaluation dimension according to the evaluation statistical result of the features under each evaluation dimension.

In some embodiments, the constructing, according to a preset construction rule, a plurality of feature matrices for a target data object by using the evaluation statistical results of the plurality of features may specifically include: constructing a current feature matrix of the plurality of feature matrices in the following manner:

s1: screening out the evaluation statistical results of the current characteristics belonging to the current evaluation dimension from the evaluation statistical results of the characteristics; wherein the current feature matrix corresponds to a current evaluation dimension;

s2: determining statistical values of different types of evaluation parameters aiming at the current characteristics according to the evaluation statistical results of the current characteristics;

s3: determining an evaluation statistical vector of the current feature according to the statistical values of different types of evaluation parameters aiming at the current feature;

s4: and combining the evaluation statistical vectors of the current features to construct and obtain the current feature matrix.

In the present embodiment, the current feature may be specifically understood as one or more features belonging to the current evaluation dimension. The current feature matrix is a matrix corresponding to the current evaluation dimension.

By the embodiment, the current feature matrix with better effect based on the statistical level can be constructed and obtained according to the evaluation statistical result of the current feature under the current evaluation dimension.

In the above manner, a plurality of feature matrices respectively corresponding to the plurality of evaluation dimensions can be constructed.

In some embodiments, in specific implementation, according to an evaluation statistical result of a current feature, statistical values of different types of evaluation parameters corresponding to the same current feature may be arranged in a preset order (for example, in a priority order of the types), so as to obtain an evaluation statistical vector corresponding to the feature; and combining the evaluation statistical vectors of the features corresponding to the same evaluation dimension to obtain a feature matrix corresponding to the evaluation dimension.

For example, for one assessment record feature in the job performance dimension, the following evaluation statistical vector can be obtained: (r)₁₁ r₁₂ r₁₃ r₁₄ r₁₅ r₁₆) (ii) a For another winning record feature in the work score dimension, the following evaluation statistics vector can be derived: (r)₂₁ r₂₂ r₂₃ r₂₄ r₂₅ r₂₆). Then, the two evaluations are countedCombining the vectors to obtain a feature matrix corresponding to the working result dimensionality as shown in the specification:

similarly, the feature matrices corresponding to other evaluation dimensions can be obtained in the above manner, and are respectively expressed as:

R₂＝[r′₁₁ r′₁₂ r′₁₃ r′₁₄ r′₁₅ r′₁₆]，

in some embodiments, the determining, according to a preset processing rule, an evaluation result of the target data object by using a plurality of feature matrices, a plurality of preset feature weight matrices, and a preset evaluation dimension weight matrix may include the following steps:

s1: performing preset function operation according to the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix to obtain corresponding operation results;

s2: and carrying out normalization processing on the operation result to obtain an evaluation result of the target data object.

Wherein, the preset feature weight matrixes respectively correspond to an evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to historical evaluation records through a fuzzy comprehensive evaluation method.

By the embodiment, the evaluation result of the target data object can be accurately and efficiently determined by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to the preset processing rule.

In some embodiments, the performing a preset function operation according to a plurality of feature matrices, a plurality of preset feature weight matrices, and a preset evaluation dimension weight matrix may include: and (3) performing preset function operation according to the formula:

With the above-described embodiment, it is possible to quickly calculate an operation result for determining an evaluation result of a target data object by performing a preset function operation, making full use of the characteristics of the matrix.

Specifically, for example, the preset evaluation dimension weight matrix is: a ═ a₁，a₂，a₃) And the three preset feature weight matrixes respectively corresponding to the three evaluation dimensions are respectively expressed as:

A₁＝(a₁₁，a₁₂)、A₂＝(a₂₁)、A₃＝(a₃₁，a₃₂)。

wherein, a₁、a₂、a₃、a₁₁、a₁₂、a₂₁、a₃₁、a₃₂Respectively, represent predetermined weight vectors.

Further, three feature matrices corresponding to the three evaluation dimensions, respectively, may be represented as: r₁、R₂、R₃。

Further, a preset function operation may be performed as follows to obtain a corresponding operation result D:

wherein the operation result may specifically include a plurality of parameter values (e.g., b)₁，b₂，b₃，b₄，b₅，b₆). Each of the plurality of parameter values corresponds to an evaluation value of one feature.

In some embodiments, the normalizing the operation result to obtain an evaluation result of the target data object may include:

the evaluation result of the target data object is calculated according to the following formula:

wherein D' represents the evaluation result of the target data object after the normalization processing.

In some embodiments, after determining the evaluation result of the target data object, when the method is implemented, the method may further include: and performing target data processing related to the target object according to the evaluation result of the target object.

Specifically, different types of target data processing can be performed according to the evaluation result of the target object corresponding to different application scenarios. For example, whether to purchase the commodity object may be determined based on the evaluation result of the commodity object. For another example, the contribution degree of the employee object may be further determined according to the evaluation result of the employee object; and then according to the contribution degree of the employee object, determining the matched bonus for issuing. For example, the user class group of the user object may be determined according to the evaluation result of the user object, and the user object may be divided into corresponding user class groups, and so on.

In some embodiments, before being embodied, the method may further include the following:

s1: acquiring a historical evaluation record;

s2: according to the historical evaluation records, constructing and obtaining a first-level judgment comparison matrix aiming at a plurality of evaluation dimensions and a plurality of second-level judgment comparison matrices aiming at a plurality of characteristics under each evaluation dimension through hierarchical analysis;

s3: determining a preset evaluation dimension weight matrix meeting the requirements according to the first-stage judgment comparison matrix; and determining a plurality of preset characteristic weight matrixes which meet the requirements according to the plurality of second-stage judgment comparison matrixes.

Through the embodiment, the acquired historical evaluation records can be effectively utilized based on a fuzzy comprehensive evaluation method, and a preset evaluation dimension weight matrix meeting the requirements and a plurality of preset feature weight matrices meeting the requirements are constructed and obtained through hierarchical analysis so as to be used in the subsequent determination of the evaluation result of the target data object.

In some embodiments, the expert experience or the existing weight setting rule may be obtained at the same time when the method is implemented. Correspondingly, a first-level judgment comparison matrix aiming at a plurality of evaluation dimensions and a plurality of second-level judgment comparison matrices respectively aiming at a plurality of characteristics under each evaluation dimension can be constructed through hierarchical analysis according to historical evaluation records and by combining with expert experience or existing weight setting rules.

In some embodiments, a preset evaluation dimension weight matrix meeting the requirements is determined according to the first-level judgment comparison matrix; after a plurality of preset feature weight matrixes meeting the requirements are determined according to the plurality of second-stage judgment comparison matrixes, consistency check can be respectively carried out on the determined preset evaluation dimension weight matrixes and the plurality of preset feature weight matrixes, and the preset evaluation dimension weight matrixes and the plurality of preset feature weight matrixes are reserved for subsequent use only when the check is determined to be passed. Under the condition that the verification is not passed, the first-stage judgment comparison matrix and/or the second-stage judgment comparison matrix can be modified in a targeted manner, and then the preset evaluation dimension weight matrix and the plurality of preset feature weight matrices are re-determined based on the modified judgment comparison matrix until the consistency verification of the determined preset evaluation dimension weight matrix and the plurality of preset feature weight matrices is passed.

Through the embodiment, the preset evaluation dimension weight matrix and the multiple preset characteristic weight matrices which have higher precision and smaller error and meet the requirements can be constructed.

As can be seen from the above, based on the method for determining the evaluation result of the data object provided in the embodiment of the present specification, when the target data object needs to be objectively evaluated, a target comment set of the target data object, which includes evaluation parameters of a plurality of characteristics of the target data object for a plurality of comment objects, may be obtained first; then according to a preset construction rule, a target comment set is utilized to construct and obtain a plurality of feature matrixes for the target data object; each feature matrix corresponds to one evaluation dimension; each characteristic matrix comprises an evaluation statistical vector of the characteristics under the corresponding evaluation dimension; and determining the evaluation result of the target data object by utilizing the plurality of characteristic matrices according to a preset processing rule and combining a plurality of preset characteristic weight matrices and a preset evaluation dimension weight matrix which are determined in advance according to a fuzzy comprehensive evaluation method. Therefore, the target data object can be intelligently evaluated automatically and objectively, and a relatively reliable evaluation result with relatively high reference value is obtained.

Embodiments of the present specification further provide a server, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented, may perform the following steps according to the instructions: acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions; according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions; determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

In order to more accurately complete the above instructions, referring to fig. 2, the present specification further provides another specific server, wherein the server includes a network communication port 201, a processor 202 and a memory 203, and the above structures are connected by an internal cable, so that the structures can perform specific data interaction.

The network communication port 201 may be specifically configured to obtain a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions.

The processor 202 may be specifically configured to construct, according to a preset construction rule, a plurality of feature matrices for a target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions; determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

The memory 203 may be specifically configured to store a corresponding instruction program.

In this embodiment, the network communication port 201 may be a virtual port that is bound to different communication protocols, so that different data can be sent or received. For example, the network communication port may be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for mail data communication. In addition, the network communication port can also be a communication interface or a communication chip of an entity. For example, it may be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it may also be a bluetooth chip.

In the present embodiment, the processor 202 may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The description is not intended to be limiting.

In this embodiment, the memory 203 may include multiple layers, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

The present specification further provides a computer-readable storage medium based on the determination method of the evaluation result of the data object, the computer-readable storage medium storing computer program instructions, which when executed implement the following: acquiring a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions; according to a preset construction rule, constructing and obtaining a plurality of feature matrixes for the target data object by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions; determining an evaluation result of the target data object by utilizing the plurality of feature matrices, the plurality of preset feature weight matrices and the preset evaluation dimension weight matrix according to a preset processing rule; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer-readable storage medium can be explained in comparison with other embodiments, and are not described herein again.

Referring to fig. 3, in a software level, an embodiment of the present specification further provides an apparatus for determining an evaluation result of a data object, where the apparatus may specifically include the following structural modules:

the obtaining module 301 may be specifically configured to obtain a target comment set of a target data object; the target comment set comprises evaluation parameters of a plurality of characteristics of a plurality of comment objects aiming at a target data object; the plurality of features respectively belong to a plurality of evaluation dimensions;

the constructing module 302 is specifically configured to construct a plurality of feature matrices for the target data object according to a preset construction rule and by using the target comment set; wherein the feature matrices respectively correspond to an evaluation dimension; the feature matrix comprises evaluation statistical vectors of features under corresponding evaluation dimensions;

the determining module 303 may be specifically configured to determine, according to a preset processing rule, an evaluation result of the target data object by using the plurality of feature matrices, the plurality of preset feature weight matrices, and the preset evaluation dimension weight matrix; the preset characteristic weight matrixes respectively correspond to one evaluation dimension; the preset characteristic weight matrix and the preset evaluation dimension weight matrix are determined in advance according to a fuzzy comprehensive evaluation method.

It should be noted that, the units, devices, modules, etc. illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. It is to be understood that, in implementing the present specification, functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules or sub-units, or the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Therefore, the device for determining the evaluation result of the data object provided by the embodiment of the specification can intelligently realize automatic and objective evaluation of the target data object and obtain a relatively reliable evaluation result with relatively high reference value.

In a specific scenario example, the determination method of the evaluation result of the data object provided by the embodiment of the present specification may be applied to implement evaluation of contribution of an employee (e.g., an employee object) based on a fuzzy comprehensive evaluation method. The enterprise manager is guided to accurately evaluate the contribution of the employees, the accuracy and the rationality of matching the contribution degree of the employees and the project scale are improved, the fine management of the employees and the utilization rate of the employees are improved, and the research, development and management efficiency is improved. A specific implementation can be seen in fig. 4, which includes the following.

Step 101: and establishing an employee contribution evaluation factor set.

In the scenario example, in the concrete implementation, an employee contribution evaluation index system can be established through data research and actual conditions of an enterprise, and evaluation factors are divided into the following two layers: first tier (corresponding to evaluation dimensions), criteria tier factor set; the second level (corresponding to the specific features in the evaluation dimension), the index level factor set. See table 1 for a review.

TABLE 1 evaluation index Table

Further, the degree of importance of the employee contribution index element may be determined. Specifically, the importance of each index to the upper-layer index may be compared pairwise with reference to the scoring rules (e.g., historical evaluation records, expert experience, etc.) in table 2, and assigned to obtain corresponding evaluation results, which may be referred to in tables 3, 4, and 5.

TABLE 2 evaluation Scale and meaning Table

TABLE 3 comparison table of relative importance of first-class indexes

TABLE 4 staff basic information index relative importance comparison table

B11/C	Working age (year) (C111)	Line age (year) (C112)
			Working age (year) (C111)	1	1/2
Line age (year) (C112)		1

TABLE 5 staff achievement index relative importance comparison table

B12/C	Assessment level (C121)	Winning prize situation (C122)
			Assessment level (C121)	1	2
Winning prize situation (C122)		1

Step 102: a set of comments contributed by the employee (e.g., a target set of comments) is established.

Specifically, the work contribution degree of employees in different positions and levels and different working years is different. Therefore, an evaluation comment set consisting of the post contribution degrees is established, the post contribution evaluation grade is scored by adopting an expert scoring method to obtain the value of the evaluation grade, and the evaluation comment set V is { V ═ V }₁,V₂,…,V_n}。

Step 103: and determining the index weight of the employee contribution degree index system (for example, constructing a plurality of preset characteristic weight matrixes and preset evaluation dimension weight matrixes).

In the present scenario example, the determination of the employee contribution evaluation index weight may specifically involve a fuzzy comprehensive evaluation method that adopts a layer analysis method. The analytic hierarchy process is a multi-level decision process combining qualitative and quantitative analysis, and its basic idea is to divide the studied things into several levels, make quantitative judgment to the relative importance of each factor of each level, and construct a 'comparison judgment matrix' based on the judgment, calculate the maximum eigenvalue of the judgment matrix and the corresponding eigenvector, and determine the relative importance weight of each index in each level on the premise of passing consistency test.

Specifically, the analytic hierarchy process may include the following steps: aiming at the indexes in each criterion, the indexes in the same layer or the same domain are compared pairwise by using the knowledge, the wisdom, the information and the value of experts, and a judgment matrix D (D) is constructed according to the judgment standard 1-9 and the meaning_ij)_m×n(including a first-level decision comparison matrix and a second-level decision comparison matrix). Then, the maximum characteristic root lambda of the comparison judgment matrix D is calculated_maxAnd is composed of_maxSolving a characteristic equation: dx ═ λ_maxx, to obtain the corresponding lambda_maxIs (x) the feature vector x ═ x₁，x₂，…，x_n)^TFinally, normalization processing is performed, and the final evaluation index weight vector can be represented as:

the decision matrix D needs to be checked for consistency before the final weight vector is determined.

Specifically, the consistency check may include the following steps:

(1) and establishing a step hierarchy.

And (4) establishing a step hierarchy according to the established worker contribution evaluation index system, and referring to table 1.

(2) And constructing a pairwise comparison judgment matrix.

For the evaluation target, which of the two elements i and j is important and how much it is relatively important is evaluated, and a certain value is assigned to how much is important. The questionnaire and the scale (for example, expert experience or existing weight setting rules) can be specifically used for setting, and the following comparison and judgment matrix is obtained:

the matrix also has the following relationship:

(3) relative weights (e.g., a preset feature weight matrix corresponding to a certain evaluation dimension) of elements (e.g., features) under a single criterion are calculated.

The problem of calculating n weight coefficients under a certain evaluation level is solved in the step.

For the judgment matrix A obtained by pairwise comparison, the matrix characteristic root problem is solved: AW ═ λ_maxW。

Multiplying elements in a comparison judgment matrix A by rows:

recalculation

And will be

Normalized to obtain

The resulting feature vector can be expressed as: w ═ W₁ W₂…W_n]^T。

Wherein, W_i(i-1, 2, …, n) represents a weight value of each element.

Then the corresponding maximum eigenvalue is calculated:

to lambda again_maxA consistency check is also required. Calculating a consistency index CI:

and then calculating the consistency ratio CR:

and carrying out consistency check according to CR. Specifically, when CR is<At 0.1, the consistency of the decision matrix is considered acceptable (e.g., check passes); otherwise (check fails), the judgment matrix needs to be corrected.

Furthermore, the importance value of each index in tables 3, 4, and 5 may be combined to finally determine the weight of the index of the staff capability evaluation index system (which is equivalent to determining a plurality of preset feature weight matrices and a preset evaluation dimension weight matrix), which may be referred to as table 6.

TABLE 6 weight table of worker contribution evaluation index system indexes

Step 104: and establishing a membership matrix for evaluating the contribution of the employees.

Determining membership r by adopting a scoring method of a judge_ij(statistics of evaluation parameters of features).

If the appraiser has n individuals (n commenting objects), for the ability of a certain employee, the membership degree r of a certain index in the index layer to a certain comment in V_ijExpressed as:

since 6 indexes in C are according to B₁₁、B₁₂、B₁₃Three criteria are divided into threeClasses, where the elements in each class are taken as a whole to construct an evaluation matrix, e.g. B₁₁"working age" and "line age" in (1) for six levels in the comment set V, a 2X 6 matrix R is obtained as defined above₁R is likewise obtained₂、R₃I.e. by

R₂＝[r′₁₁ r′₁₂ r′₁₃ r′₁₄ r′₁₅ r′₁₆]

Step 105: and establishing a fuzzy comprehensive evaluation model, and then performing comprehensive evaluation on the contribution degree of the staff (determining the evaluation result of the target data object).

The calculation of this step needs to be calculated from the bottom layer to the upper layer, so the calculation method of the next layer can be described first. That is, the first layer result is calculated from the second layer, the second layer is calculated from the third layer, if there is a fourth layer, the third layer result is also calculated from the fourth layer, and so on until the top layer.

In the present scenario example, there are only sub-levels that have weight vectors based on a single index of the fuzzy synthetic evaluation

A＝(a₁，a₂，a₃)，A₁＝(a₁₁，a₁₂)，A₂＝(a₂₁)，A₃＝(a₃₁，a₃₂)。

Wherein, A represents weight vectors of five criteria of B11, B12 and B13.

A_iSpecifically, each criterion B can be expressed_1i(i is 1,2,3) and a weight vector of each index.

Wherein "O" represents the following combined operation

Specifically, in

In, a: a, b, a × b, ab;

finally, the following can be obtained:

and D is normalized to obtain:

and obtaining a final worker contribution degree evaluation result according to the evaluation matrix D and the evaluation comment values in the evaluation comment set V: w is D.V^T。

Through the scene example, the determination method of the evaluation result of the data object provided by the embodiment of the specification is different from the traditional non-quantitative method of the fuzzy evaluation language relying on artificial subjective judgment, a set of relatively complete index system is established, the index system comprises 3 first-level indexes and 5 second-level indexes, and the employee contribution capacity evaluation system based on the fuzzy comprehensive evaluation method is established. Meanwhile, the method can be used for rapidly quantifying the adaptation degree of the project scale and the contribution capacity of the workers based on the post contribution capacity adaptation fuzzy comprehensive evaluation model of the workers and according to the project scale and the contribution capacity adaptation evaluation system of the workers, fills the gap of the theory in the field of the adaptation evaluation of the project scale and the contribution capacity of the workers, can assist managers at all levels of enterprises to objectively, accurately and reasonably distribute project tasks and human resources, improves the fine management of the personnel, improves the utilization rate of the personnel, and assists the research and development management efficiency improvement of the enterprises.

Although the present specification provides method steps as described in the examples or flowcharts, additional or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer-readable storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus necessary general hardware platform. With this understanding, the technical solutions in the present specification may be essentially embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments in the present specification.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.

Claims

1. A method for determining an evaluation result of a data object, comprising:

2. The method of claim 1, wherein the target set of comments includes a plurality of comment sentences provided by a plurality of comment objects for the target data object, respectively.

3. The method of claim 2, wherein constructing a plurality of feature matrices for a target data object using the target comment set according to a preset construction rule comprises:

4. The method according to claim 3, wherein constructing a plurality of feature matrices for the target data object using the evaluation statistics of the plurality of features according to a preset construction rule comprises:

5. The method according to claim 1, wherein determining an evaluation result of the target data object according to a preset processing rule by using a plurality of feature matrices, a plurality of preset feature weight matrices, and a preset evaluation dimension weight matrix comprises:

6. The method of claim 5, wherein performing a predetermined function operation according to the plurality of feature matrices, the plurality of predetermined feature weight matrices, and the predetermined evaluation dimension weight matrix comprises:

and (3) performing preset function operation according to the formula:

7. The method of claim 1, further comprising:

acquiring a historical evaluation record;

8. The method of claim 1, wherein the target data object comprises at least one of: commodity objects, employee objects, user objects, enterprise objects.

9. The method of claim 8, wherein where the target data object comprises an employee object, the evaluation dimension comprises: basic information dimensions, job level dimensions, job performance dimensions.

10. An apparatus for determining an evaluation result of a data object, comprising:

11. A server comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 9.

12. A computer-readable storage medium having stored thereon computer instructions which, when executed by a computer device, implement the steps of the method of any one of claims 1 to 9.