CN104899766A - Method and device for selecting object attributes - Google Patents
Method and device for selecting object attributes Download PDFInfo
- Publication number
- CN104899766A CN104899766A CN201510298581.6A CN201510298581A CN104899766A CN 104899766 A CN104899766 A CN 104899766A CN 201510298581 A CN201510298581 A CN 201510298581A CN 104899766 A CN104899766 A CN 104899766A
- Authority
- CN
- China
- Prior art keywords
- attribute
- weight
- difference degree
- utilization coefficient
- attributes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention provides a method and a device for selecting object attributes. The important degree of the object attributes can be objectively and immediately measured and the object attributes can be selected. The method comprises the steps: establishing a combined equation set of an object attribute value combination and aggregate utility and solving utilization coefficients of different attribute values by virtue of the combined equation set; calculating the in-attribute differential degrees in the attributes by comparing the utilization coefficients of the different attribute values in the same attribute; calculating first weights of the attributes according to the in-attribute differential degrees of the attributes; carrying out semantic analysis on the object related pre-stored data to obtain second weights of the attributes; calculating comprehensive weights of the attributes according to the first and second weights of the attributes; and selecting the attributes and outputting the selection results according to the comprehensive weights of the attributes.
Description
Technical field
The present invention relates to Internet technical field, particularly relate to a kind of method and device of alternative attribute.
Background technology
Normally, an object can have multiple attributes.Such as clothes can have the attributes such as color, size, making material, and books can have the attributes such as author, publisher, format.For same object, some attribute is important, and some attribute is more secondary.In order to realize carrying out better Object Selection, sell publicity and to design and develop etc. object, in the multi-object attribute that needs to comform, select the attribute wanted of overstating for user, businessman and manufacturer.
In prior art, normally by manual type, by virtue of experience weigh the importance of each attribute of certain object.Which also exists certain weak point.First, be subject to the multiple subjective factor impact such as experience, individual position, it is objective not to cause the evaluation of Importance of Attributes, selects to there will be erroneous judgement during important attribute.Secondly, the personnel that can be subject to, on the slow impact of market sensitive and reactive, cause the evaluation of Importance of Attributes or select can not keep synchronous in real time with market in time.
Summary of the invention
In view of this, the invention provides a kind of method and device of alternative attribute, the significance level of object properties can be weighed objectively, in time and make a choice accordingly.
For achieving the above object, according to an aspect of the present invention, a kind of method of alternative attribute is provided.According to the method for the alternative attribute of the embodiment of the present invention, comprising: the associating system of equations setting up object attribute values combination and aggreggate utility, solves the utilization coefficient that described associating system of equations obtains different attribute value; By comparing the utilization coefficient of the different attribute value in same alike result, difference degree in the attribute calculating this attribute; According to difference degree in the described attribute of all properties, calculate the first weight of each attribute; Preservation data in advance about described object carry out semantic analyses, obtains the second weight of each attribute; According to described first weight and described second weight of each attribute, calculate the comprehensive weight of each attribute; Make a choice and export selected results according to the comprehensive weight of each attribute described.
Alternatively, the general formula of the single associating equation in described associating system of equations is: Y=∑ VX, and wherein, Y represents the aggreggate utility that object attribute values combines, V represents the utilization coefficient of each property value, and X represents whether each property value occurs in described object attribute values combination.
Alternatively, in described attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.
Alternatively, described first weight of each attribute equal this attribute described attribute in difference degree divided by difference degree summation in the described attribute of all properties.
Alternatively, the described comprehensive weight of attribute equals the arithmetical mean of described second weight of described first weight and this attribute.
For achieving the above object, according to a further aspect in the invention, a kind of device of alternative attribute is provided.According to the device of the alternative attribute of the embodiment of the present invention, comprising: utilization coefficient computing module, for setting up the associating system of equations of object attribute values combination and aggreggate utility, solving the utilization coefficient that described associating system of equations obtains different attribute value; Difference degree computing module, for the utilization coefficient by comparing the different attribute value in same alike result, difference degree in the attribute calculating this attribute; First Weight Acquisition module, for according to difference degree in the described attribute of all properties, calculates the first weight of each attribute; Second Weight Acquisition module, for carry out semantic analysis to the preservation data in advance about described object, obtains the second weight of each attribute; Comprehensive ratio acquisition module, for according to described first weight of each attribute and described second weight, calculates the comprehensive weight of each attribute; Select output module, for making a choice according to the comprehensive weight of each attribute described and export selected results.
Alternatively, in described utilization coefficient computing module, the general formula of the single associating equation in described associating system of equations is: Y=∑ VX, wherein, Y represents the aggreggate utility that object attribute values combines, V represents the utilization coefficient of each property value, and X represents whether each property value occurs in described object attribute values combination.
Alternatively, in described difference degree computing module, in attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.
Alternatively, in described first Weight Acquisition module, in the described attribute that described first weight of each attribute equals this attribute, difference degree is divided by difference degree summation in the described attribute of all properties.
Alternatively, in described comprehensive weight acquisition module, the described comprehensive weight of attribute equals the arithmetical mean of described second weight of described first weight and this attribute.
According to technical scheme of the present invention, object properties and aggreggate utility are connected, take into account preservation data in advance simultaneously and carry out semantic analysis result, finally obtain the comprehensive weight of different object properties and make a policy accordingly, avoid error that artificial judgment Importance of Attributes brings and out-of-date, have simple, just objective, can the advantage such as real-time update.
Accompanying drawing explanation
Accompanying drawing is used for understanding the present invention better, does not form inappropriate limitation of the present invention.Wherein:
Fig. 1 is the schematic diagram of the key step of the method for alternative attribute according to the embodiment of the present invention;
Fig. 2 is the schematic diagram of the critical piece of the device of alternative attribute according to the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, one exemplary embodiment of the present invention is explained, comprising the various details of the embodiment of the present invention to help understanding, they should be thought it is only exemplary.Therefore, those of ordinary skill in the art will be appreciated that, can make various change and amendment, and can not deviate from scope and spirit of the present invention to the embodiments described herein.Equally, for clarity and conciseness, the description to known function and structure is eliminated in following description.
Fig. 1 is the schematic diagram of the key step of the method for alternative attribute according to the embodiment of the present invention.As shown in Figure 1, according to the method for the alternative attribute of the embodiment of the present invention, comprise the steps that A is to step F.
Steps A: the associating system of equations setting up object attribute values combination and aggreggate utility, solves the utilization coefficient that associating system of equations obtains different attribute value.Wherein, object refers to commodity, music, picture, article etc.Aggreggate utility can be sales volume, click volume, download, votes etc.Property value is the particular type in each attribute.
For " mobile phone " merchandise items.Mobile phone comprises " color ", " size " and " CPU check figure " three attributes." color " attribute specifically comprises " black " and " white " two property values; " size " attribute specifically comprises " 5 cun " and " 6 cun " two property values; " CPU check figure " attribute specifically comprises " double-core " and " four core " two property values.The mobile phone sales volume of different attribute value combination is different, as shown in table 1.
The sales volume of the mobile phone of table 1 different attribute value combination
In one embodiment of the invention, the general formula of the single associating equation in associating system of equations is: Y=∑ VX, and wherein, Y represents the aggreggate utility that object attribute values combines, V represents the utilization coefficient of each property value, and X represents whether each property value occurs in object attribute values combination.It should be noted that, the general formula of associating equation also can be other form, such as " multiple property values that aggreggate utility equals to form combination for property value utilization coefficient ly to amass " etc.
In the superincumbent embodiment about mobile phone sales volume, by " black, white, 5 cun, 6 cun, double-core, four cores " property value be designated as respectively " v1, v2, v3, v4, v5, v6 ", then can set up and combine system of equations as follows:
282＝1×v1+0×v2+1×v3+0×v4+1×v5+0×v6
285＝1×v1+0×v2+1×v3+0×v4+0×v5+1×v6
275＝1×v1+0×v2+0×v3+1×v4+1×v5+0×v6
278＝1×v1+0×v2+0×v3+1×v4+0×v5+1×v6
262＝0×v1+1×v2+1×v3+0×v4+1×v5+0×v6
265＝0×v1+1×v2+1×v3+0×v4+0×v5+1×v6
255＝0×v1+1×v2+0×v3+1×v4+1×v5+0×v6
258＝0×v1+1×v2+0×v3+1×v4+0×v5+1×v6
Obtaining the numerical value of v1 to v6 by solving associating system of equations, namely obtaining the utilization coefficient of each property value, as shown in table 2 below.
The utilization coefficient of each property value of table 2
| Attribute | Property value | Utilization coefficient |
| Color | Black | 100 |
| Color | White | 80 |
| Size | 5 cun | 94 |
| Size | 6 cun | 87 |
| CPU check figure | Double-core | 88 |
| CPU check figure | Four cores | 91 |
Step B: by comparing the utilization coefficient of the different attribute value in same alike result, difference degree in the attribute calculating this attribute.
In one embodiment of the invention, in attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.Weigh difference degree in attribute by the difference of max min, there is the simple advantage of algorithm.
Now, in the attribute of color attribute, difference degree equals black property value utilization coefficient and deducts white property value utilization coefficient, and result of calculation is 100-80=20.Similarly, in the attribute that can calculate size attribute difference degree be 7, CPU check figure attribute attribute in difference degree be 3.
It should be noted that, in other embodiments of the invention, in attribute, difference degree can also be represented by forms such as variances, is not necessarily defined as the difference of maximum utility coefficient and minimum utilization coefficient.
Step C: according to difference degree in the attribute of all properties, calculates the first weight of each attribute.
In one embodiment of the invention, in the attribute that the first weight of each attribute equals this attribute, difference degree is divided by difference degree summation in the attribute of all properties, and this algorithm has simple advantage.Now, first weight=20/ (20+7+3)=67% of color attribute can be calculated; First weight=7/ (20+7+3)=23% of size attribute; First weight=3/ (20+7+3)=10% of CPU check figure attribute.
Step D: carry out semantic analysis to the preservation data in advance about object, obtains the second weight of each attribute.The present invention the form of preserving data be in advance not construed as limiting about object, it can be user comment data, user journal or online question and answer chat record etc., and these data can embody the degree of attentiveness of user to certain attribute.
Such as, from user to digging user the comment data of mobile phone commodity to the review information of various mobile phone attribute, the occurrence number ratio of statistical attribute associative key, can obtain the importance on the semantic level of attribute, namely obtains the second weight.The second weight supposing to obtain color attribute is 60%, and the second weight of size attribute is 30%; Second weight of CPU check figure attribute is 10%.
Step e: according to the first weight and second weight of each attribute, calculate the comprehensive weight of each attribute.
In one embodiment of the invention, the comprehensive weight of attribute equals the arithmetical mean of the second weight of the first weight and this attribute, and this algorithm has simple advantage.Now, the data in table 3 are calculated.
The comprehensive weight of each attribute of table 3
| Attribute | Comprehensive weight |
| Color | (67％+60％)/2＝63.5％ |
| Size | (23％+30％)/2＝26.5％ |
| CPU check figure | (l0％+10％)/2＝l0％ |
As can be seen from Table 3, user pays close attention to the color attribute of mobile phone most, least pays close attention to CPU check figure attribute.
Step F: make a choice and export selected results according to the comprehensive weight of each attribute.Such as, advertisement plan personnel can describe emphatically the high attribute of comprehensive weight when publicizing object, and manufacturer can the product of different attribute value combination under the attribute that ranks forefront of focus development some comprehensive weights when designing new generation product.
Fig. 2 is the schematic diagram of the critical piece of the device of alternative attribute according to the embodiment of the present invention.As shown in Figure 2, according to the device 20 of the alternative attribute of the embodiment of the present invention, can comprise: utilization coefficient computing module 21, difference degree computing module 22, first Weight Acquisition module 23, second Weight Acquisition module 24, comprehensive ratio acquisition module 25 and selection output module 26.
Utilization coefficient computing module 21, for setting up the associating system of equations of object attribute values combination and aggreggate utility, solves the utilization coefficient that associating system of equations obtains different attribute value.In one embodiment of the invention, in utilization coefficient computing module 21, the general formula of the single associating equation in associating system of equations is: Y=∑ VX, wherein, Y represents the aggreggate utility that object attribute values combines, V represents the utilization coefficient of each property value, and X represents whether each property value occurs in object attribute values combination.
Difference degree computing module 22 for the utilization coefficient by comparing the different attribute value in same alike result, difference degree in the attribute calculating this attribute.In one embodiment of the invention, in difference degree computing module 22, in attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.
First Weight Acquisition module 23, for according to difference degree in the attribute of all properties, calculates the first weight of each attribute.In one embodiment of the invention, in the first Weight Acquisition module 23, in the attribute that the first weight of each attribute equals this attribute, difference degree is divided by difference degree summation in the attribute of all properties.
Second Weight Acquisition module 24, for carry out semantic analysis to the preservation data in advance about object, obtains the second weight of each attribute.
Comprehensive ratio acquisition module 25, for according to the first weight of each attribute and the second weight, calculates the comprehensive weight of each attribute.In one embodiment of the invention, in comprehensive weight acquisition module 25: the comprehensive weight of attribute equals the arithmetical mean of the second weight of the first weight and this attribute.
Select output module 26 for making a choice according to the comprehensive weight of each attribute and export selected results.
In sum, object properties and aggreggate utility connect by technical scheme of the present invention, take into account preservation data in advance simultaneously and carry out semantic analysis result, finally obtain the comprehensive weight of different object properties and make a policy accordingly, avoid error that artificial judgment Importance of Attributes brings and out-of-date, have simple, just objective, can the advantage such as real-time update.
Above-mentioned embodiment, does not form limiting the scope of the invention.It is to be understood that depend on designing requirement and other factors, various amendment, combination, sub-portfolio can be there is and substitute in those skilled in the art.Any amendment done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within scope.
Claims (10)
1. a method for alternative attribute, is characterized in that, comprising:
Set up the associating system of equations of object attribute values combination and aggreggate utility, solve the utilization coefficient that described associating system of equations obtains different attribute value;
By comparing the utilization coefficient of the different attribute value in same alike result, difference degree in the attribute calculating this attribute;
According to difference degree in the described attribute of all properties, calculate the first weight of each attribute;
Preservation data in advance about described object carry out semantic analyses, obtains the second weight of each attribute;
According to described first weight and described second weight of each attribute, calculate the comprehensive weight of each attribute;
Make a choice and export selected results according to the comprehensive weight of each attribute described.
2. method according to claim 1, it is characterized in that, the general formula of the single associating equation in described associating system of equations is: Y=∑ VX, wherein, Y represents the aggreggate utility that object attribute values combines, V represents the utilization coefficient of each property value, and X represents whether each property value occurs in described object attribute values combination.
3. method according to claim 1, is characterized in that, in described attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.
4. method according to claim 1, is characterized in that, in the described attribute that described first weight of each attribute equals this attribute, difference degree is divided by difference degree summation in the described attribute of all properties.
5. method according to claim 1, is characterized in that, the described comprehensive weight of attribute equals the arithmetical mean of described second weight of described first weight and this attribute.
6. a device for alternative attribute, is characterized in that, comprising:
Utilization coefficient computing module, for setting up the associating system of equations of object attribute values combination and aggreggate utility, solves the utilization coefficient that described associating system of equations obtains different attribute value;
Difference degree computing module, for the utilization coefficient by comparing the different attribute value in same alike result, difference degree in the attribute calculating this attribute;
First Weight Acquisition module, for according to difference degree in the described attribute of all properties, calculates the first weight of each attribute;
Second Weight Acquisition module, for carry out semantic analysis to the preservation data in advance about described object, obtains the second weight of each attribute;
Comprehensive ratio acquisition module, for according to described first weight of each attribute and described second weight, calculates the comprehensive weight of each attribute;
Select output module, for making a choice according to the comprehensive weight of each attribute described and export selected results.
7. device according to claim 6, it is characterized in that, in described utilization coefficient computing module, the general formula of the single associating equation in described associating system of equations is: Y=∑ VX, wherein, Y represents the aggreggate utility that object attribute values combines, and V represents the utilization coefficient of each property value, and X represents whether each property value occurs in described object attribute values combination.
8. device according to claim 6, is characterized in that, in described difference degree computing module, in described attribute, difference degree equals the difference of maximum utility coefficient in the utilization coefficient of the different attribute value in this attribute and minimum utilization coefficient.
9. device according to claim 6, is characterized in that, in described first Weight Acquisition module, in the described attribute that described first weight of each attribute equals this attribute, difference degree is divided by difference degree summation in the described attribute of all properties.
10. device according to claim 6, is characterized in that, in described comprehensive weight acquisition module, the described comprehensive weight of attribute equals the arithmetical mean of described second weight of described first weight and this attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510298581.6A CN104899766A (en) | 2015-06-03 | 2015-06-03 | Method and device for selecting object attributes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510298581.6A CN104899766A (en) | 2015-06-03 | 2015-06-03 | Method and device for selecting object attributes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104899766A true CN104899766A (en) | 2015-09-09 |
Family
ID=54032415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510298581.6A Pending CN104899766A (en) | 2015-06-03 | 2015-06-03 | Method and device for selecting object attributes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104899766A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993617A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system and computer-readable medium |
| CN116883414A (en) * | 2023-09-08 | 2023-10-13 | 国网上海市电力公司 | Multi-system data selection method and system suitable for operation and maintenance of power transmission line |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| CN103778553A (en) * | 2012-10-26 | 2014-05-07 | 腾讯科技（深圳）有限公司 | Commodity attribute recommendation method and commodity attribute recommendation system |
| CN103793388A (en) * | 2012-10-29 | 2014-05-14 | 阿里巴巴集团控股有限公司 | Method and device for search result sorting |
-
2015
- 2015-06-03 CN CN201510298581.6A patent/CN104899766A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| CN103778553A (en) * | 2012-10-26 | 2014-05-07 | 腾讯科技（深圳）有限公司 | Commodity attribute recommendation method and commodity attribute recommendation system |
| CN103793388A (en) * | 2012-10-29 | 2014-05-14 | 阿里巴巴集团控股有限公司 | Method and device for search result sorting |
Non-Patent Citations (2)
| Title |
|---|
| 叶小青: "联合分析在手机新产品开发上的应用研究", 《中南民族大学学报（自然科学版）》 * |
| 王崤: "商品关键属性抽取系统的设计与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993617A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system and computer-readable medium |
| CN116883414A (en) * | 2023-09-08 | 2023-10-13 | 国网上海市电力公司 | Multi-system data selection method and system suitable for operation and maintenance of power transmission line |
| CN116883414B (en) * | 2023-09-08 | 2024-01-26 | 国网上海市电力公司 | Multi-system data selection method and system suitable for operation and maintenance of power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11315164B2 (en) | Complementary product recommendation systems | |
| Dunford et al. | The pareto principle | |
| Enders et al. | Threshold cointegration and purchasing power parity in the pacific nations | |
| CN107436866A (en) | The recommendation method and device of finance product | |
| CN107329994A (en) | A kind of improvement collaborative filtering recommending method based on user characteristics | |
| CN105931066A (en) | Transaction data processing method and device | |
| CN108460618A (en) | A kind of resource allocation method and device, electronic equipment | |
| CN106651418A (en) | Method of recommending add-on item for special offer when spending enough by e-business | |
| CN106446189A (en) | Message-recommending method and system | |
| CN105468628B (en) | A kind of sort method and device | |
| CN109584016A (en) | A kind of Method of Commodity Recommendation | |
| Chen et al. | Optimal inventory control policy for periodic‐review inventory systems with inventory‐level‐dependent demand | |
| CN109213936A (en) | product search method and device | |
| Clements et al. | Quality, quantity, spending and prices | |
| CN105550901A (en) | Few user evaluations based goods popularity and preference combined prediction system | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN104899766A (en) | Method and device for selecting object attributes | |
| CN109858770A (en) | Object quality appraisal procedure and device | |
| Wang | Comments on operational competitiveness rating analysis (OCRA) | |
| CN112308662A (en) | Evaluation order recommendation method and device | |
| CN111783417A (en) | Article content scoring method and device | |
| CN109767333A (en) | Select based method, device, electronic equipment and computer readable storage medium | |
| CN108038735A (en) | Data creation method and device | |
| CN108681947A (en) | The collaborative filtering recommending method of association in time degree and coverage based on article | |
| Atukeren et al. | An analysis of the price dynamics between the Turkish and the international paintings markets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150909 |
|
| RJ01 | Rejection of invention patent application after publication |