CN105005896A - Data processing method and apparatus - Google Patents

Abstract

The invention discloses a data processing method. The method comprises the following steps: receiving a data processing quest sent by a user terminal, wherein the data processing request comprises information of the user terminal and current rating data of a target object; according to the data processing request, obtaining historical scoring data of the user terminal and a basic rating score for reflecting an average score of the target object; according to the current rating data, the historical rating data and the basic rating data, calculating a weight value of the user terminal for the current score of the target object; and according to the rating data of each user terminal for the target object and the corresponding weight value, calculating a current total rating score of the target object. The invention also discloses a data processing apparatus. According to the invention, the data reliability and the data authenticity are improved.

Description

Data processing method and device

Technical field

The present invention relates to networking technology area, particularly relate to data processing method and device.

Background technology

Along with the fast development of mobile intelligent terminal, the mode of to be carried out commodity purchasing by intelligent terminal is on the net also more and more frequent.In order to embody the difference of commodity, usually after user buys commodity, commodity are marked.

Due to the scoring of commodity, to user when selecting commodity, produce visual visual influence, thus the desire to purchase of adding users, therefore part manufacturer is in order to improve the scoring of commodity, thus employ professional favorable comment user terminal or occupation difference comments user terminal to evaluate commodity, to promote the commodity scoring of oneself or to reduce the scoring of other people commodity; Because commodity score data exists larger human factor, thus make the reliability of existing goods score data lower.

Summary of the invention

The fundamental purpose of the embodiment of the present invention is to provide a kind of data processing method and device, is intended to the reliability and the authenticity that improve data.

For achieving the above object, embodiments provide a kind of data processing method to comprise the following steps:

Receive the data processing request that user terminal sends, described data processing request comprises the information of user terminal and the current score data to destination object;

According to described data processing request, obtain the history score data of described user terminal and the basic score mark for reacting described destination object average score;

Calculate according to described current score data, described history score data and described basic score mark and obtain described user terminal to described destination object when time weighted value of scoring;

According to each user terminal, the current overall that the score data of described destination object and corresponding weighted value calculate destination object is marked mark.

Further, the embodiment of the present invention additionally provides a kind of data processing equipment and comprises:

Receiver module, for receiving the data processing request that user terminal sends, described data processing request comprises the information of user terminal and the current score data to destination object;

Acquisition module, for according to described data processing request, obtains the history score data of described user terminal and the basic score mark for reacting described destination object average score;

First computing module, obtains described user terminal to described destination object when time weighted value of scoring for calculating according to described current score data, described history score data and described basic score mark;

Second computing module, for marking mark to the current overall that the score data of described destination object and corresponding weighted value calculate destination object according to each user terminal.

The embodiment of the present invention is when receiving the first request of data that user terminal sends, obtain target histories score data and basic score mark, and obtain weighted value corresponding to current score data according to current score data, target histories score data and basic score mark according to preset computation rule analytical calculation, and according to the score data of destination object and the current overall scoring mark of corresponding weighted value analytical calculation acquisition destination object.Owing to have employed weighted calculation analysis, thus effectively reduce abnormal data (i.e. occupation difference comments the score data of user or the professional favorable comment user terminal) impact on TOP SCORES mark, and then improve reliability and the authenticity of data.

Accompanying drawing explanation

Fig. 1 is the schematic flow sheet of data processing method one embodiment of the present invention;

Fig. 2 is the refinement schematic flow sheet of step S30 mono-embodiment in Fig. 1;

Fig. 3 is the refinement schematic flow sheet of another embodiment of step S30 in Fig. 1;

Fig. 4 is the schematic flow sheet of another embodiment of data processing method of the present invention;

Fig. 5 is the high-level schematic functional block diagram of data processing equipment one embodiment of the present invention;

Fig. 6 is the high-level schematic functional block diagram of the first computing module in Fig. 5;

Fig. 7 is the high-level schematic functional block diagram of another embodiment of data processing equipment of the present invention;

Fig. 8 is the hardware structure schematic diagram of the another embodiment of data processing equipment of the present invention.

The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further with reference to accompanying drawing.

Embodiment

Technical scheme of the present invention is further illustrated below in conjunction with Figure of description and specific embodiment.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.

The present invention proposes a kind of data processing method.With reference to Fig. 1, the data processing method of this embodiment comprises the following steps:

Step S10, receives the data processing request that user terminal sends;

Described data processing request comprises the information of user terminal and the current score data to destination object.The information of above-mentioned user terminal can be the title or code etc. of user terminal; Above-mentioned destination object can be commodity or a kind of service, and all make detailed description for commodity in following examples, such as these commodity can be electromagnetic oven, electric cooker etc.; Above-mentioned current scoring mark is the score data of user terminal to commodity, and this score data is the evaluating data of fractional form particularly, such as, can mark with 3 points or 5 points.

Step S20, according to described data processing request, obtains the history score data of described user terminal and the basic score mark for reacting described destination object average score;

Be understandable that, in the present embodiment, can preset historgraphic data recording table and the object score record sheet to each object at server end; Wherein historgraphic data recording table is for storing each scoring record of each user terminal, and this scoring record can comprise the information etc. of the object of the scoring of user, score data and user terminal; Object score record sheet is for storing the score data each time of each object, the information of corresponding user terminal and history TOP SCORES mark etc.Particularly, when receiving data processing request, the information inquiry by user terminal obtains all history score data corresponding to described user terminal; And in object score record sheet, inquire about the basic score mark of also analytical reactions destination object average score by the title of destination object or code.

Step S30, calculates according to described current score data, described history score data and described basic score mark and obtains described user terminal to described destination object when time weighted value of scoring;

After analysis obtains above-mentioned history score data and basic score mark, calculate acquisition user terminal to described destination object when time weighted value of scoring by according to front score data, described history score data and described basic score mark according to preset computation rule.

Step S40, to mark mark to the current overall that the score data of described destination object and corresponding weighted value calculate destination object according to each user terminal.

Concrete, in object score record sheet, store all history score data of destination object and the weighted value of correspondence.After calculating the weighted value obtaining this scoring, the scoring mark of destination object will be calculated according to all score data of destination object and the weighted value of correspondence.

The embodiment of the present invention is when receiving the first request of data that user terminal sends, obtain target histories score data and basic score mark, and obtain weighted value corresponding to current score data according to current score data, target histories score data and basic score mark according to preset computation rule analytical calculation, and according to the score data of destination object and the current overall scoring mark of corresponding weighted value analytical calculation acquisition destination object.Owing to have employed weighted calculation analysis, thus effectively reduce abnormal data (i.e. occupation difference comments the score data of user or the professional favorable comment user terminal) impact on TOP SCORES mark, and then improve reliability and the authenticity of data.

It should be noted that basic score mark is the data of reacting described destination object average score, the average score data particularly using which kind of data as reaction destination object can be arranged according to actual needs.Such as when the score data amount of destination object is more, can directly adopt mark of marking based on the history TOP SCORES mark of described destination object to calculate, this history TOP SCORES mark is that all scoring marks of object are weighted acquisition with corresponding weighted value according to the mode of step S40.When the score data amount of destination object is less, mark of marking based on the history TOP SCORES score average of the history TOP SCORES mark of described destination object and the preset object identical with described destination object generic can be adopted to calculate.Be understandable that, in other embodiments, mark of marking based on the average score score average of the average score mark that also can adopt destination object or the average score mark adopting described destination object and the preset object identical with described destination object generic calculates.

Further application note is done below: the data processing method of the present embodiment specifically can be applicable in commodity score calculation by how calculating basic score mark to the data processing method in above-described embodiment, this destination object is electromagnetic oven, preset object is electric cooker, wherein the history score data of electromagnetic oven is 3,3,5,4,4,4,4,2,5,5, and corresponding weighted value is 0.9,1.1,1,1,0.7,1.3,1,1,1,1; The history score data of electric cooker is, 2,2,5,4,4,4,4,2,5,5, and corresponding weighted value is 0.8,1.2,1,1,0.7,1.3,1,1,0.9,1.1; If being weighted by the mode of step S40 the history TOP SCORES mark obtaining electromagnetic oven is 3.9, the history TOP SCORES mark of electric cooker is 3.7.When then directly adopting mark of marking based on the history TOP SCORES mark of described destination object to calculate, basic score mark is 3.9; When adopting mark of marking based on the history TOP SCORES score average of the history TOP SCORES mark of described destination object and the preset object identical with described destination object generic to calculate, basic score mark is 3.8.Should be noted that, because the generic of above-mentioned electromagnetic oven and electric cooker is household electrical appliance, therefore mark of marking based on the mean value of both history TOP SCORES marks can be adopted, particularly, the quantity of above-mentioned preset object can be arranged according to actual needs in actual applications, can be the part commodity of these household electrical appliance, also can be all commodity of household electrical appliance.Be 3.9 make detailed description with basic score mark in following examples.

Further, the mode that above-mentioned weighted value calculates can be arranged according to actual needs, and, with reference to Fig. 2, above-mentioned steps S30 comprises in the present embodiment preferably:

Step S31, adds up described history score data lower than the number of times k of described basic score mark, the number of times m of described history score data greater than or equal to described basic score mark and the mean value mean_score of history score data;

Step S32, according to current score data, basic score mark, k, m and mean_score analytical calculation, user terminal is when time weighted value of scoring;

Described weighted value w meets:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}};$ Wherein, mark of marking based on base_score, score is the current score data of user terminal, and ε is the constant in the first presetting range, and δ is the constant in the second presetting range.

The numerical values recited of above-mentioned first presetting range and the second presetting range can be arranged according to actual needs, and such as above-mentioned first presetting range is the 0 to 0.002, the second presetting range is 0 to 1, following examples, will with ε for 0.001, and δ 0.5 makes detailed description.

Further application note is done below: such as user terminal A gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven), and the history score data of user terminal A is 2,3,5,5,4 by how calculating weighted value to the data processing method in above-described embodiment; Then score is 5, mean_score be 3.8, k be 2, m is 3.Now then have:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}={\left(\frac{2}{3}\right)}^{{\left(\frac{3.8-3.9+0.001}{5-3.8+0.001}\right)}^{0.5}}=1.12$

Such as user terminal B gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven) again, and the history score data of user terminal B is 5,5,5,5,3; Then score is 5, mean_score be 4.6, k be 1, m is 4.Now then have:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}={\left(\frac{1}{4}\right)}^{{\left(\frac{4.6-3.9+0.001}{5-4.6+0.001}\right)}^{0.5}}=0.15$

User terminal A and user terminal B can find out that be similar to and can think that this user terminal B is professional favorable comment user, therefore for identical scoring, weighted value is different because the scoring of user terminal B is comparatively close to the effect being full favorable comment.

Be understandable that, in actual applications, when above-mentioned k or m is 0, conveniently calculate, correspondingly can add that a small constant (as 0.0001) calculates, i.e. k=k+0.0001.

Further, based on above-described embodiment, in the present embodiment, also comprise after above-mentioned steps S32:

Step S33, carries out additive effect Processing for removing to described weighted value;

Meet to make described weighted value w:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{e^{\mathrm{\τ}\left(\frac{{\mathrm{\Π}}_{i=1}^m{(({\mathrm{score}}_i-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ})/\max \_\mathrm{socre})}^{\mathrm{\α}}}{{\mathrm{\Π}}_{j=1}^k{\left(\right|{\mathrm{score}}_j-\mathrm{base}\_\mathrm{score}|+\mathrm{\ϵ}/\max \_\mathrm{socre})}^{\mathrm{\β}}}\right)}};$ Wherein, k is the number of times of history score data lower than described basic score mark, m is the number of times of history score data greater than or equal to described basic score mark, mean_score is the mean value of history score data, mark of marking based on base_score, and score is the current score data of user terminal, ε is the constant in the first presetting range, e is constant, and δ, τ, α, β are the constant in the second presetting range, and α and β sum is 1; Above-mentioned i and j is variable, and namely i is the natural number of 1 to m, and j is the natural number of 1 to k.

The numerical values recited of above-mentioned first presetting range and the second presetting range can be arranged according to actual needs, such as above-mentioned first presetting range is the 0 to 0.002, the second presetting range is 0 to 1, following examples, to be 0.001, α with ε, β, τ, δ be 0.5 and make detailed description.

Further application note is done below: such as user terminal A gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven), and the history score data of user terminal A is 2,3,5,5,4 by how to calculate the weighted value after eliminating additive effect to the data processing method in above-described embodiment; Then score is 5, mean_score be 3.8, k be 2, m is 3, max_socre=5.Accumulation factor G is then had to be:

$G=e^{0.5\left(\frac{{((5-3.9+0.001)/5)}^{0.5}*{((5-3.9+0.001)/5)}^{0.5}*{((4-3.9+0.001)/5)}^{0.5}+0.001}{{(\left(\right|2-3.9|+0.001)/5)}^{0.5}*{(\left(\right|3-3.9|+0.001)/5)}^{0.5}+0.001}\right)}=e^0.059$

The weighted value w eliminating accumulation factor is:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{G}=\frac{1.12}{e^0.059}=1.05$

The present embodiment eliminates the additive effect of weight owing to have employed accumulation factor, thus ensure that weighted value validity, further increases reliability and the authenticity of data.It should be noted that in actual applications, above-mentioned mean_score is the mean value of history score data, and this mean value also can for adding the mean value after weight calculation.The history score data of such as user terminal A is 2,3,5,5,4, corresponding weighted value is 1.2,1,1.5,1.1,1.2, then the mean value of the history score data of this user terminal A is: (2*1.2+3*1+5*1.5+5*1.1+4*1.2)/(1.2+1+1.5+1.1+1.2)=3.86.Specifically can arrange according to actual needs, not limit further at this.

Particularly, the calculating of the above-mentioned scoring of the current overall to destination object mark, can arrange according to actual needs, preferably, above-mentioned steps S40 comprises the present embodiment:

Using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the TOP SCORES mark obtaining destination object.

The history TOP SCORES mark of such as above-mentioned electromagnetic oven is (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1)=3.90, and the TOP SCORES mark after user terminal A scoring is (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1+5*1.05)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1+1.05)=4.00.

The user terminal of such as having employed 100 professional favorable comments when businessman has again carried out the scoring of 5 points to commodity, if calculate by above-mentioned weighted value the weighted value obtaining these 100 user terminals to be 0.01, then the TOP SCORES mark after 100 user terminal scorings is: (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1+5*0.01*1 00)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1+0.01*100)=3.94.Therefore less on the TOP SCORES mark impact that destination object is final, improve the authenticity of data.

Be understandable that, in order to the diversity of satisfied scoring, to improve the scope that data processing is suitable for, with reference to Fig. 4, described data processing request also comprises the non-score data to destination object Evaluation: Current, also comprises after above-mentioned steps S10:

Step S50, is converted to score data by described non-score data by the transformation rule preset, and using the score data after conversion as current score data.

Particularly, above-mentioned non-score data is the evaluating data (such as word evaluating data) of non-fractional form, and in the present embodiment, the evaluating data in request of data can be score data, also can be non-score data.When request of data comprises non-score data, option of such as marking is non-constant, difference, general, satisfied, very satisfaction.This option can be converted to the score data of value type scoring, then select corresponding conversion after non-constant, difference, general, satisfied, very satisfied scoring to be 1,2,3,4,5.Be understandable that, the score data of score value of also difference can being marked is converted to corresponding scoring.Such as when points-scoring system is marked with 100 points, then the scoring of 90 ~ 100 can be converted to 5, the scoring of 80 ~ 90 is converted to 4, the scoring of 70 ~ 80 is converted to 3, the scoring of 60 ~ 70 is converted to 2, by 0 ~ 60 be converted to 1 etc.It should be noted that the position of above-mentioned steps S50 and step S20 can exchange, do not limit further at this.

The present invention additionally provides a kind of data processing equipment further, and with reference to Fig. 5, the data processing equipment that the present embodiment provides comprises:

Receiver module 100, for receiving the data processing request that user terminal sends;

Described data processing request comprises the information of user terminal and the current score data to destination object.The information of above-mentioned user terminal can be the title or code etc. of user terminal; Above-mentioned destination object can be commodity or a kind of service, and all make detailed description for commodity in following examples, such as these commodity can be such as electromagnetic oven, electric cooker etc.; Above-mentioned current scoring mark is the score data of user terminal to commodity, and this score data is the evaluating data of fractional form particularly, such as, can mark with 3 points or 5 points.

Acquisition module 200, for according to described data processing request, obtains the history score data of described user terminal and the basic score mark for reacting described destination object average score;

Be understandable that, in the present embodiment, can preset historgraphic data recording table and the object score record sheet to each object at server end; Wherein historgraphic data recording table is for storing each scoring record of each user terminal, and this scoring record can comprise the information etc. of the object of the scoring of user, score data and user terminal; Object score record sheet is for storing the score data each time of each object, the information of corresponding user terminal and history TOP SCORES mark etc.Particularly, when receiving data processing request, the information inquiry by user terminal obtains all history score data corresponding to described user terminal; And in object score record sheet, inquire about the basic score mark of also analytical reactions destination object average score by the title of destination object or code.

First computing module 300, obtains described user terminal to described destination object when time weighted value of scoring for calculating according to described current score data, described history score data and described basic score mark;

After acquisition module 200 analysis obtains above-mentioned history score data and basic score mark, calculate acquisition user terminal to described destination object when time weighted value of scoring according to front score data, described history score data and described basic score mark according to preset computation rule by by the first computing module 300.

Second computing module 400, for marking mark to the current overall that the score data of described destination object and corresponding weighted value calculate destination object according to each user terminal.

Concrete, in object score record sheet, store all history score data of destination object and the weighted value of correspondence.After calculating the weighted value obtaining this scoring, the scoring mark of destination object will be calculated according to all score data of destination object and the weighted value of correspondence.

The embodiment of the present invention is when receiving the first request of data that user terminal sends, obtain target histories score data and basic score mark, and obtain weighted value corresponding to current score data according to current score data, target histories score data and basic score mark according to preset computation rule analytical calculation, and according to the score data of destination object and the current overall scoring mark of corresponding weighted value analytical calculation acquisition destination object.Owing to have employed weighted calculation analysis, thus effectively reduce abnormal data (i.e. occupation difference comments the score data of user or the professional favorable comment user terminal) impact on TOP SCORES mark, and then improve reliability and the authenticity of data.

It should be noted that basic score mark is the data of reacting described destination object average score, the average score data particularly using which kind of data as reaction destination object can be arranged according to actual needs.Such as when the score data amount of destination object is more, can directly adopt mark of marking based on the history TOP SCORES mark of described destination object to calculate, this history TOP SCORES mark is that all scoring marks of object are weighted acquisition with corresponding weighted value according to the mode of the second computing module 400.When the score data amount of destination object is less, mark of marking based on the history TOP SCORES score average of the history TOP SCORES mark of described destination object and the preset object identical with described destination object generic can be adopted to calculate.Be understandable that, in other embodiments, mark of marking based on the average score score average of the average score mark that also can adopt destination object or the average score mark adopting described destination object and the preset object identical with described destination object generic calculates.

Further application note is done below: the data processing method of the present embodiment specifically can be applicable in commodity score calculation by how calculating basic score mark to the data processing method in above-described embodiment, this destination object is electromagnetic oven, preset object is electric cooker, wherein the history score data of electromagnetic oven is 3,3,5,4,4,4,4,2,5,5, and corresponding weighted value is 0.9,1.1,1,1,0.7,1.3,1,1,1,1; The history score data of electric cooker is, 2,2,5,4,4,4,4,2,5,5, and corresponding weighted value is 0.8,1.2,1,1,0.7,1.3,1,1,0.9,1.1; If being weighted by the mode of the second computing module 400 the history TOP SCORES mark obtaining electromagnetic oven is 3.9, the history TOP SCORES mark of electric cooker is 3.7.When then directly adopting mark of marking based on the history TOP SCORES mark of described destination object to calculate, basic score mark is 3.9; When adopting mark of marking based on the history TOP SCORES score average of the history TOP SCORES mark of described destination object and the preset object identical with described destination object generic to calculate, basic score mark is 3.8.Should be noted that, because the generic of above-mentioned electromagnetic oven and electric cooker is household electrical appliance, therefore mark of marking based on the mean value of both history TOP SCORES marks can be adopted, particularly, the quantity of above-mentioned preset object can be arranged according to actual needs in actual applications, can be the part commodity of these household electrical appliance, also can be all commodity of household electrical appliance.Be 3.9 make detailed description with basic score mark in following examples.

Further, the mode that above-mentioned weighted value calculates can be arranged according to actual needs, and, with reference to Fig. 6, described first computing module 300 comprises in the present embodiment preferably:

Statistic unit 301, for adding up described history score data lower than the number of times k of described basic score mark, the number of times m of described history score data greater than or equal to described basic score mark and the mean value mean_score of history score data;

Computing unit 302, for user terminal according to current score data, basic score mark, k, m and mean_score analytical calculation when time weighted value of scoring; Described weighted value w meets:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}};$ Wherein, mark of marking based on base_score, score is the current score data of user terminal, and ε is the constant in the first presetting range, and δ is the constant in the second presetting range.

The numerical values recited of above-mentioned first presetting range and the second presetting range can be arranged according to actual needs, and such as above-mentioned first presetting range is the 0 to 0.002, the second presetting range is 0 to 1, following examples, will with ε for 0.001, and δ 0.5 makes detailed description.

Further application note is done below: such as user terminal A gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven), and the history score data of user terminal A is 2,3,5,5,4 by how calculating weighted value to the data processing method in above-described embodiment; Then score is 5, mean_score be 3.8, k be 2, m is 3.Now then have:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}={\left(\frac{2}{3}\right)}^{{\left(\frac{3.8-3.9+0.001}{5-3.8+0.001}\right)}^{0.5}}=1.12$

Such as user terminal B gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven) again, and the history score data of user terminal B is 5,5,5,5,3; Then score is 5, mean_score be 4.6, k be 1, m is 4.Now then have:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}={\left(\frac{1}{4}\right)}^{{\left(\frac{4.6-3.9+0.001}{5-4.6+0.001}\right)}^{0.5}}=0.15$

User terminal A and user terminal B can find out that be similar to and can think that this user terminal B is professional favorable comment user, therefore for identical scoring, weighted value is different because the scoring of user terminal B is comparatively close to the effect being full favorable comment.

Be understandable that, in actual applications, when above-mentioned k or m is 0, conveniently calculate, correspondingly can add that a small constant (as 0.0001) calculates, i.e. k=k+0.0001.

Further, based on above-described embodiment, in the present embodiment, described computing module 300 also comprises:

Processing unit 303, for carrying out additive effect Processing for removing to described weighted value, meets to make described weighted value w:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{e^{\mathrm{\τ}\left(\frac{{\mathrm{\Π}}_{i=1}^m{(({\mathrm{score}}_i-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ})/\max \_\mathrm{socre})}^{\mathrm{\α}}}{{\mathrm{\Π}}_{j=1}^k{\left(\right|{\mathrm{score}}_j-\mathrm{base}\_\mathrm{score}|+\mathrm{\ϵ}/\max \_\mathrm{socre})}^{\mathrm{\β}}}\right)}};$ Wherein, k is the number of times of history score data lower than described basic score mark, m is the number of times of history score data greater than or equal to described basic score mark, mean_score is the mean value of history score data, mark of marking based on base_score, and score is the current score data of user terminal, ε is the constant in the first presetting range, e is constant, and δ, τ, α, β are the constant in the second presetting range, and α and β sum is 1; Above-mentioned i and j is variable, and namely i is the natural number of 1 to m, and j is the natural number of 1 to k.

The numerical values recited of above-mentioned first presetting range and the second presetting range can be arranged according to actual needs, such as above-mentioned first presetting range is the 0 to 0.002, the second presetting range is 0 to 1, following examples, to be 0.001, α with ε, β, τ, δ be 0.5 and make detailed description.

Further application note is done below: such as user terminal A gives the scoring of 5 points to destination object (above-mentioned electromagnetic oven), and the history score data of user terminal A is 2,3,5,5,4 by how to calculate the weighted value after eliminating additive effect to the data processing method in above-described embodiment; Then score is 5, mean_score be 3.8, k be 2, m is 3, max_socre=5.Accumulation factor G is then had to be:

$G=e^{0.5\left(\frac{{((5-3.9+0.001)/5)}^{0.5}*{((5-3.9+0.001)/5)}^{0.5}*{((4-3.9+0.001)/5)}^{0.5}+0.001}{{(\left(\right|2-3.9|+0.001)/5)}^{0.5}*{(\left(\right|3-3.9|+0.001)/5)}^{0.5}+0.001}\right)}=e^0.059$

The weighted value w eliminating accumulation factor is:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{G}=\frac{1.12}{e^0.059}=1.05$

The present embodiment eliminates the additive effect of weight owing to have employed accumulation factor, thus ensure that weighted value validity, further increases reliability and the authenticity of data.It should be noted that in actual applications, above-mentioned mean_score is the mean value of history score data, and this mean value also can for adding the mean value after weight calculation.The history score data of such as user terminal A is 2,3,5,5,4, corresponding weighted value is 1.2,1,1.5,1.1,1.2, then the mean value of the history score data of this user terminal A is: (2*1.2+3*1+5*1.5+5*1.1+4*1.2)/(1.2+1+1.5+1.1+1.2)=3.86.Specifically can arrange according to actual needs, not limit further at this.

Particularly, the calculating of the above-mentioned scoring of the current overall to destination object mark, can arrange according to actual needs, the present embodiment preferably, described second computing module 400 for, using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the TOP SCORES mark obtaining destination object.

Using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the TOP SCORES mark obtaining destination object.

The TOP SCORES mark TOP SCORES mark of such as above-mentioned electromagnetic oven is (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1)=3.90, and the TOP SCORES mark after user terminal A scoring is (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1+5*1.05)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1+1.05)=4.00.

The user terminal of such as having employed 100 professional favorable comments when businessman has again carried out the scoring of 5 points to commodity, if calculate by above-mentioned weighted value the weighted value obtaining these 100 user terminals to be 0.01, then the TOP SCORES mark after 100 user terminal scorings is: (3*0.9+3*1.1+5*1+4*1+4*0.7+4*1.3+4*1+2*1+5*1+5*1+5*0.01*1 00)/(0.9+1.1+1+1+0.7+1.3+1+1+1+1+0.01*100)=3.94.Therefore less on the TOP SCORES mark impact that destination object is final, improve the authenticity of data.

Be understandable that, in order to the diversity of satisfied scoring, to improve the scope that data processing is suitable for, with reference to Fig. 7, above-mentioned data processing request also comprises the non-score data to destination object Evaluation: Current, and above-mentioned data processing equipment also comprises:

Modular converter 500, for being converted to score data by described non-score data by the transformation rule preset, and using the score data after conversion as current score data.

Particularly, above-mentioned non-score data is the evaluating data (evaluating data of such as written form) of non-fractional form, and in the present embodiment, the evaluating data in request of data can be score data, also can be non-score data.When request of data comprises non-score data, option of such as marking is non-constant, difference, general, satisfied, very satisfaction.This option can be converted to the score data of value type scoring, then select corresponding conversion after non-constant, difference, general, satisfied, very satisfied scoring to be 1,2,3,4,5.Be understandable that, the score data of score value of also difference can being marked is converted to corresponding scoring.Such as when points-scoring system is marked with 100 points, then the scoring of 90 ~ 100 can be converted to 5, the scoring of 80 ~ 90 is converted to 4, the scoring of 70 ~ 80 is converted to 3, the scoring of 60 ~ 70 is converted to 2, by 0 ~ 60 be converted to 1 etc.

With reference to Fig. 8, the another embodiment of data processing equipment of the present invention is proposed.In this embodiment, this data processing equipment comprises: processor 101, storer 102, network interface 103 and communication bus 104.Communication bus 104 is for the communication between building block each in server, and network interface 103 communicates mutually with outside for server, and to receive the data processing request of user's input, this network interface 103 also can include line interface and wave point.Storer 102 can comprise one or more computer-readable recording mediums, and it not only comprises internal storage, also comprises external memory storage.Operating system and data process application etc. is stored in this storer.Processor 101 for calling the data process application in storer 102, to perform following operation:

The data processing request of user terminal transmission is received by network interface 103;

According to described data processing request, obtain the history score data of described user terminal and the basic score mark for reacting described destination object average score;

Calculate according to described current score data, described history score data and described basic score mark and obtain described user terminal to described destination object when time weighted value of scoring;

According to each user terminal, the score data of described destination object and corresponding weighted value are calculated to the TOP SCORES mark of destination object.

Further, processor 101 also for calling the data process application in storer 102, to perform following operation:

Add up described history score data lower than the number of times k of described basic score mark, the number of times m of described history score data greater than or equal to described basic score mark and the mean value mean_score of history score data;

According to current score data, basic score mark, k, m and mean_score analytical calculation, user terminal is when time weighted value of scoring; Described weighted value w meets:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}};$ Wherein, mark of marking based on base_score, score is the current score data of user terminal, and ε is the constant in the first presetting range, and δ is the constant in the second presetting range.

Further, processor 101 also for calling the data process application in storer 102, to perform following operation:

Additive effect Processing for removing is carried out to described weighted value, meets to make described weighted value w:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{e^{\mathrm{\τ}\left(\frac{{\mathrm{\Π}}_{i=1}^m{(({\mathrm{score}}_i-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ})/\max \_\mathrm{socre})}^{\mathrm{\α}}}{{\mathrm{\Π}}_{j=1}^k{\left(\right|{\mathrm{score}}_j-\mathrm{base}\_\mathrm{score}|+\mathrm{\ϵ}/\max \_\mathrm{socre})}^{\mathrm{\β}}}\right)}};$ Wherein, k is the number of times of history score data lower than described basic score mark, m is the number of times of history score data greater than or equal to described basic score mark, mean_score is the mean value of history score data, mark of marking based on base_score, and score is the current score data of user terminal, ε is the constant in the first presetting range, e is constant, and δ, τ, α, β are the constant in the second presetting range, and α and β sum is 1; Above-mentioned i and j is variable, and namely i is the natural number of 1 to m, and j is the natural number of 1 to k.

Further, processor 101 also for calling the data process application in storer 102, to perform following operation:

Using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the TOP SCORES mark obtaining destination object.

Further, processor 101 also for calling the data process application in storer 102, to perform following operation:

Described current score data is converted to default value data by the transformation rule preset.

The embodiment of the present invention is when receiving the first request of data that user terminal sends, obtain target histories score data and basic score mark, and obtain weighted value corresponding to current score data according to current score data, target histories score data and basic score mark according to preset computation rule analytical calculation, and according to the score data of destination object and the current overall scoring mark of corresponding weighted value analytical calculation acquisition destination object.Owing to have employed weighted calculation analysis, thus effectively reduce abnormal data (i.e. occupation difference comments the score data of user or the professional favorable comment user terminal) impact on TOP SCORES mark, and then improve reliability and the authenticity of data.

The foregoing is only the preferred embodiments of the present invention; not thereby its scope of the claims is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; directly or indirectly be used in the technical field that other are relevant, be all in like manner included in scope of patent protection of the present invention.

Claims (12)

1. a data processing method, is characterized in that, comprises the following steps:

Receive the data processing request that user terminal sends, described data processing request comprises the information of user terminal and the current score data to destination object;

According to described data processing request, obtain the history score data of described user terminal and the basic score mark for reacting described destination object average score;

Calculate according to described current score data, described history score data and described basic score mark and obtain described user terminal to described destination object when time weighted value of scoring;

According to each user terminal, the current overall that the score data of described destination object and corresponding weighted value calculate destination object is marked mark.

2. data processing method as claimed in claim 1, it is characterized in that, described basic score mark is the history TOP SCORES mark of described destination object; Or described basic score mark is the history TOP SCORES mark of described destination object and the history TOP SCORES score average of the preset object identical with described destination object generic.

3. data processing method as claimed in claim 1, is characterized in that, described calculating according to current score data, described history score data and described basic score mark obtains described user terminal to described destination object when time weighted value of scoring comprises:

Add up described history score data lower than the number of times k of described basic score mark, the number of times m of described history score data greater than or equal to described basic score mark and the mean value mean_score of history score data;

According to current score data, basic score mark, k, m and mean_score analytical calculation, user terminal is when time weighted value of scoring, and described weighted value w meets:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}};$ Wherein, mark of marking based on base_score, score is the current score data of user terminal, and ε is the constant in the first presetting range, and δ is the constant in the second presetting range.

4. data processing method as claimed in claim 3, is characterized in that, described according to current score data, basic score mark, k, m and mean_score analytical calculation user terminal also comprise after the weighted value of time to mark:

Additive effect Processing for removing is carried out to described weighted value, meets to make described weighted value w:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{e^{\mathrm{\τ}\left(\frac{{\mathrm{\Π}}_{i=1}^m{(({\mathrm{score}}_i-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ})/\max \_\mathrm{socre})}^{\mathrm{\α}}}{{\mathrm{\Π}}_{j=1}^k{\left(\right|{\mathrm{score}}_j-\mathrm{base}\_\mathrm{score}|+\mathrm{\ϵ}/\max \_\mathrm{socre})}^{\mathrm{\β}}}\right)}};$ Wherein, k is the number of times of history score data lower than described basic score mark, m is the number of times of history score data greater than or equal to described basic score mark, mean_score is the mean value of history score data, mark of marking based on base_score, and score is the current score data of user terminal, ε is the constant in the first presetting range, e is constant, and δ, τ, α, β are the constant in the second presetting range, and α and β sum is 1.

5. the data processing method according to any one of Claims 1-4, is characterized in that, describedly comprises the current overall that the score data of described destination object and corresponding weighted value calculate destination object mark of marking according to each user terminal:

Using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the current overall scoring mark obtaining destination object.

6. data processing method as claimed in claim 5, it is characterized in that, described data processing request also comprises the non-score data to destination object Evaluation: Current;

Also comprise after the data processing request that described reception user terminal sends:

Described non-score data is converted to score data by the transformation rule preset, and using the score data after conversion as current score data.

7. a data processing equipment, is characterized in that, comprising:

Receiver module, for receiving the data processing request that user terminal sends, described data processing request comprises the information of user terminal and the current score data to destination object;

Acquisition module, for according to described data processing request, obtains the history score data of described user terminal and the basic score mark for reacting described destination object average score;

First computing module, obtains described user terminal to described destination object when time weighted value of scoring for calculating according to described current score data, described history score data and described basic score mark;

Second computing module, for marking mark to the current overall that the score data of described destination object and corresponding weighted value calculate destination object according to each user terminal.

8. data processing equipment as claimed in claim 7, it is characterized in that, described basic score mark is the history TOP SCORES mark of described destination object; Or described basic score mark is the history TOP SCORES mark of described destination object and the history TOP SCORES score average of the preset object identical with described destination object generic.

9. data processing equipment as claimed in claim 7, it is characterized in that, described first computing module comprises:

Statistic unit, for adding up described history score data lower than the number of times k of described basic score mark, the number of times m of described history score data greater than or equal to described basic score mark and the mean value mean_score of history score data;

Computing unit, for user terminal according to current score data, basic score mark, k, m and mean_score analytical calculation when time weighted value of scoring; Described weighted value w meets:

$w={\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}};$ Wherein, mark of marking based on base_score, score is the current score data of user terminal, and ε is the constant in the first presetting range, and δ is the constant in the second presetting range.

10. data processing equipment as claimed in claim 9, it is characterized in that, described computing module also comprises:

Processing unit, for carrying out additive effect Processing for removing to described weighted value, meets to make described weighted value w:

$w=\frac{{\left(\frac{k}{m}\right)}^{{\left(\frac{\mathrm{mean}\_\mathrm{score}-\mathrm{base}\_\mathrm{core}+\mathrm{\ϵ}}{\mathrm{score}-\mathrm{mean}\_\mathrm{score}+\mathrm{\ϵ}}\right)}^{\mathrm{\δ}}}}{e^{\mathrm{\τ}\left(\frac{{\mathrm{\Π}}_{i=1}^m{(({\mathrm{score}}_i-\mathrm{base}\_\mathrm{score}+\mathrm{\ϵ})/\max \_\mathrm{socre})}^{\mathrm{\α}}}{{\mathrm{\Π}}_{j=1}^k{\left(\right|{\mathrm{score}}_j-\mathrm{base}\_\mathrm{score}|+\mathrm{\ϵ}/\max \_\mathrm{socre})}^{\mathrm{\β}}}\right)}};$ Wherein, k is the number of times of history score data lower than described basic score mark, m is the number of times of history score data greater than or equal to described basic score mark, mean_score is the mean value of history score data, mark of marking based on base_score, and score is the current score data of user terminal, ε is the constant in the first presetting range, e is constant, and δ, τ, α, β are the constant in the second presetting range, and α and β sum is 1.

11. data processing equipments according to any one of claim 7 to 10, it is characterized in that, described second computing module is used for, using each user terminal to the product summation of the score data of described destination object and corresponding weighted value as molecule, using the weighted value sum of correspondence as denominator, calculate the current overall scoring mark obtaining destination object.

12. data processing equipments as claimed in claim 11, it is characterized in that, described data processing request also comprises the non-score data to destination object Evaluation: Current;

Described data processing equipment also comprises:

Modular converter, for being converted to score data by described non-score data by the transformation rule preset, and using the score data after conversion as current score data.