CN107944032A - Method and apparatus for generating information - Google Patents

Abstract

The embodiment of the present application discloses the method and apparatus for generating information.One embodiment of this method includes：Obtain article to be excavated；Using at least two Topics Crawling modes, the theme of at least two types of the article to be excavated is excavated, and determines to excavate the degree of association of theme and the article to be excavated；Based on excavated theme and the identified degree of association, the theme and the degree of association of the article to be excavated and theme of the article to be excavated are determined.The embodiment realizes from different dimensions and the theme of article to be excavated is excavated, with obtain more comprehensively, theme exactly.

Description

Method and apparatus for generating information

technical field

The embodiments of the present application relate to the field of computer technology, specifically to the field of Internet technology, and in particular to a method and device for generating information.

Background technique

At this stage, the Internet is an important way for people to obtain information. In order to accurately recommend articles of interest to users, it is necessary to accurately understand the topic of the article and calculate the degree of relevance between the article and the topic. At present, the topic of an article can be generated by extracting keywords from an article. For example, firstly, the full text of the article is segmented to obtain a word set; afterward, the word set is filtered, word frequency is calculated, etc., and the keywords in the obtained word set are Words are the result of article topic mining, and the accuracy of this topic mining method is easily affected by factors such as word segmentation and aliases. At present, it is also possible to generate the topic of an article by means of article topic classification. For example, extracting word vector features from sentences in an article and performing article classification to obtain article topics. Using this topic mining method for topic mining is easily limited by the set of candidate topics. , for example, if the set of candidate topics used for classification is small and the candidate topics are relatively broad, then the scope of topic mining will be limited, and articles cannot be comprehensively and accurately expressed.

Contents of the invention

The embodiments of the present application propose a method and an apparatus for generating information.

In the first aspect, the embodiment of the present application provides a method for generating information, including: obtaining articles to be mined; using at least two topic mining methods to mine at least two types of topics in the articles to be mined, and determining the Mining the degree of relevance between the topic and the article to be mined; based on the mined theme and the determined degree of association, determine the theme of the article to be mined and the degree of association between the article to be mined and the theme.

In some embodiments, using at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determining the degree of relevance between the topics to be mined and the above-mentioned articles to be mined, including: Named entity recognition, determining whether the above-mentioned article to be mined includes at least one first-type article topic based on the named-entity recognition result; in response to determining that the above-mentioned article to be mined includes at least one first-type article topic, determining whether the above-mentioned article to be mined and the above-mentioned at least one first-type article topic The first correlation degree of each first-type article topic in the first-type article topic.

In some embodiments, performing named entity recognition on the article to be mined, and determining whether the article to be mined includes at least one first-type article topic based on the named entity recognition result includes: performing named entity recognition on the article to be mined, and determining the above Whether the article to be mined contains at least one named entity; in response to determining that the article to be mined contains at least one named entity, matching each named entity in the at least one named entity with candidate topics in the pre-established candidate topic set, Determine whether the above-mentioned article to be mined includes at least one candidate topic according to the matching result, wherein the above-mentioned candidate topic set is constructed based on a knowledge map; in response to determining that the above-mentioned article to be mined includes at least one candidate topic, for the above-mentioned at least one candidate topic For each candidate topic, count the frequency of occurrence of the candidate topic in the above-mentioned article to be mined, if the frequency of the candidate topic in the above-mentioned article to be mined exceeds the preset first threshold, then determine that the candidate topic is the above-mentioned to-be-mined article The first type of article topic for mining articles.

In some embodiments, in response to determining that the article to be mined includes at least one first-type article topic, determining a first degree of association between the to-be-mined article and each first-type article topic in the at least one first-type article topic, Including: for each of the first-type article topics in the above-mentioned at least one first-type article topic, count the frequency of the first-type article topic appearing in the above-mentioned article to be mined, and determine the relationship between the above-mentioned article to be mined and the article to be mined according to the frequency obtained by statistics. The first relevance degree of the subject of the first type of article.

In some embodiments, counting the frequency of occurrence of the candidate topic in the article to be mined includes: determining whether the alias of the candidate topic is included in the article to be mined according to the knowledge map; in response to determining that the article to be mined contains the alias The alias of the candidate topic, counting the first frequency of the alias of the candidate topic appearing in the above-mentioned article to be mined; counting the second frequency of the candidate topic appearing in the above-mentioned article to be mined; calculating the difference between the above-mentioned first frequency and the above-mentioned second frequency and, take the calculation result as the frequency of occurrence of the candidate topic in the above articles to be mined.

In some embodiments, using at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determining the degree of relevance between the topics to be mined and the above-mentioned articles to be mined, including: determining the above-mentioned articles to be mined Whether the source confidence of the source information exceeds a preset confidence threshold, wherein the source confidence of the source information of the article to be mined is obtained from a preset source information and source confidence relationship table, the source information The source information and the source confidence are stored corresponding to the source confidence relationship table; in response to determining that the source confidence of the source information of the article to be mined exceeds a preset confidence threshold, the source information of the article to be mined is used as the second type article subject, and use the source confidence degree of the source information of the article to be mined as the second correlation degree between the article to be mined and the subject of the second type article.

In some embodiments, using at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determining the degree of relevance between the topics to be mined and the above-mentioned articles to be mined, including: Word segmentation processing to obtain at least one word segmentation; import the above-mentioned at least one word segmentation into a pre-established topic classification model, and obtain the probability that the above-mentioned article to be mined belongs to each third type candidate article topic in the preset third type candidate article topic collection; based on the above The probability that the articles to be mined belong to each third type of candidate article topics in the subject set of the third type of candidate articles mentioned above determines the third type of article topics of the articles to be mined, and the third relationship between the above articles to be mined and the determined third type of article topics Correlation.

In some embodiments, the above topic classification model is a deep neural network; and the above method also includes the step of establishing the above deep neural network, including: performing word segmentation processing on the sample article to obtain at least one sample word segmentation; performing at least one sample word segmentation The filtering process obtains the sample word segmentation set of the above sample article; the above sample word segmentation set is used as an input, and the preset theme of the above sample article is used as an output, and the initial deep neural network is trained to obtain the above deep neural network.

In some embodiments, based on the mined topic and the determined association degree, determining the topic of the article to be mined and the degree of association between the article to be mined and the topic includes: when the mined topic includes at least two types of topics, for For each type of topic in the above at least two types of topics, normalize the degree of association between the article to be mined and the type of topic, and perform weighting processing on the normalized degree of association.

In some embodiments, the above method further includes: pushing the above-mentioned to-be-mined article in response to determining that the target keyword matches the topic of the above-mentioned to-be-mined article.

In the second aspect, the embodiment of the present application provides a device for generating information, including: an acquisition unit, used to acquire articles to be mined; a mining unit, used to mine the above-mentioned articles to be mined by using at least two topic mining methods At least two types of topics, and determine the degree of relevance between the mined topic and the above-mentioned article to be mined; the determination unit is used to determine the topic of the above-mentioned article to be mined and the above-mentioned article to be mined and relevance of the topic.

In some embodiments, the mining unit includes: an identification subunit, configured to perform named entity recognition on the article to be mined, and determine whether the article to be mined includes at least one first type of article subject based on the named entity recognition result; the first determination A subunit, configured to, in response to determining that the article to be mined includes at least one first-type article topic, determine a first degree of association between the above-mentioned article to be mined and each first-type article topic in the at least one first-type article topic.

In some embodiments, the recognition subunit includes: a recognition and determination unit, configured to perform named entity recognition on the article to be mined, to determine whether the article to be mined contains at least one named entity; a matching and determination unit, for responding After determining that at least one named entity is contained in the above-mentioned article to be mined, each named entity in the above-mentioned at least one named entity is matched with candidate topics in a pre-established candidate topic collection, and it is determined whether the above-mentioned article to be mined includes at least A candidate topic, wherein the set of candidate topics is constructed based on a knowledge map; the statistics and determination unit is configured to respond to determining that at least one candidate topic is included in the above-mentioned article to be mined, for each candidate topic in the at least one candidate topic , counting the frequency of occurrence of the candidate topic in the above-mentioned article to be mined, if the frequency of the candidate topic in the above-mentioned article to be mined exceeds the preset first threshold, then determine that the candidate topic is the first in the above-mentioned article to be mined Type article topic.

In some embodiments, the above-mentioned first determining subunit is further configured to: for each first-type article topic in the above-mentioned at least one first-type article topic, count the occurrence of the first-type article topic in the above-mentioned articles to be mined Frequency, determining the first degree of association between the article to be mined and the subject of the first type of article according to the frequency obtained through statistics.

In some embodiments, the statistics and determination unit is further configured to: determine whether the alias of the candidate topic is included in the article to be mined according to the knowledge map; in response to determining that the alias of the candidate topic is included in the article to be mined, count the The first frequency that the alias of the candidate topic appears in the above-mentioned article to be mined; count the second frequency of the candidate topic in the above-mentioned article to be mined; calculate the sum of the above-mentioned first frequency and the above-mentioned second frequency, and use the calculation result as the Frequency of candidate topics appearing in the above articles to be mined.

In some embodiments, the mining unit is further configured to: determine whether the source confidence of the source information of the article to be mined exceeds a preset confidence threshold, wherein the source confidence of the source information of the article to be mined is obtained from Acquired from the preset source information and source confidence relationship table, the source information and source confidence relationship table correspondingly stores source information and source confidence; Pre-set confidence threshold, the source information of the above-mentioned article to be mined is used as the second type of article topic, and the source confidence of the source information of the above-mentioned article to be mined is used as the first between the above-mentioned article to be mined and the topic of the second type of article Two degrees of relevance.

In some embodiments, the mining unit is further configured to: perform word segmentation processing on the article to be mined to obtain at least one word; import the at least one word into a pre-established topic classification model to obtain that the article to be mined belongs to the preset first The probability of each third type of candidate article topic in the three types of candidate article topic collection; determine the third type of the above-mentioned article to be mined based on the probability that the above-mentioned article to be mined belongs to each third type of candidate article topic in the above-mentioned third type candidate article topic collection The subject of the article, and the third correlation degree between the article to be mined and the determined subject of the third type of article.

In some embodiments, the above-mentioned subject classification model is a deep neural network; and the above-mentioned device further includes a training unit, and the above-mentioned training unit is used to: perform word segmentation processing on the sample article to obtain at least one sample word; filter the above-mentioned at least one sample word Process to obtain the sample word segmentation set of the above sample article; use the above sample word segmentation set as input, and use the preset theme of the above sample article as output, train the initial deep neural network, and obtain the above deep neural network.

In some embodiments, the determination unit is further configured to: when the topic to be mined includes at least two types of topics, for each type of topic in the above-mentioned at least two types of topics, combine the above-mentioned article to be mined with the type The correlation degree of the topic is normalized, and the normalized correlation degree is weighted.

In some embodiments, the above-mentioned apparatus further includes: a push unit, configured to push the above-mentioned to-be-mined article in response to determining that the target keyword matches the subject of the above-mentioned to-be-mined article.

In a third aspect, the embodiment of the present application provides a server, the server includes: one or more processors; a storage device for storing one or more programs, when the above one or more programs are When the processor executes, the above-mentioned one or more processors are made to implement the method described in any implementation manner of the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

The method and device for generating information provided by the embodiments of the present application first obtains the articles to be mined, and then utilizes at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determines that the topics to be mined are related to the above-mentioned The correlation degree of the articles to be mined, and finally based on the mined topics and the determined correlations, determine the topics of the above-mentioned articles to be mined and the correlation between the above-mentioned articles to be mined and the topics, so as to realize the mining of the topics of the excavated articles from different dimensions , to obtain a more comprehensive and accurate subject.

Description of drawings

Other characteristics, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;

Figure 2 is a flowchart of one embodiment of a method for generating information according to the present application;

Fig. 3 is a partial structural diagram of the knowledge map used in this application;

FIG. 4 is a schematic diagram of an application scenario of a method for generating information according to the present application;

FIG. 5 is a flowchart of another embodiment of a method for generating information according to the present application;

Fig. 6 is a schematic structural diagram of an embodiment of a device for generating information according to the present application;

FIG. 7 is a schematic structural diagram of a computer system suitable for implementing the server of the embodiment of the present application.

Detailed ways

The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

FIG. 1 shows an exemplary system architecture 100 to which embodiments of the method for generating information or the apparatus for generating information of the present application can be applied.

As shown in FIG. 1 , a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. Various client applications may be installed on the terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, and the like.

The terminal devices 101, 102, 103 may be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, laptop computers, desktop computers and so on.

Server 105 may be a server that provides various services, such as a background server that performs topic mining on articles to be mined. The relevance of the mined topics.

It should be noted that the method for generating information provided in the embodiment of the present application is generally executed by the server 105 , and correspondingly, the device for generating information is generally disposed in the server 105 .

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

Continue referring to FIG. 2 , which shows a flow 200 of an embodiment of a method for generating information according to the present application. The method for generating information includes the following steps:

Step 201, obtaining articles to be mined.

In this embodiment, the electronic device on which the method for generating information runs (such as the server 105 shown in FIG. 1 ) can obtain articles to be mined from the Internet in various ways (for example, crawling by using a web crawler) , here, the above-mentioned article to be mined may be an article in text form, for example, it may be a text article including title, content and other parts.

Step 202, using at least two topic mining methods to mine at least two types of topics in the articles to be mined, and determine the degree of relevance between the topics to be mined and the articles to be mined.

In this embodiment, the above-mentioned electronic device can use at least two topic mining methods to mine at least two types of topics in the articles to be mined, and determine the degree of relevance between the topics to be mined and the articles to be mined. Here, the above-mentioned electronic device can Mining the subject of the article to be mined in various ways, for example, the subject of the article can be generated by extracting keywords from the article, and for example, the keywords in the title of the article to be mined can be extracted as the subject of the article to be mined.

In some optional implementations of this embodiment, the above step 202 may specifically include: first, the above-mentioned electronic device may perform named entity recognition on the above-mentioned article to be mined, and determine whether the above-mentioned article to be mined includes at least one The first type of article theme, as an example, the above-mentioned electronic device can perform named entity recognition on the above-mentioned article to be mined, and according to the named entity recognition, it can be judged whether the above-mentioned article to be mined includes one or more named entities (for example, person name, institution name, place name, book name, etc.), if the above-mentioned article to be mined includes one or more named entities, then this one or more named entities can be used as the first type of article subject of the above-mentioned article to be mined. Afterwards, in response to determining that the article to be mined includes at least one first-type article topic, the electronic device may determine a first degree of association between the above-mentioned article to be mined and each first-type article topic in the at least one first-type article topic, as For example, corresponding to each first-type article topic in the above-mentioned at least one first-type article topic, the above-mentioned electronic device may determine the first-type article according to the position where the first-type article topic first appears in the above-mentioned article to be mined The first degree of association between the topic and the above-mentioned article to be mined, for example, can be set to be higher in the front where it appears, the higher the first degree of association.

In some optional implementation manners, performing named entity recognition on the article to be mined, and determining whether the article to be mined includes at least one first-type article topic based on the named entity recognition result may specifically include: first, the electronic device may Perform named entity recognition on the article to be mined, and determine whether the article to be mined contains at least one named entity. Then, in response to determining that the article to be mined contains at least one named entity, the electronic device may match each named entity in the at least one named entity with candidate topics in a pre-established candidate topic set, and determine the above-mentioned Whether at least one candidate topic is included in the article to be mined, for example, for each named entity in at least one named entity, the above-mentioned electronic device can compare the named entity with each candidate topic in the above-mentioned candidate topic set, if the named entity and If one of the candidate topics in the above-mentioned candidate topic set is the same, it can be determined that the above-mentioned article to be mined includes a candidate topic in the above-mentioned candidate topic set that is the same as the named entity. Here, the above-mentioned candidate topic set can be constructed based on a knowledge map As shown in Figure 3, it shows a schematic structural diagram of a certain part of the knowledge graph. In Figure 3, characters, works, locations, values, heights, etc. are used as nodes in the knowledge graph. Through the knowledge graph, the above-mentioned electronic devices can Knowing more information about the named entity (for example, the alias of the named entity, the upper and lower relationships, related entities/concepts, etc.), a more comprehensive and accurate set of candidate topics can be obtained through the knowledge graph. Finally, in response to determining that the article to be mined includes at least one candidate topic, for each candidate topic in the at least one candidate topic, the electronic device may count the frequency of occurrence of the candidate topic in the article to be mined, that is, the number of times, If the frequency of occurrence of the candidate topic in the article to be mined exceeds the preset first threshold, it can be determined that the candidate topic is the first type of article topic of the article to be mined. Here, the first threshold can be based on In fact, manual setting is required.

In some optional implementation manners, in response to determining that the article to be mined includes at least one article topic of the first type, determine whether the article to be mined and the first type of article topic among the at least one article topic of the first type The degree of relevance may specifically include: for each first-type article topic in the above-mentioned at least one first-type article topic, the above-mentioned electronic device may count the frequency of occurrence of the first-type article topic in the above-mentioned article to be mined, and obtain according to the statistics The frequency determines the first degree of association between the article to be mined and the subject of the first type of article. For example, for a certain first type of article topic, the number of times it appears in the above-mentioned article to be mined can be directly or indirectly (for example, the calculation result obtained by multiplying the number of occurrences by the preset weight) as the first type of article topic and The first relevance degree of the above articles to be mined.

Optionally, the counting of the frequency of occurrence of the candidate topic in the article to be mined may specifically include: first, the above-mentioned electronic device may determine whether the alias of the candidate topic is included in the article to be mined according to the above-mentioned knowledge map, for example, according to The knowledge map can determine that the alias of "Peking University" is "Peking University". Then, in response to determining that the alias of the candidate topic is included in the article to be mined, the electronic device may first count the first frequency of the alias of the candidate topic appearing in the article to be mined; The second frequency that appears in the article; finally, calculate the sum of the above-mentioned first frequency and the above-mentioned second frequency, and use the calculation result as the frequency that the candidate topic appears in the above-mentioned article to be mined.

In some optional implementations of this embodiment, the above step 202 may also specifically include: first, the above electronic device may determine whether the source confidence of the source information of the article to be mined exceeds a preset confidence threshold, where , the source confidence of the source information of the article to be mined may be obtained from a preset source information and source confidence relationship table, and the source information and source confidence relationship table stores the source information and the source confidence correspondingly, As an example, the above-mentioned electronic device may first obtain source information of the above-mentioned article to be mined, such as the author of the above-mentioned article to be mined, the media account and website that published the above-mentioned article to be mined, and so on. After that, the source information of the article to be mined can be matched with the source information in the source confidence relationship table, so as to obtain the source confidence of the source information of the article to be mined. Here, in the source information and source confidence relationship table, the source confidence of the source information can be determined in various ways, for example, when the above-mentioned source information is a media number used to release information, the source of the media number Confidence can be set according to factors such as the topic concentration, quality, and originality of the historically released information. For example, it can be set that the more concentrated the topic of the historically released information, the higher the source confidence, and the quality of the historically released information can also be set ( For example, it can be determined by reading volume, click volume, subscription volume, etc.) The higher the source, the higher the confidence. Then, in response to determining that the source confidence of the source information of the article to be mined exceeds a preset confidence threshold, the electronic device may use the source information of the article to be mined as the subject of the second type of article, and may use the source information of the article to be mined The source confidence degree of the source information of the article is used as the second correlation degree between the article to be mined and the subject of the second type of article.

In some optional implementations of this embodiment, the above step 202 may also specifically include: first, the above-mentioned electronic device may perform word segmentation processing on the above-mentioned article to be mined to obtain at least one word segmentation; The pre-established topic classification model obtains the probability that the above-mentioned article to be mined belongs to each third-type candidate article topic in the preset third-type candidate article topic set. Here, the above-mentioned third-type candidate article topic set can be based on the above-mentioned knowledge The network is established, for example, the above-mentioned electronic device can extract the abstract concepts in the above-mentioned knowledge network as the third type of candidate article topics, for example, words such as "constellation", "language", "car" and "variety show" can be extracted as the third type Type candidate article topic. It should be noted that the above topic classification model can be used to characterize the corresponding relationship between word segmentation sets and topic classification results. A correspondence table storing correspondences between multiple word segmentation sets and subject classification results. Finally, based on the probability that the article to be mined belongs to each of the third type candidate article topics in the third type candidate article topic set, the third type article subject of the above article to be mined is determined, and the relationship between the above article to be mined and the determined third type article The third degree of relevance of the topic, as an example, the electronic device can determine whether the probability that the article to be mined belongs to a third type of candidate article topic exceeds a preset probability threshold, and if it exceeds, the third type of candidate article can be determined The subject is the third type of article subject of the article to be mined. In addition, the electronic device may also use the probability that the article to be mined belongs to the subject of the third type of candidate article as the third relationship between the article to be mined and the subject of the third type of article. Correlation.

In some optional implementations, the subject classification model above may be a deep neural network; and the above method for generating information may also include the step of establishing the above deep neural network, specifically may include: first, the above electronic device or other The electronic device for training the above-mentioned deep neural network can perform word segmentation processing on sample articles to obtain at least one sample word segment. After that, the at least one sample word segmentation can be filtered to obtain the sample word segmentation set of the sample article, for example, the at least one sample word segmentation can be filtered to remove some punctuation marks, stop words, etc. in the at least one sample word segmentation Wait. Finally, the above-mentioned sample word segmentation set can be used as input, and the preset theme of the above-mentioned sample articles can be used as output to train the initial deep neural network to obtain the above-mentioned deep neural network. Here, the above-mentioned initial deep neural network can be obtained in various ways The obtained initial deep neural network, for example, based on the existing deep neural network, randomly generates the network parameters of the neural network to obtain the deep neural network. As an example, the above-mentioned initial deep neural network may include a convolutional neural network and a fully connected layer, and the specific training process of the above-mentioned deep neural network may include: first, the sample word segmentation set may be input into the convolutional neural network to obtain the characteristics of the sample word segmentation set Afterwards, the feature vector of the sample word segmentation set can be input to the fully connected layer to obtain the predicted probability that the sample article belongs to each third-type candidate article subject in the third-type candidate article subject set, and the sample article belongs to the third-type candidate article subject set The predicted probability of each third type of candidate article topic in the topic set and the topic of the preset sample article (here, it can be assumed that the probability that the sample article belongs to the topic of the preset sample article is 100%, and the probability of belonging to the topic except the preset topic The probability of other topics other than 0) is compared to obtain the prediction accuracy of the initial deep neural network. If the prediction accuracy is greater than the preset accuracy threshold, the initial deep neural network can be used as the trained deep neural network . If the prediction accuracy is less than the preset accuracy threshold, the network parameters of the initial deep neural network are adjusted. It should be noted that the training process of the above-mentioned deep neural network is only used to illustrate the adjustment process of the deep neural network parameters. It can be considered that the initial deep neural network is the network before parameter adjustment, and the deep neural network is the network after parameter adjustment. The adjustment process is not limited to one time, and can be repeated many times according to the optimization degree of the network and actual needs.

Step 203, based on the mined topic and the determined correlation degree, determine the topic of the article to be mined and the correlation degree between the article to be mined and the topic.

In this embodiment, the above-mentioned electronic device may determine the subject of the above-mentioned article to be mined and the degree of relevance between the above-mentioned article to be mined and the topic based on the mined topic and the determined degree of association. All or part of the subject as the subject to be excavated above. For another example, for a certain type of topic, the electronic device may increase the degree of relevance between this type of topic and the above-mentioned article to be mined in various ways (for example, adding a preset value to the degree of relevance).

In some optional implementations of this embodiment, the above step 203 may specifically include: when the mined topic includes at least two types of topics, for each type of topic in the above-mentioned at least two types of topics, the above-mentioned The electronic device may perform normalization processing on the degree of association between the article to be mined and the topic of this type, and perform weighting processing on the normalized degree of association. Generally, the degree of relevance between the mined topics determined by different topic mining methods and the above-mentioned articles to be mined will be distributed in different numerical intervals. Between [0,100], the degree of association between the mined topic and the above-mentioned articles to be mined determined by the second method may be distributed between the digital interval [0,1], therefore, for the convenience of comparison, the determined association degree can be normalized Processing, so that the mined topics determined by different topic mining methods and the above-mentioned articles to be mined are distributed in the same numerical range. In addition, weighting can also be performed on the normalized association degree. For example, for a topic mining method with a good mining effect, the mined value determined by the topic mining method can be increased by weighting (such as multiplying a certain value). The degree of relevance between the topic and the above articles to be mined.

Continue referring to FIG. 4 , which is a schematic diagram of an application scenario of the method for generating information according to this embodiment. In the application scenario of Fig. 4, server 401 acquires an article about actor A and actor B's quarrel through website A as an article to be mined; after that, server 401 can use at least two topic mining methods to mine at least Two types of topics, for example, dig out the topics "Actor A", "Actor B", etc. of the named entity class, and dig out the topics "quarrel", "hype", etc. of the abstract concept class, and determine the topics to be mined degree of association with the article to be mined; finally, the server 401 can determine the subject of the article to be mined and the degree of association between the article to be mined and the topic based on the mined topic and the determined association degree, for example, the server can mine the All or part of the topic is used as the topic of the topic to be mined.

The method provided by the above-mentioned embodiments of the present application uses at least two topic mining methods to mine at least two types of topics in the articles to be mined, and determines the degree of relevance between the topics to be mined and the articles to be mined, thereby realizing mining from different dimensions The topic of the article is mined to obtain a more comprehensive and accurate topic.

Further referring to FIG. 5 , it shows a flow 500 of still another embodiment of a method for generating information. The flow 500 of the method for generating information includes the following steps:

Step 501, obtaining articles to be mined.

In this embodiment, the electronic device on which the method for generating information runs (for example, the server 105 shown in FIG. 1 ) can acquire articles to be mined from the Internet in various ways.

Step 502, using at least two topic mining methods to mine at least two types of topics in the articles to be mined, and determine the degree of relevance between the topics to be mined and the articles to be mined.

In this embodiment, based on the articles to be mined obtained in step 501, the above-mentioned electronic device can use at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determine the relationship between the topics to be mined and the above-mentioned articles to be mined. degree of relevance.

Step 503, based on the mined topic and the determined correlation degree, determine the topic of the article to be mined and the correlation degree between the article to be mined and the topic.

In this embodiment, the above-mentioned electronic device may determine the topic of the article to be mined and the degree of association between the article to be mined and the topic based on the mined topic and the determined correlation degree.

Step 504, pushing the article to be mined in response to determining that the target keyword matches the subject of the article to be mined.

In this embodiment, the electronic device may match the target keyword with the topic of the article to be mined determined in step 503, for example, may compare the target keyword with the topic of the article to be mined determined in step 503 , if the target keyword is the same as a topic of the article to be mined determined in step 503, and the correlation between the topic and the article to be mined is greater than a preset push threshold, then it can be determined that the target keyword is related to the article to be mined Themes match. In response to determining that the target keyword matches the topic of the article to be mined, the electronic device may push the article to be mined, for example, the electronic device may push the article to be mined to the terminal sending the target keyword. Here, the target keyword may be extracted from the search information sent by the user through the terminal, for example, the user sends the search information "star chapter XX" through the terminal, and the electronic device may extract "chapter XX" as the target keyword. In addition, the above-mentioned target keywords may be keywords obtained based on user portraits. For example, if the user portrait of a certain user shows that the user is a fan of "star Li XX", the above-mentioned electronic device may use "Li XX" as the target keyword .

It can be seen from FIG. 5 that, compared with the embodiment corresponding to FIG. 2 , the process 500 of the method for generating information in this embodiment highlights the step of pushing articles to be mined. Therefore, the solution described in this embodiment can effectively utilize the determined subject of the article to be mined and the degree of association between the article to be mined and the subject, thereby realizing more accurate information push.

Further referring to FIG. 6 , as an implementation of the methods shown in the above figures, the present application provides an embodiment of a device for generating information. This device embodiment corresponds to the method embodiment shown in FIG. 2 , the The device can be specifically applied to various electronic devices.

As shown in FIG. 6 , the apparatus 600 for generating information in this embodiment includes: an acquiring unit 601 , a mining unit 602 and a determining unit 603 . Wherein, the obtaining unit 601 is used to obtain articles to be mined; the mining unit 602 is used to use at least two topic mining methods to mine at least two types of topics of the above-mentioned articles to be mined, and determine the association between the topics to be mined and the above-mentioned articles to be mined degree; the determining unit 603 is configured to determine the topic of the article to be mined and the degree of association between the article to be mined and the topic based on the mined topic and the determined association degree.

In this embodiment, the specific processing of the acquiring unit 601, the mining unit 602, and the determining unit 603 of the apparatus 600 for generating information and the technical effects brought about by them can refer to step 201 and step 202 in the corresponding embodiment of FIG. 2 respectively. The related description of step 203 will not be repeated here.

In some optional implementations of this embodiment, the above-mentioned mining unit 602 includes: an identification subunit (not shown in the figure), configured to perform named entity recognition on the above-mentioned articles to be mined, and determine the above-mentioned articles to be mined based on the named entity recognition results Whether the excavated article includes at least one first type of article subject; the first determination subunit (not shown in the figure) is used for determining that the above-mentioned article to be mined is related to the above-mentioned The first degree of relevance of each first-type article topic in at least one first-type article topic.

In some optional implementations of this embodiment, the recognition subunit includes: a recognition and determination unit (not shown in the figure), configured to perform named entity recognition on the article to be mined, and determine whether the article to be mined is Contains at least one named entity; a matching and determining unit (not shown in the figure), configured to match each named entity in the at least one named entity with a pre-established candidate in response to determining that the article to be mined contains at least one named entity The candidate topics in the topic collection are matched, and it is determined whether at least one candidate topic is included in the above-mentioned article to be mined according to the matching result, wherein, the above-mentioned candidate topic collection is constructed based on a knowledge map; a statistical and determination unit (not shown in the figure), In response to determining that the above-mentioned article to be mined includes at least one candidate topic, for each candidate topic in the above-mentioned at least one candidate topic, count the frequency of occurrence of the candidate topic in the above-mentioned article to be mined, if the candidate topic is in the above-mentioned to-be-mined If the frequency of occurrences in the mined articles exceeds the preset first threshold, the candidate topic is determined to be the first type of article topic of the above-mentioned articles to be mined.

In some optional implementations of this embodiment, the above-mentioned first determining subunit is further configured to: for each first-type article topic in the above-mentioned at least one first-type article topic, count the first-type article topics in The frequency of appearance of the article to be mined is determined according to the frequency obtained by statistics, and the first correlation degree between the article to be mined and the subject of the first type of article is determined.

In some optional implementations of this embodiment, the statistics and determination unit is further configured to: determine whether the alias of the candidate topic is included in the article to be mined according to the knowledge map; The alias of the candidate topic, counting the first frequency of the alias of the candidate topic appearing in the above-mentioned article to be mined; counting the second frequency of the candidate topic appearing in the above-mentioned article to be mined; calculating the difference between the above-mentioned first frequency and the above-mentioned second frequency and, take the calculation result as the frequency of occurrence of the candidate topic in the above articles to be mined.

In some optional implementations of this embodiment, the mining unit 602 is further configured to: determine whether the source confidence of the source information of the article to be mined exceeds a preset confidence threshold, wherein the source information of the article to be mined The source confidence of the source information is obtained from the preset source information and source confidence relationship table, and the above source information and source confidence relationship table correspondingly stores the source information and source confidence; in response to determining the above-mentioned article to be mined If the source confidence of the source information exceeds the preset confidence threshold, the source information of the above-mentioned article to be mined is taken as the second type of article topic, and the source confidence of the source information of the above-mentioned article to be mined is used as the source information of the above-mentioned article to be mined and A second degree of relevance to the subject of the second type of article above.

In some optional implementations of this embodiment, the mining unit 602 is further configured to: perform word segmentation on the article to be mined to obtain at least one word; import the at least one word into a pre-established topic classification model to obtain The probability that the article to be mined belongs to each third-type candidate article topic in the preset third-type candidate article topic set; is determined based on the probability that the above-mentioned article to be mined belongs to each third-type candidate article topic in the third-type candidate article topic set A third type of article topic of the article to be mined, and a third correlation degree between the above article to be mined and the determined third type of article topic.

In some optional implementations of this embodiment, the above-mentioned topic classification model is a deep neural network; and the above-mentioned device further includes a training unit (not shown in the figure), and the above-mentioned training unit is used to: perform word segmentation processing on sample articles, Obtain at least one sample word; filter the at least one sample word to obtain a sample word set of the sample article; use the above sample word set as input, and use the preset theme of the above sample article as output to train the initial deep neural network , to obtain the above deep neural network.

In some optional implementations of this embodiment, the determination unit 603 is further configured to: when the mined topics include at least two types of topics, for each type of topic in the at least two types of topics, Perform normalization processing on the degree of association between the above-mentioned articles to be mined and the topic of this type, and perform weighting processing on the degree of association after normalization processing.

In some optional implementations of this embodiment, the above-mentioned device 600 further includes: a push unit (not shown in the figure), configured to push the above-mentioned to-be-mined article.

Referring now to FIG. 7 , it shows a schematic structural diagram of a computer system 700 suitable for implementing the server of the embodiment of the present application. The server shown in FIG. 7 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

As shown in FIG. 7 , a computer system 700 includes a central processing unit (CPU, Central Processing Unit) 701, which can be randomly accessed according to a program stored in a read-only memory (ROM, Read Only Memory) 702 or loaded from a storage section 706 Various appropriate actions and processes are executed by programs stored in random access memory (RAM) 703 . In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701 , ROM 702 , and RAM 703 are connected to each other via a bus 704 . An input/output (I/O, Input/Output) interface 705 is also connected to the bus 704 .

The following components are connected to the I/O interface 705: a storage section 5706 including a hard disk and the like; and a communication section 707 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 707 performs communication processing via a network such as the Internet. A drive 708 is also connected to the I/O interface 705 as necessary. A removable medium 709 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 708 as necessary so that a computer program read therefrom is installed into the storage section 706 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 707 and/or installed from removable media 709 . When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the method of the present application are performed. It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present application may be implemented by means of software or by means of hardware. The described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a mining unit, and a determination unit. Wherein, the names of these units do not limit the unit itself under certain circumstances, for example, the obtaining unit may also be described as "a unit for obtaining articles to be mined".

As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the device described in the above embodiments, or it may exist independently without being assembled into the device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the device, the device: acquires articles to be mined; uses at least two topic mining methods to mine the content of the articles to be mined at least two types of topics, and determine the degree of association between the mined topic and the article to be mined; based on the mined topic and the determined association degree, determine the topic of the article to be mined and the relationship between the article to be mined and the topic Correlation.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover the technical solutions formed by the above-mentioned technical features or without departing from the above-mentioned inventive concept. Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.

Claims (22)

1. a kind of method for generating information, including：

Obtain article to be excavated；

Using at least two Topics Crawling modes, the theme of at least two types of the article to be excavated is excavated, and determines institute Excavate the degree of association of theme and the article to be excavated；

Based on excavated theme and the identified degree of association, the theme of the article to be excavated and the article to be excavated are determined With the degree of association of theme.

2. it is described to utilize at least two Topics Crawling modes according to the method described in claim 1, wherein, wait to dig described in excavation The theme of at least two types of article is dug, and determines to excavate the degree of association of theme and the article to be excavated, including：

Entity recognition is named to the article to be excavated, determines that the article to be excavated is based on name Entity recognition result It is no including at least one first kind article theme；

In response to determine the article to be excavated include at least one first kind article theme, determine the article to be excavated and First degree of association of each first kind article theme at least one first kind article theme.

3. according to the method described in claim 2, wherein, Entity recognition is named to the article to be excavated, based on name Entity recognition result determines whether the article to be excavated includes at least one first kind article theme, including：

Entity recognition is named to the article to be excavated, determines whether include at least one name in the article to be excavated Entity；

In response to determining to include at least one name entity in the article to be excavated, by least one name entity Each name entity is matched with the candidate topics in the candidate topics set pre-established, according to determining matching result Whether include at least one candidate topics in article to be excavated, wherein, the candidate topics set is knowledge based map construction 's；

In response to determining that the article to be excavated includes at least one candidate topics, at least one candidate topics Each candidate topics, the frequency that the candidate topics occur in the article to be excavated is counted, if the candidate topics exist The frequency occurred in the article to be excavated exceedes first threshold set in advance, it is determined that the candidate topics are described to be excavated The first kind article theme of article.

It is described in response to determining that the article to be excavated includes at least one the 4. according to the method described in claim 3, wherein One types of articles theme, determines the article to be excavated and each first kind at least one first kind article theme First degree of association of article theme, including：

For each first kind article theme at least one first kind article theme, the first kind is counted The frequency that article theme occurs in the article to be excavated, the frequency obtained according to statistics determine the article to be excavated with being somebody's turn to do First degree of association of first kind article theme.

5. according to the method described in claim 4, wherein, count the frequency that the candidate topics occur in the article to be excavated It is secondary, including：

Determine the alias of the candidate topics whether is included in the article to be excavated according to the knowledge mapping；

In response to the alias for determining to include the candidate topics in the article to be excavated, the alias of the candidate topics is counted described First frequency occurred in article to be excavated；

Count second frequency that the candidate topics occur in the article to be excavated；

The sum of first frequency and second frequency are calculated, using result of calculation as the candidate topics in the text to be excavated The frequency occurred in chapter.

6. it is described to utilize at least two Topics Crawling modes according to the method described in claim 1, wherein, wait to dig described in excavation The theme of at least two types of article is dug, and determines to excavate the degree of association of theme and the article to be excavated, including：

Determine the source-information of the article to be excavated comes whether source confidence exceedes confidence threshold value set in advance, its In, the source confidence that comes of the source-information of the article to be excavated is from source-information set in advance and carrys out source confidence relation Obtained in table, the source-information is corresponding with carrying out source confidence relation table to be stored with source-information and carry out source confidence；

The source confidence that comes of source-information in response to determining the article to be excavated exceedes confidence threshold value set in advance, will The source-information of the article to be excavated comes as Second Type article theme, and by the source-information of the article to be excavated Second degree of association of the source confidence as the article to be excavated and the Second Type article theme.

7. it is described to utilize at least two Topics Crawling modes according to the method described in claim 1, wherein, wait to dig described in excavation The theme of at least two types of article is dug, and determines to excavate the degree of association of theme and the article to be excavated, including：

Word segmentation processing is carried out to the article to be excavated, obtains at least one participle；

At least one participle is imported into the subject classification model that pre-establishes, show that the article to be excavated belongs to default the The probability of each 3rd type candidate article theme in three type candidate article theme set；

Each 3rd type candidate article master in the 3rd type candidate article theme set is belonged to based on the article to be excavated 3rd types of articles theme of article to be excavated described in the determine the probability of topic, and the article to be excavated and definite three classes 3rd degree of association of type article theme.

8. according to the method described in claim 7, wherein, the subject classification model is deep neural network；And

The method further includes the step of establishing the deep neural network, including：

Word segmentation processing is carried out to sample article, obtains at least one sample participle；

Filtration treatment is carried out at least one sample participle and obtains the sample participle set of the sample article；

Using sample participle set as input, using the theme of the sample article set in advance as output, training is just Beginning deep neural network, obtains the deep neural network.

9. according to the method described in claim 1, wherein, based on excavated theme and the identified degree of association, determine described treat The theme and the degree of association of the article to be excavated and theme of article are excavated, including：

When excavated theme includes the theme of at least two types, for each in the theme of at least two type The theme of type, the degree of association of the article to be excavated and the theme of the type is normalized, and to normalization at The degree of association after reason is weighted processing.

10. according to the method described in claim 1, wherein, the method further includes：

In response to determining that target keyword is matched with the theme of the article to be excavated, the article to be excavated is pushed.

11. a kind of device for being used to generate information, including：

Acquiring unit, for obtaining article to be excavated；

Unit is excavated, for utilizing at least two Topics Crawling modes, excavates at least two types of the article to be excavated Theme, and determine to excavate the degree of association of theme and the article to be excavated；

Determination unit, for based on excavated theme and the identified degree of association, determine the article to be excavated theme and The degree of association of the article to be excavated and theme.

12. according to the devices described in claim 11, wherein, the excavation unit includes：

Identify subelement, for being named Entity recognition to the article to be excavated, determined based on name Entity recognition result Whether the article to be excavated includes at least one first kind article theme；

First determination subelement, for including at least one first kind article theme in response to the definite article to be excavated, Determine the first of the article to be excavated and each first kind article theme at least one first kind article theme The degree of association.

13. device according to claim 12, wherein, the identification subelement includes：

Identification and determination unit, for being named Entity recognition to the article to be excavated, determine in the article to be excavated Whether at least one name entity is included；

Matching and determination unit, in response to determining include at least one name entity in the article to be excavated, described in general Each name entity at least one name entity is matched with the candidate topics in the candidate topics set pre-established, Determine whether include at least one candidate topics in the article to be excavated according to matching result, wherein, the candidate topics collection Conjunction is knowledge based map construction；

Statistics and determination unit, for including at least one candidate topics in response to the definite article to be excavated, for institute Each candidate topics at least one candidate topics are stated, count the frequency that the candidate topics occur in the article to be excavated It is secondary, if the frequency that the candidate topics occur in the article to be excavated exceedes first threshold set in advance, it is determined that should Candidate topics are the first kind article theme of the article to be excavated.

14. device according to claim 13, wherein, first determination subelement is further used for：

For each first kind article theme at least one first kind article theme, the first kind is counted The frequency that article theme occurs in the article to be excavated, the frequency obtained according to statistics determine the article to be excavated with being somebody's turn to do First degree of association of first kind article theme.

15. device according to claim 14, wherein, the statistics and determination unit are further used for：

Determine the alias of the candidate topics whether is included in the article to be excavated according to the knowledge mapping；

In response to the alias for determining to include the candidate topics in the article to be excavated, the alias of the candidate topics is counted described First frequency occurred in article to be excavated；

Count second frequency that the candidate topics occur in the article to be excavated；

The sum of first frequency and second frequency are calculated, using result of calculation as the candidate topics in the text to be excavated The frequency occurred in chapter.

16. according to the devices described in claim 11, wherein, the excavation unit is further used for：

Determine the source-information of the article to be excavated comes whether source confidence exceedes confidence threshold value set in advance, its In, the source confidence that comes of the source-information of the article to be excavated is from source-information set in advance and carrys out source confidence relation Obtained in table, the source-information is corresponding with carrying out source confidence relation table to be stored with source-information and carry out source confidence；

The source confidence that comes of source-information in response to determining the article to be excavated exceedes confidence threshold value set in advance, will The source-information of the article to be excavated comes as Second Type article theme, and by the source-information of the article to be excavated Second degree of association of the source confidence as the article to be excavated and the Second Type article theme.

17. according to the devices described in claim 11, wherein, the excavation unit is further used for：

Word segmentation processing is carried out to the article to be excavated, obtains at least one participle；

At least one participle is imported into the subject classification model that pre-establishes, show that the article to be excavated belongs to default the The probability of each 3rd type candidate article theme in three type candidate article theme set；

Each 3rd type candidate article master in the 3rd type candidate article theme set is belonged to based on the article to be excavated 3rd types of articles theme of article to be excavated described in the determine the probability of topic, and the article to be excavated and definite three classes 3rd degree of association of type article theme.

18. device according to claim 17, wherein, the subject classification model is deep neural network；And

Described device further includes training unit, and the training unit is used for：

Word segmentation processing is carried out to sample article, obtains at least one sample participle；

Filtration treatment is carried out at least one sample participle and obtains the sample participle set of the sample article；

Using sample participle set as input, using the theme of the sample article set in advance as output, training is just Beginning deep neural network, obtains the deep neural network.

19. according to the devices described in claim 11, wherein, the determination unit is further used for：

When excavated theme includes the theme of at least two types, for each in the theme of at least two type The theme of type, the degree of association of the article to be excavated and the theme of the type is normalized, and to normalization at The degree of association after reason is weighted processing.

20. device according to claim 19, wherein, described device further includes：

Push unit, in response to determining that target keyword is matched with the theme of the article to be excavated, waiting to dig described in push Dig article.

21. a kind of server, including：

One or more processors；

Storage device, for storing one or more programs,

When one or more of programs are performed by one or more of processors so that one or more of processors Realize the method as described in any in claim 1-10.

22. a kind of computer-readable recording medium, is stored thereon with computer program, wherein, the computer program is by processor The method as described in any in claim 1-10 is realized during execution.