JP4672578B2 - Interest information providing apparatus, interest information providing method, and interest information providing program - Google Patents

Description

The present invention relates to the interest information providing programs and Your interest information providing equipment, in particular, with reference to the blog entry, on the interest information of the individual is automatically generate conceptual layered personal ontology, individuals interested It is suitable for application to a method for providing unexpected information that has a high possibility of having

  In the conventional information providing method, as disclosed in Non-Patent Document 1, the hierarchical structure of bookmarks registered by individuals and folders held by individuals, and file information (words) stored in these bookmarks and folders, etc. Based on the correlation), a collaborative filtering technique is used to determine the opposing relationship of the interest bookmark page in the user set and to recommend personal interest information.

Here, in the collaborative filtering technique, the user's preference is recorded in the form of past behavior, and the user's preference is measured based on the preference information of the user who is taking a behavior similar to that user. This collaborative filtering technique is a typical technique used to provide a recommendation service, and more accurate information can be estimated when there is more preference information for each user and the number of users is larger.
Non-Patent Documents 2 and 3 disclose methods of measuring the degree of approximation between ontology and mapping between ontology.

Keisuke Sabota, Kenji Hatano, Jun Miyazaki, Toshiaki Uemura: Web page recommendation method by collaborative filtering considering bookmark hierarchy, Vol. 3, No. 1, DBSJ Letters (2004). Maedche, A .; and Staab, S .; : Measuring Similarity between Ontologies, In Technical Report, E0448, University of Karlsruhe (2001). Noy, N.A. F. and Musen, M .; A. : Anchor-PROMPT: Usage Non-Local Context for Semantic Matching, In Proceedings of the Workshop on Ontology and Information Sharing at the Int.

  However, in the method disclosed in Non-Patent Document 1, interest consistency between bookmark pages is determined using the hierarchical structure of the user, and only information belonging to a corresponding hierarchical level can be extracted. For the user, only the information that was taken for granted in the sense of belonging to the same class (concept) could be presented. For this reason, in the method disclosed in Non-Patent Document 1, although the possibility that the user is interested is statistically high, information that is unexpected for the user cannot be presented, and the user has not known so far. There was a problem of not being able to give the opportunity to expand the range of interest.

In addition, even the methods disclosed in Non-Patent Documents 2 and 3 are not in a correspondence relationship as a hierarchy, but it is not possible to present unexpected information that is statistically highly likely to be of interest to an individual. There was a problem that it was not possible to give an opportunity to expand the range of interest that I did not know.
An object of the present invention, individuals is to provide a possibility statistically higher surprising information capable of presenting interest information providing equipment Contact and interest information providing program interested.

In order to solve the above-described problem, the interest information providing apparatus of the present invention includes an approximation degree measuring unit that measures an approximation degree between ontologies for each user in which words are conceptually hierarchized, and the approximation degree is a predetermined value or more. Between the ontology, the unexpected information extracting means for extracting the class and instance included in one ontology but not including the other ontology among the classes or instances constituting the ontology as unexpected information; Unexpected information extraction means for presenting the unexpected information extracted by the unexpected information extraction means to a user holding an ontology that does not include the class and the instance extracted as the unexpected information, and the unexpected information presentation The means presents both the class extracted as the unexpected information and the instance belonging to the class to the user. It is characterized in.

  As a result, it is possible to receive information on classes or instances that are included in the ontology held by other users but are not included in the ontology held by the user, although the degree of approximation between the ontology is close. For this reason, although there is no correspondence as a class hierarchy, it is possible to receive unexpected information that an individual may be interested in, and it is possible to widen the range of interest that the user has not known before.

Further, the interest information providing apparatus of the present invention is configured such that the degree of approximation between an ontology for each user in which words are conceptually hierarchized and the degree of approximation between one ontology is not less than a predetermined value. In a common class that includes a common word in a class that constitutes the ontology and exists in both of the ontology and the one ontology, any one of the plurality of ontologies among the instances belonging to the common class Unexpected information extracted means for extracting an instance including a word that is included in the ontology but not included in the one ontology, and the unexpected information extracted by the unexpected information extraction means is used as the unexpected information. Unexpected information presenting means for presenting to a user holding the one ontology that does not include the extracted instance. The features.

Thus, despite the close similarity between ontologies, although other Yu chromatography The are included in the ontology to hold, you may receive information included not class or instance in ontology they hold . Therefore, although not in the correspondence as a class hierarchy, individuals can receive surprising information that might interested, it is possible to widen the interest which the user did not know until now.

Further, the interest information providing apparatus according to claim 1 includes: a word extracting unit that extracts words included in the interest information constructed for each individual; and a template ontology in which preset words are hierarchized in concept. Classifier application means for extracting a class or instance including a word extracted by the word extraction means, and a hierarchical structure including the extracted class or instance and higher classes thereof for each individual as the personal ontology. Personal ontology extracting means for extracting from the model ontology, approximation degree measuring means for measuring the degree of approximation between the personal ontology, and classes or instances constituting the personal ontology between personal ontologies where the degree of approximation is a predetermined value or more One of them is included in the personal ontology A class and an instance including a word that is not included in the personal ontology as unexpected information, and the unexpected information extracted by the unexpected information extraction means as the unexpected information. And an unexpected information presentation means for presenting to a user holding a personal ontology not including an instance,
The unexpected information presenting means presents both a class extracted as the unexpected information and an instance belonging to the class to the user.

  As a result, by comparing the words included in each individual's interest information on the template ontology, a personal ontology in which the personal interest information is conceptually hierarchized is automatically generated, and the degree of approximation between the personal ontologies is increased. Despite being close, it is possible to receive information on classes or instances that are included in the personal ontology held by other users but are not included in the personal ontology held by the user. For this reason, it is possible to generate personal ontology while suppressing the cost of creation, and to provide unexpected information that is not related as a class hierarchy but may be of interest to individuals Can do. As a result, it is possible to improve the accuracy of information retrieval, and to distribute the personal ontology of each individual widely on the Internet while enabling the range of interest that the user has not known before. Thus, it is possible to form a community that suits individual preferences.

Further, the interest information providing apparatus according to claim 2 includes: word extraction means for extracting words included in the interest information constructed for each individual; and a template ontology in which preset words are hierarchized in concept. Classifier application means for extracting a class or instance including a word extracted by the word extraction means, and a hierarchical structure including the extracted class or instance and higher classes thereof for each individual as the personal ontology. Personal ontology extracting means for extracting from a model ontology, approximation degree measuring means for measuring the degree of approximation between the personal ontology, a plurality of personal ontology in which the degree of approximation between one personal ontology is a predetermined value or more, and the The personal ontology that exists in one personal ontology In a common class in which a common word is included in a class, a word that is included in any one of the plurality of personal ontologies out of instances belonging to the common class but is not included in the one personal ontology A user who holds the one personal ontology that does not include the instance extracted as the unexpected information, and the unexpected information extracted by the unexpected information extraction unit. And an unexpected information presenting means for presenting the information.

The interest information providing apparatus according to claim 3 , wherein a morphological analysis is applied to the blog entry to extract a word included in the blog entry, and a preset word is hierarchized into a concept hierarchy. A model ontology selection means for selecting a model ontology, a classifier application means for extracting a class or an instance including a word extracted from the blog entry from the template ontology, and the extracted class for each user. Alternatively, a personal ontology extracting means for extracting a hierarchical structure including instances and their higher classes from the template ontology as a personal ontology, an approximation measuring means for measuring an approximation between the personal ontology, and the approximation is predetermined. Between the personal ontology above the value. Surprising information extraction means for extracting, as unexpected information, classes and instances that include words that are included in one personal ontology but not included in the other personal ontology, among the classes or instances constituting the sonality ontology, and the unexpected information Unexpected information extracted by the extracting means, and unexpected information presenting means for presenting to the user holding the personal ontology not including the class and instance extracted as the unexpected information, the unexpected information presenting means The class extracted as the unexpected information and the instances belonging to the class are both presented to the user.

Also, interest information providing apparatus according to claim 4, wherein, by applying the morphological analysis on a blog entry, a word extraction means for extracting words included in the blog entry, word concept hierarchical set in advance A model ontology selection means for selecting a model ontology, a classifier application means for extracting a class or an instance including a word extracted from the blog entry from the template ontology, and the extracted class for each user. Or a personal ontology extracting means for extracting a hierarchical structure including instances and their higher classes from the template ontology as a personal ontology, an approximation measuring means for measuring the degree of approximation between the personal ontology, and one personal ontology The degree of approximation between Any one of the plurality of personal ontology among instances belonging to the common class in a common class including a common word in a class constituting the personal ontology existing in the personal ontology and the one personal ontology Surprising information extracting means for extracting, as unexpected information, an instance including a word that is included in a plurality of personal ontologies but not in the one personal ontology, and the unexpected information extracted by the unexpected information extracting means, Surprising information presenting means for presenting to a user holding the one personal ontology that does not include the instance extracted as unexpected information.

The interest information providing apparatus according to claim 5 is extracted by the word extracting unit from a word extracting unit that extracts a word included in the blog entry and a template ontology in which preset words are hierarchized in concept. Classifier application means for extracting a class or instance including a word, and a personal ontology for extracting a hierarchical structure including the extracted class or instance and higher classes from the template ontology for each user as a personal ontology. Extraction means, approximation degree measurement means for measuring the degree of approximation between the personal ontology, and the blog entry having a word included in a class constituting the template ontology or an instance belonging to the class, the class ontology class or To instances belonging to the class For example, among the classes of the template ontology and the instances belonging to the class, the words included in the class or the instance corresponding to the classes and instances corresponding to the classes and instances constituting the personal ontology having the approximation degree equal to or greater than a predetermined value Included in one personal ontology among classes or instances constituting the personal ontology between the user number analyzing means for measuring the number of users including the blog entry and the personal ontology with the degree of approximation equal to or greater than a predetermined value. Is a class and an instance including a word not included in the other personal ontology, and a class and an instance having the number of users equal to or greater than a predetermined value are extracted as unexpected information, and extracted by the unexpected information extracting unit Is Unexpected information presenting means for presenting the unexpected information to a user having a personal ontology that does not include the class or instance extracted as the unexpected information, and the unexpected information presenting means is extracted as the unexpected information. The class and the instance belonging to the class are both presented to the user.

The interest information providing apparatus according to claim 6 , wherein the unexpected information presenting means belongs to the class having the highest concept in the hierarchical structure of the concept hierarchy among the classes extracted as the unexpected information. An instance or a class having the lowest concept and an instance belonging to the class are preferentially presented to the user.

  As described above, according to the present invention, it is possible to search for information suitable for one's preference with high accuracy, and to expand the range of interest that the user has not known before, It is possible to widely circulate information suitable for personal preferences on the Internet, and form a community adapted to personal preferences.

Hereinafter, an interest information providing apparatus and method according to an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a schematic configuration of a system to which an interest information providing apparatus according to an embodiment of the present invention is applied.
In FIG. 1, terminals 2 to 4 and a server 5 are connected via a communication network 1. As the communication network 1, for example, a public communication network that performs IP communication can be used, and the Internet may be used. Further, it may be a private communication network between companies or a public communication network, but it is like an IP-VPN (Internet Protocol-Virtual Private Network) that can provide dedicated communication with high reliability and security. A simple net may be used.

  Further, the terminals 2 to 4 may be a notebook personal computer or a desktop personal computer, and may be a mobile phone terminal or a PDA (Personal Data Assistant). The server 5 can be installed on a program provider or ISP (Information Service Provider).

  Here, the server 5 is provided with blog sites 7 to 9 corresponding to the terminals 2 to 4 respectively, and the blog entries 7a to 7n, 8a to 8n, and 9a to 9n are held in the blog sites 7 to 9, respectively. Has been. The blog entries 7a to 7n, 8a to 8n, and 9a to 9n represent minimum units of articles in the blog, and can be provided for each day. The server 5 holds a template ontology 6, and the template ontology 6 is provided with a personal ontology template in which personal interest information is conceptually hierarchized.

  The template ontology 6 can be arbitrarily created on the blog provider side. For example, if the blog provider wants the users of the terminals 2 to 4 to construct a personal ontology related to music, the template ontology 6 related to music may be constructed. Here, in order to express the interests of the users of the terminals 2 to 4 in detail, it is preferable to construct a template ontology 6 that is subdivided as much as possible and has high coverage. The entity of the template ontology 6 is a text file described in an XML language such as the ontology description language OWL. In order to simplify the organization of information, instances may be classified only into the lowest class.

  Furthermore, the server 5 applies words that appear frequently in the blog entries 7a to 7n, 8a to 8n, and 9a to 9n by applying morphological analysis to the blog entries 7a to 7n, 8a to 8n, and 9a to 9n, respectively. In the frequent word extraction means 5a to be extracted, the classifier application means 5b and the classifier application means 5b to extract from the template ontology 6 a class or instance including words that frequently appear in the blog entries 7a to 7n, 8a to 8n, and 9a to 9n. Personal ontology extraction means 5c for extracting the extracted classes or instances and all classes above them as a model ontology 6 from the model ontology 6, and approximation for measuring the degree of approximation between the personal ontology extracted by the personal ontology extraction means 5c Degree measuring means 5d, persona whose degree of approximation is a predetermined value or more Surprisingly information presentation unit 5f for presenting surprising information extracted in surprising information extractor 5e and surprising information extractor 5e extracts surprisingly information to users without the surprising information is provided from the ontology. The unexpected information refers to an unknown class (concept) or an unknown instance (entity) that is likely to be of interest to an individual.

Here, the unexpected information extraction unit 5e extracts, as unexpected information, classes or instances that are included in one personal ontology but not included in the other personal ontology, between the personal ontology having a degree of approximation equal to or greater than a predetermined value. Can do.
The frequent word extraction means 5a applies morphological analysis to the blog entries 7a to 7n, 8a to 8n, and 9a to 9n, respectively. Then, morphemes that frequently appear in a plurality of blog entries 7a to 7n, 8a to 8n, and 9a to 9n possessed by the same user are extracted.

  Next, the classifier applying unit 5b applies each morpheme frequently appearing in the blog entries 7a to 7n, 8a to 8n, and 9a to 9n to the template ontology 6, and a character string that matches the class or instance in the template ontology 6 is applied. Find out if there is. If there is a character string that matches the class or instance in the template ontology 6, the personal ontology extraction means 5c uses the personal ontology as a direct descendant class and instance from the root class of the template ontology 6 to the class or instance. Extract as

  Furthermore, the degree-of-approximation measuring means 5d measures the degree of approximation between personal ontology, and the unexpected information extracting means 5e is included in one personal ontology between personal ontologies whose degree of approximation is a predetermined value or more, but the other personal Class or instance not included in ontology is extracted as unexpected information. Then, the unexpected information presenting means 5f presents the class or instance information extracted by the unexpected information extracting means 5e to the user holding the personal ontology that does not include the class or instance.

  As a result, a personal ontology in which personal interest information is conceptually hierarchized automatically by collating the words contained in each individual's blog entries 7a-7n, 8a-8n, 9a-9n on the template ontology 6. Generates information about classes or instances that are included in the personal ontology held by other users but are not included in the personal ontology held by the user even though the degree of approximation between the personal ontology is close. be able to. For this reason, it is possible to generate personal ontology while suppressing the cost of creation, and to provide unexpected information that is not related as a class hierarchy but may be of interest to individuals Can do. As a result, it is possible to improve the accuracy of information retrieval, and to distribute the personal ontology of each individual widely on the Internet while enabling the range of interest that the user has not known before. Thus, it is possible to form a community that suits individual preferences.

  Note that the template ontology 6 may be manually created by desk work and stored in the server 5, or the personal ontology extracted by the personal ontology extracting means 5c may be merged with the existing template ontology 6. You may create it. Furthermore, a class or instance that the user is interested in may be added to the personal ontology extracted from the template ontology 6, or a class or instance that the user is not interested in may be deleted.

The frequent word extraction means 5a, classifier application means 5b, personal ontology extraction means 5c, approximation measure means 5d, unexpected information extraction means 5e, and unexpected information presentation means 5f are instructions for executing the processing performed by these means. Can be realized by causing a computer to execute a program in which is described.
If this program is stored in a storage medium such as a CD-ROM, the frequent word extraction means 5a and classifier application means are installed by installing the storage medium in the computer of the server 5 and installing the program in the computer. 5b, personal ontology extracting means 5c, approximation degree measuring means 5d, unexpected information extracting means 5e and unexpected information presenting means 5f can be realized. Moreover, by downloading this program via the communication network 1, this program can be easily spread.

  Also, a program in which instructions for executing the processing performed by the frequent word extraction means 5a, classifier application means 5b, personal ontology extraction means 5c, approximation measure means 5d, unexpected information extraction means 5e, and unexpected information presentation means 5f are described. May be executed by a stand-alone computer, or may be distributed to a plurality of computers connected to a network.

  In the above-described embodiment, between personal ontology having a degree of approximation equal to or greater than a predetermined value, a class or instance that is included in one personal ontology but not included in the other personal ontology is extracted as unexpected information. The method for providing information to the user has been described, but the number of users who are interested in the same class or instance is analyzed between ontology whose degree of approximation is a predetermined value or more, and it is included in one ontology but is included in the other ontology. It is also possible to extract classes or instances that are not included in the class and instances in which the number of interested users is a predetermined value or more as unexpected information, and provide the unexpected information to the users.

This makes it possible to receive information on classes or instances that are not in your personal ontology and that are of interest not only to one user, but also to many other users, as a class hierarchy. Even when there is no correspondence relationship, it is possible to accurately receive unexpected information that he does not know while improving the validity of his interest.
In the above-described embodiment, the personal ontology constructed from the template ontology 6 has been described as an example in order to extract unexpected information. However, the present invention is not necessarily limited to the personal ontology constructed from the template ontology 6. However, it may be applied to other ontology.

  Further, when measuring the degree of approximation between personal ontologies, the degree-of-approximation measuring means 5d is based on the determination result of whether or not the class ID or instance ID allocated from the template ontology 6 is held in the personal ontology. The degree of topology or class approximation between ontologies can be measured. Alternatively, the degree-of-approximation measuring means 5d measures the degree of approximation between personal ontology by using the degree of co-occurrence between class sets forming the topology of the personal ontology extracted by the personal ontology extracting means 5c. Alternatively, the degree of approximation between personal ontology may be measured by using the co-occurrence degree between the instance sets included in the personal ontology extracted by the personal ontology extracting means 5c. The co-occurrence degree is a ratio of a product set of members included in the set.

  For example, the degree-of-approximation measuring unit 5d measures the degree of topology approximation between personal ontology based on the value obtained by dividing the number of members of the product set between the class sets of personal ontology by the number of members of the class set of template ontology 6. Alternatively, based on a value obtained by dividing the number of members of the product set between the instance sets of the personal ontology by the number of members of the instance set of the template ontology 6, the closeness of the classes between the personal ontology is measured. Alternatively, the degree of approximation between personal ontologies may be measured by comprehensively determining the degree of topology approximation between personal ontology and the degree of class approximation between personal ontology.

FIG. 2 is a diagram illustrating a method for measuring the degree of approximation between personal ontology according to an embodiment of the present invention. In the following description, when the degree of approximation between an ontology and another ontology is measured, the former is called a source ontology and the latter is called a target ontology.
In FIG. 2, classes “b1”, “b2”, and “b3” exist immediately below the class “a1” of the template ontology OH, and “c1” and “c3” immediately below the class “b1”. It is assumed that a class called “c2” exists and classes “d1” and “d2” exist immediately below the class called “c1”. Also, it is assumed that classes “c3” and “c4” exist immediately below the class “b2”, and a class “c5” exists immediately below the class “b3”.

  The class “d1” includes instances “j” and “k”, the class “d2” includes the instance “l”, and the class “c2” includes “m”. "B", the class "b2" has an instance "n", and the class "c3" has "a", "e", "c", "f", "b" ”,“ D ”, and“ g ”exist, and the class“ c4 ”includes instances“ p ”,“ g ”,“ j ”, and“ h ”.

Then, the words that frequently appear in each user's blog entry are extracted, and the classes or instances including the words and all the classes above them are extracted from the template ontology OH, thereby creating personal ontologies OA and OB. Shall be.
Here, the classes “b1” and “b2” exist immediately below the class “a1” of the personal ontology OA, and the classes “c1” and “c2” exist immediately below the class “b1”. It is assumed that a class “d1” exists immediately below the class “c1”, and a class “c3” and “c4” exist immediately below the class “b2”. , The class “d1” includes instances “j” and “k”, the class “c2” includes the instance “m”, and the class “c3” includes “a”. , “C”, “b”, and “d” exist, and the class “c4” includes instances “q” and “h”.

  Also, in the personal ontology OB, there are “b1”, “b2”, and “b3” classes directly under the “a1” class, and there is a “c1” class directly under the “b1” class. Assume that a class “d1” exists immediately below the class “c1”, and a class “c3” and “c4” exist immediately below the class “b2”. The class “d2” has an instance “l”, the class “b2” has an instance “n”, and the class “c3” has “a” and “c”. ”,“ E ”, and“ f ”exist, and“ c4 ”class includes“ p ”and“ j ”.

  Then, a common class excluding a terminal class is analyzed between the template ontology OH and the personal ontology OA and OB, and a topology composed of parent and child classes with the common class as a parent class is extracted. In the example of FIG. 2, the end classes are “d1”, “d2”, “c3”, and “c4”. As a result, a child class set G1 having the class “a1” as the parent class, a child class set G2 having the class “b1” as the parent class, and the class “c1” being the parent class between the template ontology OH and the personal ontologies OA and OB. Child class set G3, child class set G4 having class “b2” as a parent class, and child class set G5 having class “b3” as a parent class can be extracted.

The analysis of the common class only needs to confirm whether the same class ID exists between the template ontology OH and the personal ontology OA, OB. For this reason, it is not necessary to measure the degree of approximation of class name attributes, instance set properties, etc., and the amount of calculation can be reduced while maintaining the correspondence between classes accurately.
Next, the degree of approximation between the child class sets X and Y forming each topology between the personal ontology OA and OB is calculated with depth priority. Here, if the set of child classes of the classes constituting the template ontology OH is Z, the degree of approximation between the child class sets X and Y can be obtained by | X∩Y | / | Z |. By adding the approximation degree between the child class set for each topology, it is possible to measure the degree of approximation S _T personal ontology OA, between OB topology.

  For example, in the child class set G1, since the template ontology OH includes child classes “b1”, “b2”, and “b3”, the number of members of the child class set of the template ontology OH in the child class set G1 is 3 In the child class set G1, the personal ontology OA includes child classes “b1” and “b2”, and the personal ontology OB includes child classes “b1”, “b2”, and “b3”. Therefore, the child classes commonly included in the personal ontologies OA and OB are only “b1” and b2 ”, and the number of members of the product set of the child class sets of the personal ontology OA and OB in the child class set G1 is 2. As a result, the degree of approximation between the child ontology sets G1 of the personal ontology OA and OB is 2/3.

Similarly, the degree of approximation between the personal ontology OA and OB between the child class sets G2 is 1/2, the degree of approximation between the child class sets G3 is 0/2, and the degree of approximation between the child class sets G4 is 2/2. As a result, personal ontology OA, similarity S _T topology between OB becomes 2/3 + 1/2 + 0/2 + 2/2.
In the calculation of the approximate degree of topology between the personal ontology OA and OB, the class ID assigned from the template ontology OH is referred to, and the one along the connection form of the template ontology OH exists between the personal ontology OA and OB. You only have to confirm whether you want to do it. For example, whether the connection form a1-b1-c1 in the personal ontology OA, OB is the same as the connection form of the template ontology OH depends on whether the classes “a1”, “b1”, and “c1” are the personal ontology OA, OB. It can be determined simply by confirming whether or not it is held at.

  For this reason, in order to confirm the degree of coincidence of the topology between the personal ontology OA and OB, it is only necessary to check the class ID possessed by the personal ontology OA and OB. Therefore, it is possible to reduce the calculation amount of the degree of approximation of the topology between the personal ontology OA and OB.

Next, the degree of approximation between the common classes of the personal ontology OA and OB is calculated. Here, when calculating the degree of approximation between the common classes of the personal ontology OA and OB, an instance set belonging to the class can be used. That is, in a certain class C1, if the instance set of the source ontology is x, the instance set of the target ontology is y, and the instance set of the template ontology OH is z, the degree of approximation between the common classes of the personal ontology OA and OB is | x ∩y | / | z |. By adding the degree of approximation between the common class, it is possible to measure the degree of approximation S _C between personal ontology OA, the OB classes.

  For example, in the common class “b2” between the personal ontologies OA and OB, the instance set G6 in the common class “b2” of the personal ontology OA includes the instance “n”, and the common class “b2” of the personal ontology OB. An instance “n” exists in the instance set G6, and an instance “n” exists in the common class “b2” of the template ontology OH. As a result, the number of members of the common class “b2” of the template ontology OH is 1, the number of members of the product set of the instance set G6 of the personal ontology OA and OB is 1, and the degree of approximation between the common classes “b2” is 1/1.

  In the common class “c2” between the personal ontology OA and OB, the instance set G7 in the common class “c2” of the personal ontology OA includes instances “a”, “c”, “b”, and “d”. In the instance set G7 in the common class “c3” of the personal ontology OB, instances “a”, “c”, “e”, and “f” exist, and in the common class “c3” of the template ontology OH “A”, “e”, “c”, “f”, “b”, “d”, and “g” exist.

As a result, the number of members of the common class “c3” of the template ontology OH is 7, the number of members of the product set of the instance set G7 of the personal ontologies OA and OB is 2, and the degree of approximation between the common classes “c3” is 2/7.
Accordingly, the degree of approximation S _C between the classes of the personal ontology OA and OB is 1/1 + 2/7.

Note that even in the calculation of the degree of approximation between the common classes of the personal ontology OA and OB, it is only necessary to confirm whether the instance ID allocated from the template ontology OH exists between the personal ontology OA and OB. For this reason, in order to calculate the degree of approximation between the classes of the personal ontology OA and OB, it is not necessary to confirm in advance the correspondence between instances based on the consistency of the names of instances, and the amount of calculation can be reduced.
Then, the personal ontology OA, the similarity S _C between the degree of approximation S _T and class topology in OB is determined, by using an evaluation function f (X) corresponding to the importance for the topology and class, the following expression Thus, the degree of approximation S _O (AB) between the personal ontology OA and OB can be given.
S _O (AB) = S _T + f (S _C )

  As a result, the personal ontology OA and OB can be constructed while inheriting the class characteristics of the template ontology OH, and the degree of co-occurrence between the instance sets can be directly measured for the degree of approximation between the personal ontology OA and OB. It is possible to appropriately extract personal ontology OA and OB adapted to individual tastes while suppressing the amount of calculation, and the domain ontology OH possesses knowledge of the domain possessed by the template ontology OH. It can be used as a relative measure of possession, and users who have a lot of knowledge about the domain can be effectively narrowed down.

The personal ontology OA, when measuring the degree of approximation S _T topology in OB, based on the number of members of the class set stationery ontology, personal ontology OA, by measuring the degree of approximation topology between OB, personal ontology Even when the number of members of the class set of OA and OB increases, the degree of topology approximation between the personal ontology OA and OB can be prevented from decreasing, and the amount of knowledge is large in the sense that there are abundant classes. The degree of approximation with the personal ontology OA, OB can be increased.

Then, the degree-of-approximation measuring means 5d applies the degree-of-approximation measurement algorithm as described above, so that the degree of approximation S _O between the personal ontology held by the user A and the personal ontology held by the other users U ( AU) is measured by brute force. The surprising information extractor 5e sets the heuristic threshold [delta], to derive user group G _U satisfying S _O (AU)> δ. Then, the accumulation and personal ontology of each user belonging to the user group G _U, classes and instances of the difference between the personal ontology user A holds a surprising information.

The surprising information presentation unit 5f, despite close similarity between interest ontologies, but are included in the user group G _U, the information included not class or instance in personal ontology user A holds It can be presented to user A. For example, in the example of FIG. 2, the unexpected information extracting unit 5 e can extract the combination of the class “b3” or the class “d2” and the instance “l” from the personal ontology OB as unexpected information for the user A. Then, the class combination of "d2" instances "l" is, if the frequent in personal ontology of each user belonging to the user group _{G U,} surprising information presentation unit 5f, the class "d2" instances "l" Information to the user A can be presented to the user A.

Alternatively, among classes that do not exist in the personal ontology held by the user A, information of a class having a large hierarchy shift may be preferentially presented to the user A as unexpected information. Here, the class having a large shift in the hierarchical structure refers to a portion where the branch is shifted at an early stage in the root hierarchy as compared with the personal ontology of the user A. For example, in the example of FIG. 2, the class “b3” of the personal ontology OB has a shift in the branch at an earlier stage in the root hierarchy than the class “d2”. That is, the class “b3” of the personal ontology OB has a shift in the branch at the second level, but the class “d2” has a shift in the branch at the fourth level. Therefore, the unexpected information extracting unit 5e can extract the information of the class “b3” from the personal ontology OB as unexpected information for the user A. The combination of Class "b3" is, if the frequent in personal ontology of each user belonging to the user group G _U, surprising information presentation unit 5f may present the information in the class "b3" to the user A .

  Or you may make it present to the user A preferentially the information of the class in which the shift | offset | difference has arisen in the deep part of a class hierarchy among the classes which do not exist in the personal ontology which the user A hold | maintains. That is, it is possible to preferentially present to the user A, as unexpected information, information on a class that does not exist in the personal ontology held by the user A and in which a deviation occurs in the branch at a deep stage in the root hierarchy.

For example, in the example of FIG. 2, the class “d2” of the personal ontology OB has a shift in the branch at a deeper level in the root hierarchy than the class “b3”. That is, the class “b3” of the personal ontology OB has a shift in the branch at the second level, but the class “d2” has a shift in the branch at the fourth level. For this reason, the unexpected information extraction unit 5e can extract the information of the class “d2” and the instance “l” from the personal ontology OB as unexpected information for the user A. The combination of Class "d2" instances "l" is, if the frequent in personal ontology of each user belonging to the user group _{G U,} surprising information presentation unit 5f, the class "d2" and instances of "l" Information can be presented to user A.

Alternatively, a personal ontology user A holds, in the class appearing in common to the personal ontology of each user belonging to the user group G _U, but are included in the personal ontology of each user belonging to the user group G _U, Instance information that is not included in the personal ontology held by the user A may be presented to the user A. For example, in the example of FIG. 2, the unexpected information extraction unit 5 e extracts the class “c3” that appears in common in the personal ontology OA held by the user A and the personal ontology OB held by the user B. An instance “e” included in the class “c3” of the OB but not included in the class “c3” of the personal ontology OA can be extracted. The combination of Class "c3" and instance "e" is, if the frequent in personal ontology of each user belonging to the user group G _U, surprising information presentation unit 5f is information of an instance "e" to the user A Can be presented.

FIG. 3 is a diagram illustrating a method for generating a personal ontology and a method for analyzing the number of users interested in the same class or instance according to an embodiment of the present invention.
In FIG. 3, an entry set of users A, B,..., X is collected through a ping server or the like, and an index is created by performing morphological analysis on all the collected blog entries ( Step S1). The ping server refers to a server that collects and provides blog update information.

Next, all the blog entries collected by the ping server are classified with respect to the template ontology OH (step S2). Here, as a method for classifying blog entries, if there is a description in an entry having a name attribute of class C _{i having} a template ontology OH, the entry can be classified into class C _i . In addition, if the name attribute of the instance I _i (∈C _i ) belonging to the class C _i having the template ontology OH is described in the entry, the entry is classified into the instance I _i belonging to the class C _i. Can do. Note that the same entry may be classified into a plurality of classes.

For example, when a character string “Charlantans” is included in the description in the entry, the entry can be classified into an instance “Charlantans” of the class “Madchester”.
Next, the number of users A, B,..., X who are interested in each instance of the lowermost class C ₁ forming the template ontology OH is measured (step S3). When the number of users A, B,..., X who are interested in instances of class C _l is measured, the number of users even when the same user describes instance I _l in a plurality of entries. Measures 1

Next, the number of users A, B,..., X who are interested in the lowest class C ₁ forming the template ontology OH is measured. Here, the number of users A, B,..., X interested in the lowest class C ₁ forming the template ontology OH is the number of users interested in all instances under the lowest class C _1. , it can be calculated by the sum of the number of users interested in the lowest layer class C _l itself. Note that the number of users is measured as 1 even when the same user is interested in a plurality of instances or is interested in the lowermost class and instances belonging to the lowermost class at the same time. In this way, by recursively measuring the number of users A, B,..., X interested in the class or instance forming the template ontology OH up to the root class, the user A interested in the domain , B,..., X can be calculated.
Next, when all the blog entries collected by the ping server are classified with respect to the template ontology OH, the classification results are arranged for each user ID, whereby each user A, B,. Each interest ontology OA,..., OX is generated (step S4).

FIG. 4 is a diagram illustrating a community formation method using the approximation of interest ontology according to an embodiment of the present invention.
In FIG. 4, it is assumed that the blog entries PA and PB of the users A and B are classified with respect to the template ontology, thereby generating the interest ontologies KA and KB of the users A and B, respectively (step S11). . Then, the degree of approximation between the interest ontologies KA and KB of the users A and B is measured (step S12), and the topologies are analyzed by analyzing classes and instances that co-occur between the interest ontologies KA and KB having a high degree of approximation. Although it is different, information that is highly likely to be of interest can be recommended to the user as unexpected information through the entry of another user (step S13).

For example, by measuring the degree of approximation between the interest ontologies KA and KB of each user A and B, a user who is interested in a class such as “Madchester” or an instance such as “Happy Mondays” can have a class “Glasgow” It can be seen that there is a high possibility of being interested in an instance of “Teenage Fanclub”.
Also, by applying such interest ontologies KA and KB to a program, it is possible to support the formation of a community by unexpected entry recommendation based on the degree of approximation between interest ontologies KA and KB, rather than simple keyword search. The user's interest can be naturally expanded (step S14).

  The present invention makes it possible to easily create a personal ontology and quickly obtain information that matches one's interest, and automatically and efficiently information that matches one's interest from an information source of an information communication system. Can be used.

It is a block diagram which shows schematic structure of the system with which the interest information provision apparatus which concerns on one Embodiment of this invention is applied. It is a figure which shows the approximation measuring method between personal ontology concerning one Embodiment of this invention. It is a figure which shows the production | generation method of the personal ontology which concerns on one Embodiment of this invention, and the analysis method of the number of users who are interested in the same class or instance. It is a figure which shows the community formation method using the approximation of the interest ontology which concerns on one Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Communication network 2-4 Terminal 5 Server 5a Frequent word extraction means 5b Classifier application means 5c Personal ontology extraction means 5d Approximation degree measurement means 5e Unexpected information extraction means 5f Unexpected information presentation means 6 Model ontology 7-9 Blog sites 7a-7n , 8a-8n, 9a-9n Blog entries

Claims (6)

A word extraction means for extracting words included in the interest information constructed for each individual;
Classifier application means for extracting a class or instance including a word extracted by the word extraction means from a template ontology in which preset words are hierarchized in concept,
A personal ontology extraction means for extracting, from each model ontology, a hierarchical structure including the extracted classes or instances and higher classes thereof for each individual as a personal ontology;
Approximation degree measuring means for measuring the degree of approximation between the personal ontology;
Among classes of personal ontologies that have a degree of approximation equal to or greater than a predetermined value, among classes or instances constituting the personal ontology, classes and instances that include words that are included in one personal ontology but not included in the other personal ontology. Unexpected information extracting means for extracting as unexpected information;
Unexpected information extracted by the unexpected information extracting means, and unexpected information presenting means for presenting to a user holding a personal ontology that does not include the class and the instance extracted as the unexpected information,
The unexpected information presentation means includes:
An interest information generation apparatus characterized by presenting to a user both a class extracted as the unexpected information and an instance belonging to the class. A word extraction means for extracting words included in the interest information constructed for each individual;
Classifier application means for extracting a class or instance including a word extracted by the word extraction means from a template ontology in which preset words are hierarchized in concept,
A personal ontology extraction means for extracting, from each model ontology, a hierarchical structure including the extracted classes or instances and higher classes thereof for each individual as a personal ontology;
Approximation degree measuring means for measuring the degree of approximation between the personal ontology;
In a common class including words common to a class constituting the personal ontology, which is present in a plurality of personal ontologies in which the degree of approximation between one personal ontology is a predetermined value or more and the one personal ontology, Unexpected information extraction that extracts instances including words that are included in any one of the plurality of personal ontologies but not included in the one personal ontology among the instances belonging to the common class as unexpected information Means,
Surprising information presenting means for presenting unexpected information extracted by the unexpected information extracting means to a user holding the one personal ontology not including the instance extracted as the unexpected information, Interest information generation device. Word extraction means for extracting words included in the blog entry by applying morphological analysis to the blog entry;
A template ontology selection means for selecting a template ontology in which preset words are hierarchized into concepts;
Classifier application means for extracting a class or instance including a word extracted from the blog entry from the template ontology;
A personal ontology extraction means for extracting a hierarchical structure including the extracted classes or instances and their higher classes for each user from the template ontology as a personal ontology;
Approximation degree measuring means for measuring the degree of approximation between the personal ontology;
Among classes of personal ontologies that have a degree of approximation equal to or greater than a predetermined value, among classes or instances constituting the personal ontology, classes and instances that include words that are included in one personal ontology but not included in the other personal ontology. Unexpected information extracting means for extracting as unexpected information;
Unexpected information extracted by the unexpected information extracting means, and unexpected information presenting means for presenting to a user holding a personal ontology that does not include the class and the instance extracted as the unexpected information,
The unexpected information presentation means includes:
An interest information generation apparatus characterized by presenting to a user both a class extracted as the unexpected information and an instance belonging to the class. Word extraction means for extracting words included in the blog entry by applying morphological analysis to the blog entry;
A template ontology selection means for selecting a template ontology in which preset words are hierarchized into concepts;
Classifier application means for extracting a class or instance including a word extracted from the blog entry from the template ontology;
A personal ontology extraction means for extracting a hierarchical structure including the extracted classes or instances and their higher classes for each user from the template ontology as a personal ontology;
Approximation degree measuring means for measuring the degree of approximation between the personal ontology;
In a common class including words common to a class constituting the personal ontology, which is present in a plurality of personal ontologies in which the degree of approximation between one personal ontology is a predetermined value or more and the one personal ontology, Unexpected information extraction that extracts instances including words that are included in any one of the plurality of personal ontologies but not included in the one personal ontology among the instances belonging to the common class as unexpected information Means,
Surprising information presenting means for presenting unexpected information extracted by the unexpected information extracting means to a user holding the one personal ontology not including the instance extracted as the unexpected information, Interest information generation device. Word extraction means for extracting words included in the blog entry;
Classifier application means for extracting a class or instance including a word extracted by the word extraction means from a template ontology in which preset words are hierarchized in concept,
A personal ontology extraction means for extracting a hierarchical structure including the extracted classes or instances and their higher classes for each user from the template ontology as a personal ontology;
Approximation degree measuring means for measuring the degree of approximation between the personal ontology;
Classifying the blog entry having a word included in a class constituting the template ontology or an instance belonging to the class into the class ontology class or the instance belonging to the class, and to class the instance ontology and the instance belonging to the class Among them, for each class and instance corresponding to a class and instance constituting a personal ontology having a degree of approximation equal to or greater than a predetermined value, a user number analysis is performed to measure the number of users including words included in the class or instance in the blog entry. Means,
Among the classes of personal ontologies whose degree of approximation is greater than or equal to a predetermined value, among classes or instances constituting the personal ontology, classes and instances that include words that are included in one personal ontology but not included in the other personal ontology. Unexpected information extracting means for extracting, as unexpected information, classes and instances having the number of users equal to or greater than a predetermined value;
Unexpected information extracted by the unexpected information extraction means, and unexpected information presenting means for presenting to a user holding a personal ontology that does not include the class or instance extracted as the unexpected information,
The unexpected information presentation means includes:
An interest information generation apparatus characterized by presenting to a user both a class extracted as the unexpected information and an instance belonging to the class. The unexpected information presentation means includes:
Among the classes extracted as the unexpected information, the class having the highest concept and the instances belonging thereto, or the class having the lowest concept and the instances belonging thereto are preferentially given to the user in the hierarchical structure of the concept hierarchy. The interest information generating apparatus according to claim 1, wherein the interest information generating apparatus is provided.

Images