CN102456056B - Information output method and information output device - Google Patents
Information output method and information output device Download PDFInfo
- Publication number
- CN102456056B CN102456056B CN 201010529404 CN201010529404A CN102456056B CN 102456056 B CN102456056 B CN 102456056B CN 201010529404 CN201010529404 CN 201010529404 CN 201010529404 A CN201010529404 A CN 201010529404A CN 102456056 B CN102456056 B CN 102456056B
- Authority
- CN
- China
- Prior art keywords
- information
- parameter
- integrity degree
- value
- output
- 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.)
- Active
Links
Images
Abstract
The embodiment of the invention discloses an information output method and an information output device. The method comprises the following steps of: before outputting information, calculating integrity score of the output information; comparing the calculated integrity score of the to-be output information with a set integrity standard value; if the calculated integrity score is not less than the integrity standard value, outputting the to-be output information to a webpage by scheduling an interface layer, otherwise, refusing to output the information. According to the embodiment of the invention, the utilization rate of a network system can be improved, and system resource of a searching engine server or a recommendation engine server can be saved.
Description
Technical field
The application relates to communication and field of computer technology, particularly relates to a kind of information output method and device.
Background technology
No matter in search engine, still in recommended engine, the various information via searching algorithms of storing in database or the processing of proposed algorithm, and after the filtration of business rules such as fatigue strength filtration and the filtration of commodity support, by direct calling interface layer, the information that obtains after finally filtering is outputed to the WEB page, to represent mentioned above searching results or recommendation results at the WEB page.See also Fig. 1, the synoptic diagram that it is handled information for recommended engine in the prior art.As shown in Figure 1, the information after recommended engine filters business rule has been pushed directly to the WEB page by interface layer.
Information usually can appear in the Search Results that represents at the WEB page or recommendation results does not have corresponding picture, information is described problems such as too simple and partial information disappearance, has had a strong impact on the integrality of Search Results or recommendation results.Obviously, Search Results or the recommendation results that integrality is not high is invalid information for the user.When the not high invalid information of more integrality occurring in Search Results or recommendation results, search engine or recommended engine need be handled more information again could obtain certain effective information, and this process may be repeated multiple times sometimes.
In the process of search engine or recommended engine repeated multiple times ground process information, will certainly increase the load of network system, particularly search engine server or recommended engine server, reduced the utilization factor of network system.Simultaneously, also increased the consumption of search procedure for search engine server, perhaps recommendation process has been wasted the system resource of search engine server or recommended engine server for the consumption of recommended engine server.
Summary of the invention
In order to solve the problems of the technologies described above, the embodiment of the present application provides a kind of information output method and device, with the utilization factor of raising network system, and the system resource of saving search engine server or recommended engine server.
The embodiment of the present application discloses following technical scheme:
A kind of information output method comprises: before output information, calculate the integrity degree fractional value for the treatment of output information; The integrity degree fractional value for the treatment of output information that calculates and the integrity degree standard value of setting are compared; When the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
Preferably, described calculating treats that the integrity degree fractional value of output information comprises: choose the parameter that the output information integrity degree is treated in reflection; The parameter of choosing is carried out normalized; And, calculate the weight of the parameter of choosing according to principal component analysis (PCA); According to the weight that calculates, the parameter value after the normalized is weighted summation, obtain treating the integrity degree fractional value of output information.
Preferably, described method also comprises: before weighted sum, with the parameter of choosing be assigned to title be correlated with, fill in integrity degree relevant with information count any one or any a plurality of combination in relevant three parameter group; Calculate the importance scores together value of each parameter group according to principal component analysis (PCA); Abandon weight less than the parameter of default minimum threshold; The weight that calculates of described basis then, parameter value after the normalized is weighted summation, obtain treating that the integrity degree fractional value of output information specifically comprises: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
Preferably, described parameter comprises any one or any a plurality of combination in the matching degree of the consistance of the degree of piling up of word number that information attribute fills in rate, transaction attribute and fill in the picture size of picture number, the information of rate, information, message header, message header, number of words that outline information is described, number of words, message header and key word that information is described in detail and information and place classification.
Preferably, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, in the degree of piling up of message header and the consistance of message header and key word any one or any a plurality of combination, the described integrity degree correlation parameter group of filling in comprises that information attribute fills in rate, the transaction attribute is filled in any one or any a plurality of combination in the picture number of rate and information, and the described information correlation parameter group of counting comprises the picture size of information, in the number of words that the number of words that informative abstract is described and information are described in detail any one or any a plurality of combination.
A kind of information output apparatus comprises: computing module is used for calculating the integrity degree fractional value for the treatment of output information before output information; Comparison module compares the integrity degree fractional value for the treatment of output information that calculates and the integrity degree standard value of setting; Output module when the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
Preferably, described computing module comprises: the chooser module is used for choosing the parameter that the output information integrity degree is treated in reflection; The normalization submodule is used for the parameter of choosing is carried out normalized; The weight calculation submodule is for the weight that calculates the parameter of choosing according to principal component analysis (PCA); The weighted sum submodule is used for according to the weight that calculates the parameter value after the normalized being weighted summation, obtains treating the integrity degree fractional value of output information.
Preferably, described device also comprises: the classification submodule, be used for before weighted sum, with the parameter of choosing be assigned to title be correlated with, fill in integrity degree relevant with information count any one or any a plurality of combination in relevant three parameter group; Importance scores together value calculating sub module is for the importance scores together value that calculates each parameter group according to principal component analysis (PCA); Abandon submodule, be used for abandoning weight less than the parameter of default minimum threshold; Then described weighted sum submodule is specially: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
Preferably, described parameter comprises any one or any a plurality of combination in the matching degree of the consistance of the degree of piling up of word number that information attribute fills in rate, transaction attribute and fill in the picture size of picture number, the information of rate, information, message header, message header, number of words that outline information is described, number of words, message header and key word that information is described in detail and information and place classification.
Preferably, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, in the degree of piling up of message header and the consistance of message header and key word any one or any a plurality of combination, the described integrity degree correlation parameter group of filling in comprises that information attribute fills in rate, the transaction attribute is filled in any one or any a plurality of combination in the picture number of rate and information, and the described information correlation parameter group of counting comprises the picture size of information, in the number of words that the number of words that informative abstract is described and information are described in detail any one or any a plurality of combination.
As can be seen from the above-described embodiment, before output information, calculate each earlier and treat the integrity degree fractional value of output information, treat according to the integrity degree fractional value judgement that calculates whether the integrity degree of output information meets standard, if meet standard, output information is treated in output, otherwise, do not export and treat output information.Therefore, guarantee the Search Results of each output or the integrality of recommendation results, made search engine or recommended engine handle less information and can obtain effective information, reduced the quantity of search engine or recommended engine process information, therefore, improved the utilization factor of network system.Simultaneously, owing to reduced the quantity of search engine or recommended engine process information, correspondingly also reduced the consumption of search procedure for search engine server, perhaps reduced the consumption of search procedure for search engine server, the system resource of having saved search engine server or recommended engine server.
Description of drawings
In order to be illustrated more clearly in the embodiment of the present application or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
The synoptic diagram that Fig. 1 handles information for recommended engine in the prior art;
Fig. 2 is the process flow diagram of an embodiment of a kind of information output method of the application;
Fig. 3 is the process flow diagram of another embodiment of a kind of information output method of the application;
Fig. 4 is the structural representation of a kind of information output apparatus of the application;
Fig. 5 is a structural representation of the application's computing module;
Fig. 6 is another structural representation of the application's computing module.
Embodiment
In the embodiment of the present application, with the precondition of the integrity degree degree of the information output information as whether, only export the satisfactory information of integrity degree degree.Namely, when the integrity degree fractional value of information to be exported is greater than or equal to the integrity degree standard value of setting, the integrity degree degree of descriptive information meets the requirements, to treat that output information outputs to Webpage, if the integrity degree fractional value of information to be exported is less than the integrity degree standard value that arranges, the integrity degree degree of descriptive information is undesirable, then output information not.
For above-mentioned purpose, the feature and advantage that make the application can become apparent more, below in conjunction with accompanying drawing the embodiment of the present application is described in detail.
Embodiment one
See also Fig. 2, it is the process flow diagram of an embodiment of a kind of information output method of the application, and this method may further comprise the steps:
Step 201: before output information, calculate the integrity degree fractional value for the treatment of output information;
For example, in search engine, through after the search 1 information A to be exported being arranged, before output information A any one constantly, as, canned data carries out searching algorithm when handling in database, for search engine, this moment, processed information was information to be exported, and calculated the integrity degree fractional value of each processed information, perhaps, when information being carried out the business rule filtration, for search engine, the information that be filtered this moment is information to be exported, calculate the integrity degree fractional value that each is filtered information, again or, after the information after obtaining business rule and filtering, for search engine, information after filter this moment is information to be exported, and calculates the integrity degree fractional value of the information after filtering.
Wherein, described calculating treats that the integrity degree fractional value of output information comprises: choose the parameter that the output information integrity degree is treated in reflection; The parameter of choosing is carried out normalized; And, calculate the weight of the parameter of choosing according to principal component analysis (PCA); According to the weight that calculates, the parameter value after the normalized is weighted summation, obtain treating the integrity degree fractional value of output information.
For example, according to the content of the information in search engine or the recommended engine, choose the parameter that the output information integrity degree is treated in reflection.Preferably, through after choosing, this parameter comprises any one or any a plurality of combination in the matching degree of the consistance of the degree of piling up of word number that information attribute fills in rate, transaction attribute and fill in the picture size of the picture number of rate, information, information, message header, message header, number of words that outline information is described, number of words, message header and key word that information is described in detail and information and place classification.Wherein, the information attribute rate of filling in is that product attribute is filled in number and product attribute is filled in total ratio, and the attribute of concluding the business is filled in rate and filled in the ratio of counting and concluding the business the attribute sum for the transaction attribute.Above-mentioned each parameter only is the explanation of the application's illustrative, and concrete parameter can be selected according to actual conditions, and the application does not limit this.
After the process above-mentioned parameter is chosen, respectively selected parameter is carried out normalized, and, according to the weight of the selected parameter of principal component analysis (PCA) calculating.Wherein, the normalized value=x of each parameter
n/ Max (x
n), x
nParameter value for selected parameter.In addition, present embodiment can be calculated the weight of selected parameter by R software by principal component analysis (PCA).List the weighted value corresponding tables of each parameter that calculates below.Wherein, the sign in the weighted value is represented the correlativity of corresponding parameters and information completely degree, and weighted value is for just representing parameter and the positive correlation of information completely degree, and weighted value is negative indication parameter and information completely degree negative correlation.
| Parameter name | The correlativity of parameter and information completely degree | Weight |
| The matching degree of information and place classification | Negative correlation | -0.0000000398 |
| The word number of message header | Positive correlation | 0.246224339 |
| The degree of piling up of message header | Negative correlation | -0.025809714 |
| The consistance of title and key word | Positive correlation | 0.968869152 |
| Information attribute is filled in rate | Positive correlation | 0.378990038 |
| The transaction attribute is filled in rate | Positive correlation | 0.626758808 |
| The picture number of information | Positive correlation | 0.680837681 |
| The picture size of information | Positive correlation | 0.148349219 |
| The number of words that outline information is described | Positive correlation | 0.893119786 |
| The number of words that information is described in detail | Positive correlation | 0.449818905 |
After the normalized parameter value and weight of the parameter that has obtained to choose, the parameter value after the normalized is weighted summation, obtain treating the integrity degree fractional value of output information.That is y ≈ a,
1x
1+ a
2x
2...+a
nx
n, wherein, a is the weight of selected parameter, and x is the normalized parameter value of selected parameter, and y is the integrity degree fractional value of information.
When the normalized parameter value that obtains selected parameter, and after the weight of selected parameter, except directly being weighted summation, obtain treating outside the integrity degree fractional value of output information, can also abandon the less one or more not too important parameters of integrity degree influence to information earlier, then the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
Then described method also comprises: before weighted sum, the parameter of choosing is assigned to title is correlated with, fills in that integrity degree is relevant counts in relevant three parameter group with information; Calculate the importance scores together value of each parameter group according to principal component analysis (PCA); Abandon weight less than the parameter of default minimum threshold;
The weight that calculates of described basis then, parameter value after the normalized is weighted summation, obtain treating that the integrity degree fractional value of output information specifically comprises: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
For example, before weighted sum, earlier the parameter of choosing is assigned to title and is correlated with, fills in that integrity degree is relevant counts in relevant three parameter group with information.Preferably, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, the degree of piling up of message header and the consistance of message header and key word, the described integrity degree correlation parameter group of filling in comprises that information attribute is filled in rate, the transaction attribute is filled in the picture number of rate and information, the described information number of words that the correlation parameter group comprises that the picture size of information, number of words that informative abstract is described and information are described in detail of counting.Calculate the importance scores together value of each parameter group then according to principal component analysis (PCA), abandon weight less than the parameter of default minimum threshold.For example, Yu She minimum threshold is 0.01.This less one or more not too important parameters of integrity degree influence that abandon earlier information, and then the parameter value that is not dropped is weighted summation, obtain treating the method for the integrity degree fractional value of output information, not only can improve the accuracy of information completely degree, also reduce the complexity of handling to a certain extent.
List below the parameter of choosing distributed after, importance scores together value and the result of each corresponding parameter group.As shown in the table, if default minimum threshold is 0.01, then therefore the weighted value of this parameter of matching degree of information and place classification, is dropped less than this minimum threshold.
At last, according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
Need to prove that the process that the parameter of choosing is classified is to finish before being weighted summation, that is, and itself and normalized process, and calculating parameter weight process does not have strict time order and function order.
Step 202: the integrity degree fractional value for the treatment of output information that will calculate and the integrity degree standard value of setting compare;
Wherein, the integrity degree standard value can be according to concrete application demand setting.For example, if the integrity degree of information of output is had relatively high expectations, higher integrity degree standard value can be set, otherwise, lower integrity degree standard value then is set.
Step 203: when the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
When the integrity degree fractional value for the treatment of output information that calculates is greater than or equal to the integrity degree standard value of setting, the integrity degree that information to be exported is described meets outputting standard, to treat that by the calling interface layer output information outputs to Webpage, otherwise, the integrity degree that information to be exported is described does not meet outputting standard, not output information.
As can be seen from the above-described embodiment, before output information, calculate each earlier and treat the integrity degree fractional value of output information, treat according to the integrity degree fractional value judgement that calculates whether the integrity degree of output information meets standard, if meet standard, output information is treated in output, otherwise, do not export and treat output information.Therefore, guarantee the Search Results of each output or the integrality of recommendation results, made search engine or recommended engine handle less information and can obtain effective information, reduced the quantity of search engine or recommended engine process information, therefore, improved the utilization factor of network system.Simultaneously, owing to reduced the quantity of search engine or recommended engine process information, correspondingly also reduced the consumption of search procedure for search engine server, perhaps reduced the consumption of search procedure for search engine server, the system resource of having saved search engine server or recommended engine server.In addition, because the non-compliant information of integrity degree is not carried out the network transmission, therefore, reduce data quantity transmitted in the network, improved the efficient of network transmission, avoided the generation of network blockage phenomenon.
Embodiment two
Describe an a kind of preferred implementation of information output method below in detail.See also Fig. 3, it is the process flow diagram of another embodiment of a kind of information output method of the application, said method comprising the steps of:
Step 301: choose the parameter that the output information integrity degree is treated in reflection;
The embodiment of the present application is that example is illustrated with the commodity displaying information of issuing in the e-commerce website, can comprise the various information contents in this commodity displaying information, as: message header, picture, outline information description, information detailed description, type of transaction, information attribute etc., the application does not limit this.Wherein, can select the parameter that some reflect this information completely degree according to the content of these commodity displaying information, the matching degree that described parameter can comprise the consistance of the degree of piling up of word number that information attribute fills in rate, transaction attribute and fill in the picture size of picture number, the information of rate, information, message header, message header, number of words that outline information is described, number of words, message header and key word that information is described in detail and information and place classification is totally 10 parameters.Above-mentioned each parameter only is the explanation of the application's illustrative, can the selecting according to actual conditions of concrete parameter, and the application does not limit this.
Step 302: the whole parameters that will choose are assigned to title and are correlated with, fill in that integrity degree is relevant counts in relevant three parameter group with information;
Wherein, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, the degree of piling up of message header and the consistance of message header and key word, the described integrity degree correlation parameter group of filling in comprises that information attribute is filled in rate, the transaction attribute is filled in the picture number of rate and information, the described information number of words that the correlation parameter group comprises that the picture size of information, number of words that informative abstract is described and information are described in detail of counting.Following table has shown the result after all parameters of choosing are distributed.
Step 303: the parameter value of each parameter is carried out normalized processing respectively;
Wherein, the normalized value=x of each parameter
n/ Max (x
n), x
nParameter value for selected parameter.
Step 304: according to principal component analysis (PCA), calculate the weight of each parameter and the importance scores together value of each parameter group;
Principal component analysis (PCA) is a kind of method of mathematic(al) manipulation, and it changes into another to one group of given correlated variables by linear transformation and organizes incoherent variable, and the order that these new variablees successively decrease successively according to variance is arranged.Keep the population variance of variable constant in mathematic(al) manipulation, make first variable have maximum variance, be called first principal component, the variance of second variable is inferior big, and uncorrelated with first variable, is called Second principal component.And the like, I variable just has I major component.Following table has shown through after the calculating of principal component analysis (PCA), the weight of each parameter, and the importance scores together value of each parameter group.
Step 305: abandon weight less than the parameter of default minimum threshold;
Need to prove, this integrity degree that abandons earlier information influences less one or more not too important parameters or has abandoned a unessential parameter that the integrity degree of information is influenced minimum, and then the parameter value that is not dropped is weighted summation, obtain treating the method for the integrity degree fractional value of output information, not only can improve the accuracy of information completely degree, also reduce the complexity of handling to a certain extent.
Step 306: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information;
Wherein, treat the integrity degree fractional value y ≈ a of output information
1x
1+ a
2x
2...+a
nx
n, wherein, a is the weight of selected parameter, and x is the normalized parameter value of selected parameter, and y is the integrity degree fractional value of information.
Step 307: the integrity degree fractional value for the treatment of output information that will calculate and the integrity degree standard value of setting compare;
Step 308: when the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
As can be seen from the above-described embodiment, before output information, calculate each earlier and treat the integrity degree fractional value of output information, treat according to the integrity degree fractional value judgement that calculates whether the integrity degree of output information meets standard, if meet standard, output information is treated in output, otherwise, do not export and treat output information.Therefore, guarantee the Search Results of each output or the integrality of recommendation results, made search engine or recommended engine handle less information and can obtain effective information, reduced the quantity of search engine or recommended engine process information, therefore, improved the utilization factor of network system.Simultaneously, owing to reduced the quantity of search engine or recommended engine process information, correspondingly also reduced the consumption of search procedure for search engine server, perhaps reduced the consumption of search procedure for search engine server, the system resource of having saved search engine server or recommended engine server.In addition, because the non-compliant information of integrity degree is not carried out the network transmission, therefore, reduce data quantity transmitted in the network, improved the efficient of network transmission, avoided the generation of network blockage phenomenon.
Embodiment three
Corresponding with above-mentioned a kind of information output method, the embodiment of the present application also provides a kind of information output apparatus.See also Fig. 4, it is the structural representation of an embodiment of a kind of information output apparatus of the application, comprising: computing module 401, comparison module 402 and output module 403.Principle of work below in conjunction with this device is further introduced its inner structure and annexation.
Preferably, see also Fig. 5, it is a structural representation of the application's computing module.Wherein, computing module 401 comprises: chooser module 4011, normalization submodule 4012, weight calculation submodule 4013 and weighted sum submodule 4014.
Preferably, see also Fig. 6, it is another structural representation of the application's computing module.Wherein, computing module 401 also comprises classification submodule 4015, importance scores together value calculating sub module 4016 and abandons submodule 4017 except comprising chooser module 4011, normalization submodule 4012, weight calculation submodule 4013 and weighted sum submodule 4014.
Importance scores together value calculating sub module 4016 is for the importance scores together value that calculates each parameter group according to principal component analysis (PCA);
Then weighted sum submodule 4014 is specially: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
The function of chooser module 4011 wherein, normalization submodule 4012 and weight calculation submodule 4013 can repeat no more referring to above-mentioned description herein.
Preferably, described parameter comprises any one or any a plurality of combination in the matching degree of the consistance of the degree of piling up of word number that information attribute fills in rate, transaction attribute and fill in the picture size of picture number, the information of rate, information, message header, message header, number of words that outline information is described, number of words, message header and key word that information is described in detail and information and place classification.
Preferably, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, the degree of piling up of message header and the consistance of message header and key word, the described integrity degree correlation parameter group of filling in comprises that information attribute is filled in rate, the transaction attribute is filled in the picture number of rate and information, the described information number of words that the correlation parameter group comprises that the picture size of information, number of words that informative abstract is described and information are described in detail of counting.
As can be seen from the above-described embodiment, before output information, calculate each earlier and treat the integrity degree fractional value of output information, treat according to the integrity degree fractional value judgement that calculates whether the integrity degree of output information meets standard, if meet standard, output information is treated in output, otherwise, do not export and treat output information.Therefore, guarantee the Search Results of each output or the integrality of recommendation results, made search engine or recommended engine handle less information and can obtain effective information, reduced the quantity of search engine or recommended engine process information, therefore, improved the utilization factor of network system.Simultaneously, owing to reduced the quantity of search engine or recommended engine process information, correspondingly also reduced the consumption of search procedure for search engine server, perhaps reduced the consumption of search procedure for search engine server, the system resource of having saved search engine server or recommended engine server.In addition, because the non-compliant information of integrity degree is not carried out the network transmission, therefore, reduce data quantity transmitted in the network, improved the efficient of network transmission, avoided the generation of network blockage phenomenon.
Need to prove, one of ordinary skill in the art will appreciate that all or part of flow process that realizes in above-described embodiment method, be to instruct relevant hardware to finish by computer program, described program can be stored in the computer read/write memory medium, this program can comprise the flow process as the embodiment of above-mentioned each side method when carrying out.Wherein, described storage medium can be magnetic disc, CD, read-only storage memory body (Read-Only Memory, ROM) or at random store memory body (Random AccessMemory, RAM) etc.
More than a kind of information output method and device that the application is provided be described in detail, used specific embodiment herein the application's principle and embodiment are set forth, the explanation of above embodiment just is used for helping to understand the application's method and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to the application's thought, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as the restriction to the application.
Claims (6)
1. an information output method is characterized in that, comprising:
Before output information, the integrity degree fractional value of output information is treated in calculating, wherein, described calculating treats that the integrity degree fractional value of output information comprises: choose the parameter that the output information integrity degree is treated in reflection, the parameter of choosing is carried out normalized, and calculate the weight of the parameter of choosing according to principal component analysis (PCA), according to the weight that calculates, parameter value after the normalized is weighted summation, obtain treating the integrity degree fractional value of output information, described parameter comprises that information attribute fills in rate, the transaction attribute is filled in rate, the picture number of information, the picture size of information, the word number of message header, the degree of piling up of message header, the number of words that outline information is described, the number of words that information is described in detail, in the matching degree of the consistance of message header and key word and information and place classification any one or any a plurality of combination;
The integrity degree fractional value for the treatment of output information that calculates and the integrity degree standard value of setting are compared;
When the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
2. method according to claim 1 is characterized in that, described method also comprises:
Before weighted sum, with the parameter of choosing be assigned to title be correlated with, fill in integrity degree relevant with information count any one or any a plurality of combination in relevant three parameter group;
Calculate the importance scores together value of each parameter group according to principal component analysis (PCA);
Abandon weight less than the parameter of default minimum threshold;
The weight that calculates of described basis then, parameter value after the normalized is weighted summation, obtain treating that the integrity degree fractional value of output information specifically comprises: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
3. method according to claim 1, it is characterized in that, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, in the degree of piling up of message header and the consistance of message header and key word any one or any a plurality of combination, the described integrity degree correlation parameter group of filling in comprises that information attribute fills in rate, the transaction attribute is filled in any one or any a plurality of combination in the picture number of rate and information, and the described information correlation parameter group of counting comprises the picture size of information, in the number of words that the number of words that informative abstract is described and information are described in detail any one or any a plurality of combination.
4. an information output apparatus is characterized in that, comprising:
Computing module, be used for before output information, the integrity degree fractional value of output information is treated in calculating, wherein, described computing module comprises: the chooser module, be used for choosing the parameter that the output information integrity degree is treated in reflection, the normalization submodule, be used for the parameter of choosing is carried out normalized, the weight calculation submodule, be used for calculating according to principal component analysis (PCA) the weight of the parameter of choosing, the weighted sum submodule, be used for according to the weight that calculates, parameter value after the normalized is weighted summation, obtain treating the integrity degree fractional value of output information, described parameter comprises that information attribute fills in rate, the transaction attribute is filled in rate, the picture number of information, the picture size of information, the word number of message header, the degree of piling up of message header, the number of words that outline information is described, the number of words that information is described in detail, in the matching degree of the consistance of message header and key word and information and place classification any one or any a plurality of combination;
Comparison module compares the integrity degree fractional value for the treatment of output information that calculates and the integrity degree standard value of setting;
Output module when the former is greater than or equal to the latter, will treat that by the calling interface layer output information outputs to Webpage, otherwise, output information not.
5. device according to claim 4 is characterized in that, described device also comprises:
The classification submodule was used for before weighted sum, with the parameter of choosing be assigned to title be correlated with, fill in integrity degree relevant with information count any one or any a plurality of combination in relevant three parameter group;
Importance scores together value calculating sub module is for the importance scores together value that calculates each parameter group according to principal component analysis (PCA);
Abandon submodule, be used for abandoning weight less than the parameter of default minimum threshold;
Then described weighted sum submodule is specially: according to the weight that calculates, to after the normalized, and the parameter value that is not dropped is weighted summation, obtains treating the integrity degree fractional value of output information.
6. device according to claim 4, it is characterized in that, described title correlation parameter group comprises the matching degree of information and place classification, the word number of message header, in the degree of piling up of message header and the consistance of message header and key word any one or any a plurality of combination, the described integrity degree correlation parameter group of filling in comprises that information attribute fills in rate, the transaction attribute is filled in any one or any a plurality of combination in the picture number of rate and information, and the described information correlation parameter group of counting comprises the picture size of information, in the number of words that the number of words that informative abstract is described and information are described in detail any one or any a plurality of combination.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010529404 CN102456056B (en) | 2010-11-01 | 2010-11-01 | Information output method and information output device |
| HK12106891.3A HK1166385A1 (en) | 2010-11-01 | 2012-07-13 | Method and apparatus for outputting information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010529404 CN102456056B (en) | 2010-11-01 | 2010-11-01 | Information output method and information output device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102456056A CN102456056A (en) | 2012-05-16 |
| CN102456056B true CN102456056B (en) | 2013-07-03 |
Family
ID=46039253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010529404 Active CN102456056B (en) | 2010-11-01 | 2010-11-01 | Information output method and information output device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102456056B (en) |
| HK (1) | HK1166385A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10846462B2 (en) * | 2013-05-29 | 2020-11-24 | Hewlett-Packard Development Company, L.P. | Web page output selection |
| CN106484747A (en) * | 2015-09-02 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind of webpage item recommendation method based on alternative events and device |
| CN106652419A (en) * | 2017-01-17 | 2017-05-10 | 西南科技大学 | Wireless monitoring network dynamic synchronous acquisition method based on comprehensive sensitive event driving |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001035315A2 (en) * | 1999-11-12 | 2001-05-17 | Webassured.Com | An on-line business performance indication system |
| CN1787631A (en) * | 2004-12-10 | 2006-06-14 | 阿尔卡特公司 | Distributive system for marking and blocking video and audio content |
| US7526678B2 (en) * | 2004-03-30 | 2009-04-28 | At&T Intellectual Property I, L.P. | Methods, systems, and products for verifying integrity of web-server served content |
| CN101702149A (en) * | 2009-11-12 | 2010-05-05 | 深圳市五巨科技有限公司 | Method for displaying electronic book with movable terminal and device thereof |
-
2010
- 2010-11-01 CN CN 201010529404 patent/CN102456056B/en active Active
-
2012
- 2012-07-13 HK HK12106891.3A patent/HK1166385A1/en not_active IP Right Cessation
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001035315A2 (en) * | 1999-11-12 | 2001-05-17 | Webassured.Com | An on-line business performance indication system |
| US7526678B2 (en) * | 2004-03-30 | 2009-04-28 | At&T Intellectual Property I, L.P. | Methods, systems, and products for verifying integrity of web-server served content |
| CN1787631A (en) * | 2004-12-10 | 2006-06-14 | 阿尔卡特公司 | Distributive system for marking and blocking video and audio content |
| CN101702149A (en) * | 2009-11-12 | 2010-05-05 | 深圳市五巨科技有限公司 | Method for displaying electronic book with movable terminal and device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102456056A (en) | 2012-05-16 |
| HK1166385A1 (en) | 2012-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gaspars-Wieloch | Project net present value estimation under uncertainty | |
| EP3279806A1 (en) | Data processing method and apparatus | |
| EP2581843A2 (en) | Bigram Suggestions | |
| CN107133865A (en) | A kind of acquisition of credit score, the output intent and its device of characteristic vector value | |
| EP3217296A1 (en) | Data query method and apparatus | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| CN111597348A (en) | User image drawing method, device, computer equipment and storage medium | |
| CN110347724A (en) | Abnormal behaviour recognition methods, device, electronic equipment and medium | |
| CN107273391A (en) | Document recommends method and apparatus | |
| CN102456056B (en) | Information output method and information output device | |
| WO2019085332A1 (en) | Financial data analysis method, application server, and computer readable storage medium | |
| CN103888543A (en) | Medical resource recommendation method and system based on Web services | |
| CN105243124A (en) | Resource combination processing method and apparatus | |
| CN110969172A (en) | Text classification method and related equipment | |
| CN107784027A (en) | A kind of reminding method and device of judgement document's search key | |
| US8682808B2 (en) | Method and apparatus for processing logistic information | |
| CN111951051B (en) | Method, device and system for recommending products to clients | |
| CN113362139A (en) | Data processing method and device based on double-tower structure model | |
| CN110347934B (en) | Text data filtering method, device and medium | |
| CN111611228A (en) | Load balance adjustment method and device based on distributed database | |
| CN114066310A (en) | Approval task allocation method and device, computer equipment and storage medium | |
| CN111966916A (en) | Recommendation method and device, electronic equipment and computer readable storage medium | |
| CN110322150A (en) | A kind of signal auditing method, device and server | |
| CN112765451A (en) | Client intelligent screening method and system based on ensemble learning algorithm | |
| CN114254624B (en) | Method and system for determining website type |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1166385 Country of ref document: HK |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |