JP2009301540A - Information retrieval device and information retrieval method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To present a retrieved result with high precision even when a word input as a retrieval query has a plurality of meanings and many users who input the retrieval query intend to obtain information about a specified meaning. <P>SOLUTION: An information retrieval server 140 includes: a user attribute information storage part 114 for storing attribute information of the user gathered beforehand; an access history storage part 111 for storing access history of each user; an URL attribute distribution generation part 112 for extracting attribute distribution of the users who have accessed for each URL; a retrieval history storage part 121 for storing retrieval history of each user; a retrieval query attribute distribution generation part 122 for extracting the attribute distribution of the user who has performed input for each retrieval query; and a final retrieved result generation part 134 for generating the retrieved result to be presented to the user on the basis of a similarity degree between the attribute distribution of the retrieval query input by the user and the attribute distribution of the URL of a retrieved result candidate. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an information search apparatus and an information search method for providing a user with a search result corresponding to a search query.

  Currently, a large amount of information is stored in the Internet, and a user accesses information by requesting desired information from an information providing apparatus by a method such as search. A conventional information providing apparatus such as a search engine provides information that matches a condition by using a relationship between search query information input by a user and document information such as a keyword distribution of a stored document group. It was general. As a conventional search method using keywords, there is Patent Document 1 or the like.

JP 2002-149683 A

  However, in the method of calculating the degree of match based on the keyword distribution of the search query and the document, even if the keyword of the search query is used in the meaning that the user did not intend, if the appearance frequency is high, There is a problem of being ranked.

  For example, common nouns may be added to proper nouns such as product names, web site names, TV program names, software names, and store names, and users want to obtain information on such proper nouns. Even when entered as a search query, even with a conventional search engine, even if a Web page uses the same word as a general noun, it is displayed at the top as a search result. Different search results may be provided.

  As described above, in the conventional search method, when a word input as a search query has a plurality of meanings and many users who input the search query are trying to obtain information on a specific meaning, the search is performed with high accuracy. The method of presenting results is a challenge.

  Therefore, an object of the present invention is to provide an information search apparatus and an information search method that can provide a search result with high accuracy for more users.

  In order to solve the above-described problems, an information search apparatus according to the present invention includes a user attribute information storage unit that stores user attribute information collected in advance, and an access history that accumulates an access history to a network or search result document for each user. Based on the storage means, the user attribute information stored in the user attribute information storage means, and the access history stored in the access history storage means, a URL attribute distribution as a user attribute distribution for each URL related to the accessed user is obtained. URL attribute distribution generating means for generating, search history storing means for storing search history for each user, user attribute information stored in user attribute information storing means, and search history for each user stored in search history storing means And a search query that generates a search query attribute distribution as a user attribute distribution entered for each search query based on And Li attributes distribution generating means, based on the URL attribute distribution, a search query attributes distribution, the degree of similarity is characterized by comprising: a search result generation means for generating a search result to be presented to the user.

  As a result, it is possible to present, as a search result, a URL having a high degree of matching with the attribute characteristics of the user group inputting the search query. There are various methods for accessing the URL, such as a link click from a portal site, a link click from a blog or a bulletin board, a direct URL input, and a link click from a search result of a search engine. When there is a bias in the attributes of users who access URLs by these various methods, there is a similar bias in the attribute distribution of search queries that are input when using a search engine that is a means of accessing the URL. Probability is high. Therefore, by considering not only the fitness of the description contents of the page corresponding to the URL but also the similarity of the attribute distribution, more users intend even when the search query has a plurality of meanings. There is an effect that it is possible to present a highly accurate search result in which URLs having a high degree of association with the meaning are ranked high.

  In the information search apparatus of the present invention, the URL attribute distribution generation unit generates a URL attribute distribution based on the access history extracted separately for each accessed date and time, and the search query attribute distribution generation unit It is preferable to generate a search query attribute distribution based on a search history for each user extracted separately for each date and time. As a result, by generating an attribute distribution including time-series access information and search information, even if the trend of information that the user wants to obtain with the same search query differs by time series, the time zone, day of the week, etc. Accordingly, there is an effect that it is possible to present a search result reflecting the information that the user wants to obtain with high accuracy.

  In the information search apparatus of the present invention, the access history storage means may store only the history when the URL is accessed from the search result list of the search engine, and generate the URL attribute distribution based on the history. . As a result, even when the user's access history to the network cannot be used, the information search device of the present invention can be provided if the business is providing a search engine. In addition, since the number of target histories is reduced in generating the URL attribute distribution, the storage capacity required in the access history accumulating unit is reduced, and further, the processing time required for generating the URL attribute distribution is shortened. There is an effect that can be. In addition, by using only the access to the URL from the search result list of the search engine, it becomes possible to remove the access unrelated to the user's intention due to another URL or a link from spam mail. Search actions are surely performed by the user's intention, and access to the search result is also clicked at the user's discretion after browsing the document title and summary, reflecting the user's intention with higher accuracy Thus, it is possible to generate a URL attribute distribution, and it is possible to present a search result with higher accuracy to the user.

  In order to solve the above problems, an information search method of the present invention is an information search method executed by an information search device that provides information, a user attribute information storage step for storing user attribute information collected in advance, and a user Based on the access history accumulating step for accumulating the access history for each network or search result document, the user attribute information stored in the user attribute information storing step, and the access history accumulated in the access history accumulating step A URL attribute distribution generating step for generating a URL attribute distribution as a user attribute distribution for each URL related to the accessed user, a search history storing step for storing a search history for each user, and stored user attribute information. Entered for each search query based on the search history for each user A search result for generating a search result to be presented to the user based on the similarity between the search query attribute distribution generation step for generating the search query attribute distribution as the user attribute distribution, the URL attribute distribution, and the search query attribute distribution And a generating step.

  As a result, it is possible to present, as a search result, a URL having a high degree of matching with the attribute characteristics of the user group inputting the search query. There are various methods for accessing the URL, such as a link click from a portal site, a link click from a blog or a bulletin board, a direct URL input, and a link click from a search result of a search engine. When there is a bias in the attributes of users who access URLs by these various methods, there is a similar bias in the attribute distribution of search queries that are input when using a search engine that is a means of accessing the URL. Probability is high. Therefore, by considering not only the fitness of the description contents of the page corresponding to the URL but also the similarity of the attribute distribution, more users intend even when the search query has a plurality of meanings. There is an effect that it is possible to present a highly accurate search result in which URLs having a high degree of association with the meaning are ranked high.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to provide the information search device and information search method which can provide a highly accurate search result for more users.

It is a figure which shows the structure of the information search system which concerns on embodiment of this invention. It is a figure which shows the access history information which shows the log | history of the information of the access destination of a user which is acquired and used in an information search system. It is a figure which shows the search history information which shows the log | history of a user's search request | requirement acquired and used in an information search system. It is a figure which shows the user attribute information which shows the attribute of a user which is acquired and used in an information search system. It is a figure which shows the attribute distribution of URL produced | generated and used in an information search system. It is a figure which shows the attribute distribution of a search query produced | generated and used in an information search system. It is a flowchart which shows the process (information search method) performed with the information search system which concerns on embodiment of this invention. It is a figure which shows the structure of the information search system which concerns on the modification of embodiment.

  Hereinafter, preferred embodiments of an information search system and an information search method according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

  FIG. 1 shows the configuration of an information search system according to this embodiment. The information search system is a system that provides information to the client portable terminal 100. The information provided to the client portable terminal 100 is specifically search result information for a search query transmitted from the client portable terminal 100. The information search is performed in response to a request from the client portable terminal 100 as described above. As shown in FIG. 1, the information search system includes an information search server 140 having a main function for providing information to the client portable terminal 100. The information search system may include an access history collection system 101 and a search engine 102. The information search server 140, the access history collection system 101, and the search engine 102 are connected to each other and can transmit and receive information.

  The client portable terminal 100 is a terminal device used by a user, and has a function of accessing the network N. Specifically, the network N is, for example, a mobile communication network, and the client mobile terminal 100 is a mobile communication terminal such as a mobile phone. The client portable terminal 100 accesses information on the network N by a predetermined method. Specifically, the client portable terminal 100 transmits an HTTP (Hyper Text Transfer Protocol) request including a URL (Uniform Resource Locator) to the network N, thereby accessing a Web server corresponding to the URL and content (information). Receive.

  The client portable terminal 100 can transmit / receive information to / from each device (information search server 140, access history collection system 101, and search engine 102) constituting the information search system via the network N. Moreover, the client portable terminal 100 receives the search result information corresponding to the search query by transmitting a search request including the search query to the information search system. The client portable terminal 100 displays the received search result information and presents the information to the user.

  The access history collection system 101 is a system that is provided on the network and is a means for acquiring access history information indicating a history of user access destination information. That is, the access history collection system 101 may function as an access history storage unit that acquires access history information for each user. The access history collection system 101 acquires information indicating which client mobile terminal 100 accessed which content (information) and when. Specifically, as shown in the table of FIG. 2, the access history collection system 101 includes a user ID that is information for identifying the client portable terminal 100, a URL included in an HTTP request transmitted by the client portable terminal 100, and Each information of the time (time stamp) at which the client portable terminal 100 transmits the HTTP request is acquired in association with each other. Here, the time when the client portable terminal 100 transmits the HTTP request indicates the time when the user accesses the content.

  For example, the access history collection system 101 functions as a proxy server of the client portable terminal 100 and receives and analyzes an HTTP request including the user ID from the client portable terminal 100. Is called. Further, for example, each information may be acquired by other methods such as receiving each information from the client portable terminal 100. The access history collection system 101 transmits the acquired access history information to the information search server 140. In addition, when the access history collection system 101 is a proxy server, the HTTP request received from the client portable terminal 100 is transferred to the Web server with the corresponding URL.

  The search engine 102 is a device that receives a search request including a search query from the client portable terminal 100 and performs a search using the search query. Here, the search query corresponds to, for example, a keyword used for search. The search target by the search engine 102 is, for example, the content of a Web server on the Internet, as in the case of a normal search engine.

  The search engine 102 acquires (calculates) a list of URLs that match the search query and a list of the degree of matching ScoreM as search results. The fitness level ScoreM is an index value indicating how much the web page is adapted to the search query. The search engine 102 transmits the acquired information to the information search server 140. Note that the search itself in the search engine 102 is performed according to an existing method.

  Further, when the search engine 102 receives a search query from a user, the search engine 102 transmits search history information indicating which user has input what search query to the information search server 140. Specifically, as shown in the table of FIG. 3, the user ID, which is information for identifying the client portable terminal 100, the search query transmitted by the client portable terminal 100, and the time when the client portable terminal 100 transmitted the search query Each information of (time stamp) is acquired in association with each other.

  Subsequently, the function of the information search server 140 having a main function for providing information to the client portable terminal 100 in the information search system will be described. As shown in FIG. 1, the information search server 140 includes a URL attribute distribution generation block 110, a search query attribute distribution generation block 120, and a search result generation block 130 as functional configuration blocks. .

  The URL attribute distribution generation block 110 aggregates the access user attributes for each URL based on the user access history information, and generates a URL attribute distribution. As shown in FIG. 1, the URL attribute distribution generation block 110 includes an access history storage unit 111, a user attribute information storage unit 114, a URL attribute distribution generation unit 112, a URL attribute as further detailed functional components. And a distribution storage unit 113.

  The access history accumulation unit 111 is an access history accumulation unit that receives access history information transmitted from the access history collection system 101 and accumulates it over a certain period. Accumulation of access information is performed, for example, by storing each information in the table shown in FIG. The certain period during which the access history information is stored in the access history storage unit 111 is determined in advance.

  The user attribute information storage unit 114 is attribute information storage means for storing attribute information indicating user attributes. The user attribute information storage unit 114 stores each attribute information in association with the user ID. The attribute information stored in the user attribute information storage unit 114 is, for example, age, sex, and address. The attribute information stored in the user attribute information storage unit 114 is notified in advance in a format associated with the user ID from the client portable terminal 100 or by using information reported by the user when starting the use of the communication service in advance. be registered. When age and sex are used as attribute information, as shown in the table of FIG. 4, attribute information is stored in association with a user ID, age, and gender.

The URL attribute distribution generation unit 112 is a means for generating the URL attribute distribution by aggregating the attributes of users who have accessed each URL. The URL attribute distribution generation unit 112 refers to the access history storage unit 111 and the user attribute information storage unit 114, and counts the number of people accessing each URL or the number of accesses by attribute by combining the user ID as a key. , URL attribute distribution is generated. Here, as attribute classification, a combination of sex and age may be used as it is, or attributes aggregated for each fixed age range such as male 10s and females 10s may be used. The URL attribute distribution A is expressed in a vector format having the attribute type n to be classified as a dimension and the number of persons accessed for each attribute or the number of accesses as an element, and A = {a ₁ , a ₂ , a _{3 ,.} }.

  The generation of the URL attribute distribution by the URL attribute distribution generation unit 112 may be performed for the URL that has been stored every time access history information is stored in the access history storage unit 111, or all URLs may be generated at regular time intervals. May be done about.

  The URL attribute distribution generation unit 112 may generate a URL attribute distribution for each day of the week or time period of access. In this case, the URL attribute distribution generation unit 112 obtains the time at which the HTTP request as the time when the user accessed the content is obtained from the time stamp held by the access history accumulation unit 111, and from the time, the accessed day of the week, Alternatively, an attribute distribution is generated for each time zone. The time zone can be determined in advance, for example, every hour, every two hours, or in the morning (4 o'clock to 12 o'clock), noon (12 o'clock to 20 o'clock), or night (from 20 o'clock to 4 o'clock the next day).

  The URL attribute distribution generation unit 112 outputs the generated URL attribute distribution to the URL attribute distribution storage unit 113.

  The URL attribute distribution storage unit 113 is a URL attribute distribution storage unit that stores the attribute distribution for each URL generated by the URL attribute distribution generation unit 112. The URL attribute distribution is stored, for example, by storing the URL and the attribute distribution in association with each other as shown in the table of FIG. When the URL attribute distribution corresponding to the URL that already stores the attribute distribution is input from the URL attribute distribution generation unit 112, the information stored in the input URL attribute distribution is updated.

  The search query attribute distribution generation block 120 aggregates the attributes of the input user for each search query based on the search history information input by the user, and generates a search query attribute distribution. As shown in FIG. 1, the search query attribute distribution generation block 120 includes a search history storage unit 121, a user attribute information storage unit 114, a search query attribute distribution generation unit 122, and more detailed functional components. And a search query attribute distribution storage unit 123. Here, the user attribute information storage unit 114 is used in common with the URL attribute distribution generation block 110.

  The search history accumulation unit 121 is a search history accumulation unit that receives the search history information transmitted from the search engine 102 and accumulates it over a certain period. For example, the search information is accumulated by storing each information in the table shown in FIG. The certain period during which the search history information is stored in the search history storage unit 121 is determined in advance.

The search query attribute distribution generation unit 122 is a unit that aggregates the user attributes input for each search query and generates a search query attribute distribution. The search query attribute distribution generation unit 122 refers to the search history storage unit 121 and the user attribute information storage unit 114 and combines the user ID as a key to determine the number of persons who input each search query or the number of input times for each attribute. Count and generate search query attribute distribution. Here, by attribute, the same attribute classification used in the URL attribute distribution is used. The search query attribute distribution B is expressed in a vector format in which the attribute type n to be classified is a dimension and the number of input for each attribute or the number of inputs is an element, and B = {b ₁ , b ₂ , b ₃ ,. _n }.

  The search query attribute distribution generation by the search query attribute distribution generation unit 122 may be performed for a search query that has been stored every time search history information is stored in the search history storage unit 121, or at regular time intervals. May be performed for all search queries.

  In addition, the search query attribute distribution generation unit 122 may generate a search query attribute distribution for each day of the week or time period of access. In this case, the search query attribute distribution generation unit 122 obtains the time at which the search query was transmitted from the time stamp held by the search history storage unit 121, and generates the attribute distribution for each day of the week or for each time zone from the time. . The time zone can be determined in advance, for example, every hour, every two hours, or in the morning (4 o'clock to 12 o'clock), noon (12 o'clock to 20 o'clock), or night (from 20 o'clock to 4 o'clock the next day).

  The search query attribute distribution generation unit 122 outputs the generated search query attribute distribution to the search query attribute distribution storage unit 123.

  The search query attribute distribution storage unit 123 is a search query attribute distribution storage unit that stores an attribute distribution for each search query generated by the search query attribute distribution generation unit 122. The search query attribute distribution is stored, for example, by storing the search query and the attribute distribution in association with each other as shown in the table of FIG. When a search query attribute distribution corresponding to a search query that already stores an attribute distribution is input from the search query attribute distribution generation unit 122, information stored in the input search query attribute distribution is updated.

  The search result generation block 130 generates and provides a search result to be provided to the user based on the URL attribute distribution and the search query attribute distribution. The search result generation block 130 includes a primary search result acquisition unit 131, a search query and URL attribute distribution attribute distribution similarity calculation unit 132, a score recalculation unit 133, a final search, and more detailed functional components. And a result generation unit 134.

  The primary search result acquisition unit 131 is a means for receiving, as search results transmitted from the search engine 102, a list of search queries, URLs that match the search queries, and the degree of match ScoreM thereof. The primary search result acquisition unit 131 outputs the acquired information to the search query and URL attribute distribution attribute distribution similarity calculation unit 132.

The search query and URL attribute distribution attribute distribution similarity calculation unit 132 is a means for calculating the similarity of each attribute distribution for the search query and URL input from the primary search result acquisition unit 131. The similarity of the attribute distribution is, for example, a vector expression B = {b ₁ , b ₂ , b _3, ..., B _n } of the search query attribute distribution and a vector expression A = {a ₁ , a ₂ , It is calculated by the cosine distance cos θ of a _3, ..., a _n }. cos θ is a value obtained by dividing the inner product (A · B) of both vectors by the product (| A | · | B |) of the absolute values of both vectors, and is calculated by the following equation.

  cos θ takes a value of 0 to 1, and is close to 1 if the attribute distributions of both vectors are similar, and close to 0 if the attribute distributions are different. That is, the value becomes larger as the attribute distribution of the user inputting the search query is closer to the attribute distribution of the user accessing the URL. cos θ is calculated for all URLs acquired as search results. The search query and URL attribute distribution The attribute distribution similarity calculation unit 132 outputs the search query, ScoreM and cos θ of each URL to the score recalculation unit 133.

  The score recalculation unit 133 is a means for calculating ScoreL in consideration of the attribute distribution similarity for the search result URL input from the search query and the URL attribute distribution attribute distribution similarity calculation unit 132. ScoreL is calculated by combining the search query and URL matching score ScoreM and the search query and URL attribute distribution similarity cos θ. The score recalculation unit 133 calculates ScoreL using, for example, the following formula stored in advance in the score recalculation unit 133.

ScoreL = (1−α) * ScoreM + α * cosθ (2)
Here, α is a value satisfying (0 <α <1), which is set in advance according to the degree to which the similarity between the search query and the URL attribute distribution is to be reflected in the search result. It is remembered. Note that if the output from the search engine 102 does not include ScoreM, cos θ may be ScoreL. The score recalculation unit 133 outputs information indicating each URL and ScoreL corresponding to the URL to the final search result generation unit 134.

  The final search result generation unit 134 is a function of a search result providing unit that generates and transmits information to be transmitted to the client portable terminal 100 based on information input from the score recalculation unit 133. The final search result generation unit 134 sorts the input URLs from those with the highest ScoreL values, generates the final search results, transmits them to the client portable terminal 100, and presents them to the user. The functional configuration of the information search server 140 according to the present embodiment has been described above.

  Subsequently, a process (information search method) executed by the information search system according to the present embodiment will be described with reference to the flowchart of FIG.

  In the information search system, first, notification in a format associated with the user ID from the client portable terminal 100, or using information reported by the user when starting the use of the communication service, the user attribute information is changed to the user attribute. It is registered in the information storage unit 114 (S11).

  Subsequently, the access history information 111 and the search history of the client portable terminal 100 are acquired and stored for a certain period by the access history storage unit 111 and the search history storage unit 121 of the information search server 140 (S12). Specifically, the access history information is accumulated as follows. An HTTP request that is an access request from the client portable terminal 100 is received by the access history collection system 101. Based on this, access history information is generated by the access history collection system 101. The generated access history information is transmitted from the access history collection system 101 to the information search server 140 and received by the access history storage unit 111.

  Specifically, the search history information is accumulated as follows. A search request from the client portable terminal 100 is received by the search engine 102. The search engine 102 transmits the search query included in the search request to the information search server 140 together with the user ID and time stamp, and the search history storage unit 121 receives the search query.

  Subsequently, the URL attribute distribution generation unit 112 and the search query attribute distribution generation unit 122 generate a URL attribute distribution and a search query attribute distribution URL (S13). The generation of the URL attribute distribution is specifically performed as follows. The URL attribute distribution generation unit 112 refers to the access history information and the user attribute information stored in the access history storage unit 111 and the user attribute information storage unit 114, totals the user ID as a key, and accesses each URL The number of people or the number of accesses is calculated for each attribute. Specifically, the search query attribute distribution is generated as follows. The search query attribute distribution generation unit 122 refers to the search history information and the user attribute information stored in the search history accumulation unit 121 and the user attribute information storage unit 114, aggregates the user IDs as keys, The number of inputs or the number of inputs is calculated for each attribute.

  The URL attribute distribution generation unit 112 may generate a URL attribute distribution for each day of the week or time period of access. In this case, the URL attribute distribution generation unit 112 obtains the time at which the HTTP request as the time when the user accessed the content is obtained from the time stamp held by the access history accumulation unit 111, and from the time, the accessed day of the week, Alternatively, an attribute distribution is generated for each time zone. The time zone can be determined in advance, for example, every hour, every two hours, or in the morning (4 o'clock to 12 o'clock), noon (12 o'clock to 20 o'clock), or night (from 20 o'clock to 4 o'clock the next day).

  In addition, the search query attribute distribution generation unit 122 may generate a search query attribute distribution for each day of the week or time period of access. In this case, the search query attribute distribution generation unit 122 obtains the time at which the search query was transmitted from the time stamp held by the search history storage unit 121, and generates the attribute distribution for each day of the week or for each time zone from the time. .

  The above is the processing until the URL and the search query attribute distribution are generated.

  Thereafter, when a search request including a search query is transmitted from the client portable terminal 100 to the search engine 102 (S14), the subsequent processing is performed. A search related to the search request is performed by the search engine 102, and a search query and information indicating the search result are transmitted from the search engine 102 to the information search server 140. In the information search server 140, the primary search result acquisition unit 131 receives and acquires the search query and information indicating the search result (S15).

  Subsequently, the attribute distribution similarity calculation unit 132 of the search query and the URL calculates the attribute distribution similarity of the acquired search query and the URL group as the search result (S16). The attribute distribution similarity is obtained by acquiring the attribute distribution of the search query and the attribute distribution of the URL from the search query attribute distribution storage unit 123 and the URL attribute distribution storage unit 113, and calculating the cosine distance cos θ by the method described above. Calculated.

  Subsequently, the URL recalculation score ScoreL considering the similarity of the attribute distribution is calculated by the score recalculation unit 133 (S17). ScoreL is calculated by the above-described method using ScoreM, which is the score of the primary search result, and attribute distribution similarity cosθ.

  Subsequently, the final search result generation unit 134 generates information indicating the final search result in which the URLs of the search results are sorted in descending order of ScoreL, and transmits the information to the client portable terminal 100 via the network N (S18). ).

  In the client portable terminal 100, information indicating the final search result is received and output such as display is performed. The above is the processing executed by the information search system according to this embodiment.

  In the information search system according to the present embodiment described above, the deviation of the user attribute distribution of the Web page URL that is each access destination of the user and the deviation of the attribute distribution of the user who inputs the search query are extracted. Similarity is generated. The URL score of the search result is calculated based on the similarity, and the URL is rearranged based on the score and provided to the user as the search result.

  As described above, in the information search system according to the present embodiment, not only the degree of matching between the search query and the web page but also the search result information to the user based on the similarity of the attribute distribution of the search query and the URL of the web page. Is provided. If the URL attribute distribution is biased, the search query input to the search engine to refer to the URL is likely to have the same bias. Therefore, according to the information search system according to the present embodiment, by considering the attribute distribution of the search query, it is possible to detect the URL that the user wants to refer to with higher accuracy and present it as a search result.

  As described above, in the information search system according to the present embodiment, the URL attribute distribution generation unit 112 and the search query attribute distribution generation unit 122 generate attribute distributions including time-series access information and search information, The ability to present search results that reflect the information that the user wants to obtain with high accuracy according to the time of day, day of the week, etc. effective.

  The search query has multiple meanings, and one of them is, for example, the program name or store name, and there is a bias in the time to access the corresponding information, such as before and after the program broadcast time or store opening time When searching at such a time, compared to information corresponding to other meanings, the information is preferentially displayed at the top of the search result, and there is a high probability that it matches the information desired by many users.

  In the embodiment described above, the URL that is the information to be provided is rearranged and provided to the user. For example, the information provided to the user is not rearranged, and only the information with a high score is provided to the user. It is good also as judging.

  Further, in the generation of the URL attribute distribution and the generation of the search query in the above-described embodiment, the time zone and the day of the week are determined based on the information indicating the time when the user accesses the information or the time when the user transmits the search query. A corresponding URL attribute distribution and search query attribute distribution may be generated. In this case, the time and day of the week are divided into arbitrary granularities, and the attribute distribution of the user who executed the access or search is generated for each divided time or day of the week, and the URL attribute distribution storage unit and the search query attribute distribution are generated. Store in the storage. As the search result, ScoreL is calculated by the above-described method based on these attribute distributions corresponding to the time when the search is performed, and the search result is presented.

  According to this configuration, even when the tendency of the information that the user wants to obtain with the same search query varies depending on the time series, the search result that reflects the information that the user wants to obtain with high accuracy according to the time zone, day of the week, etc. Can do.

  Subsequently, a modification of the present embodiment will be described with reference to FIG.

  In the embodiment described above, the access history accumulating unit 111 accumulates the access history to the network for each user. However, the history when the URL is accessed from the search result list of the search engine 102 (the search result for each user). It is also possible to accumulate only the document access history and generate a URL attribute distribution based on this. Acquisition of the URL from the search result list is performed by describing, for example, the URL included in the search result list as a redirect method via the access history collection system 101. Here, the function of the access history collection system 101 may be included as a function of the search engine 102. The collected access history is subjected to aggregation processing in the same manner as in the above-described embodiment, and thereafter operates in the same steps.

  FIG. 8 shows a configuration of an information search system in a modification. As shown in this figure, the access history collection system 101 receives only the access history to the search result document for each user from the search engine 102. The access history collection system 101 has the same function as that of the above-described embodiment except that only the access history to the document of the search result for each user is used as the access history.

  In FIG. 8, the access history collection system 101 is described separately from the search engine 102. However, as described above, the functions of the access history collection system 101 are included in the search engine 102 shown in FIG. Also good.

  Then, the effect | action and effect of this modification are demonstrated.

  According to this configuration, even when a user's access history to the network cannot be used, the information search apparatus of the present invention can be provided by any business provider that provides a search engine. In addition, since the number of target histories is reduced in generating the URL attribute distribution, the storage capacity required in the access history accumulating unit is reduced, and further, the processing time required for generating the URL attribute distribution is shortened. There is an effect and action that can be done. In addition, by using only the access to the URL from the search result list of the search engine, it becomes possible to remove the access unrelated to the user's intention due to another URL or a link from spam mail. Search actions are surely performed by the user's intention, and access to the search result is also clicked at the user's discretion after browsing the document title and summary, reflecting the user's intention with higher accuracy It is possible to generate a URL attribute distribution, and it is possible to present a search result with higher accuracy to the user.

  DESCRIPTION OF SYMBOLS 100 ... Client portable terminal, 101 ... Access history collection system, 102 ... Search engine, 110 ... URL attribute distribution generation block, 111 ... Access history storage part, 112 ... URL attribute distribution generation part, 113 ... URL attribute distribution storage part, 114 ... User attribute information storage unit, 120 ... Search query attribute distribution generation block, 121 ... Search history storage unit, 122 ... Search query attribute distribution generation unit, 123 ... Search query attribute distribution storage unit, 130 ... Search result generation block, 131 ... Primary search result acquisition unit, 132... Search query and URL attribute distribution similarity calculation unit, 133... Score recalculation unit, 134... Final search result generation unit, 140.

Claims (4)

User attribute information storage means for storing user attribute information collected in advance;
Access history accumulating means for accumulating access history to a network or search result document for each user;
Based on the user attribute information stored in the user attribute information storage unit and the access history stored in the access history storage unit, a URL attribute distribution as a user attribute distribution for each URL related to the accessed user is generated. URL attribute distribution generation means;
Search history storage means for storing search history for each user;
Search query attribute distribution as user attribute distribution input for each search query based on the user attribute information stored in the user attribute information storage means and the search history for each user stored in the search history storage means Search query attribute distribution generation means for generating
Search result generating means for generating a search result to be presented to the user based on the similarity between the URL attribute distribution and the search query attribute distribution;
An information retrieval apparatus comprising: The URL attribute distribution generation unit generates the URL attribute distribution based on the access history extracted separately for each accessed date and time,
The search query attribute distribution generation means generates the search query attribute distribution based on the search history for each user extracted separately for each search date and time.
The information retrieval apparatus according to claim 1. The access history accumulating means accumulates only the access history to the search result document for each user,
The URL attribute distribution generation means generates the URL attribute distribution based on the user attribute information and an access history to the document of the stored search results for each user.
The information search apparatus according to claim 1 or 2, characterized in that An information search method executed by an information search device that provides information,
A user attribute information storage step for storing user attribute information collected in advance;
An access history accumulating step for accumulating access history to the network or search result document for each user;
Based on the user attribute information stored in the user attribute information storage step and the access history stored in the access history storage step, a URL attribute distribution as a user attribute distribution for each URL related to the accessed user is generated. URL attribute distribution generation step;
A search history accumulation step for accumulating a search history for each user;
A search query attribute distribution generating step for generating a search query attribute distribution as a user attribute distribution input for each search query based on the stored user attribute information and the accumulated search history for each user;
A search result generation step for generating a search result to be presented to the user based on the similarity between the URL attribute distribution and the search query attribute distribution;
An information retrieval method comprising:

Images