JP2014170438A - Information processing device and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily evaluate the relative difficulty between contents with a small burden, and use it for recommendation.SOLUTION: The information processing device includes time acquiring means for acquiring the browsing time accompanied with an operation for a content; number-of-characters acquiring means for acquiring the number of characters of the content; evaluating means for evaluating a content so that a content of a longer browsing time for the number of characters has a higher level; and recommending means for recommending the content to a user on the basis of the evaluated level. The evaluating means normalizes the browsing time for the number of characters related to the content to a relative value with reference to the user, and evaluates the level for each content by counting the normalized relative values for each content.

Description

  The present invention relates to a technology for recommending content.

  Conventionally, a social filtering technique has been used for recommending (ie, recommending) content suitable for a target person. In social filtering, other targets used by other users who use the same target are recommended as being suitable for the user's interest, such as “Users using this XX also use this XX”. Further, a technique that considers a time-series purchase order has been known (see, for example, Patent Documents 1 and 2).

JP 2008-287550 A JP 2010-061456 JP 2002-108201 A

  However, among the content used by other users who use the same content, there should be a difference in relative difficulty between the contents, but the technology to evaluate such difference in difficulty and make use of it as a recommendation is Did not exist.

  Ingenuity has been proposed, such as manually classifying content in advance, or preparing an explanatory dictionary according to the content in advance and evaluating the difficulty level based on the number of references (for example, see Patent Document 3). The burden is heavy, and it is not suitable for easily evaluating the relative difficulty among a plurality of contents that happen to be used by some people among many contents.

  An object of the present invention is to easily evaluate the relative difficulty level between contents with a small burden and to make use of the recommendation.

  Based on the above object, an information processing apparatus according to one aspect (1) of the present invention includes a time acquisition unit that acquires a browsing time accompanied by an operation on content, a character number acquisition unit that acquires the number of characters of the content, and the number of characters. An evaluation means for creating evaluation information that makes the content having a relatively long browsing time relatively high and makes the content having a relatively short browsing time per number of characters relatively low And recommending means for recommending the content to the user based on the evaluation information.

  An information processing method according to another aspect (2) of the present invention captures the above aspect in a category of the method, and acquires a time acquisition process for acquiring a browsing time accompanied by an operation on the content and the number of characters of the content. Character number acquisition processing, and evaluation information that relatively high the content with the relatively long browsing time per number of characters and relatively low the content with the relatively short browsing time per the number of characters The computer executes an evaluation process to be created, a recommendation process for recommending content to the user based on the created evaluation information, and a computer.

  In addition, according to another aspect (2) of the present invention, in any one of the above aspects, the time acquisition unit receives a predetermined input from a sensor of the information processing apparatus during the display of the content. The time detected more than the predetermined amount per time is acquired as the browsing time with the said operation.

  In another aspect (3) of the present invention, in any one of the above aspects, the evaluation unit normalizes the browsing time per number of characters related to the content to a relative value based on a user. The evaluation information for each content is created by counting the relative values for each content.

  According to another aspect (4) of the present invention, in any one of the above aspects, during the browsing of the content, an amount by which a word in the content is searched in the terminal or user identification information related to the browsing is acquired as a search amount. A search amount acquisition means for performing the search, and the evaluation means relatively compares the content with a relatively high search amount per number of characters and relatively sets the content with a relatively small search amount per number of characters. It is characterized in that evaluation information is created at a low level.

  Another aspect (5) of the present invention is characterized in that, in any one of the above aspects, the content is a web page of a jump destination in an Internet search result corresponding to a specified condition.

  According to the present invention, it is possible to easily evaluate the relative difficulty level between contents with a small burden and utilize it for a recommendation.

The functional block diagram which shows a structure about embodiment of this invention. The figure which shows the example of the data in embodiment of this invention. The figure which shows the example of the data in embodiment of this invention. The flowchart which shows the process sequence in embodiment of this invention. The example of a screen display in embodiment of this invention.

  Next, a mode for carrying out the present invention (referred to as “embodiment”) will be illustrated along the drawings. In addition, the assumptions common to the contents already described in the background art and problems are omitted as appropriate.

[1. Constitution〕
FIG. 1 is a configuration diagram of this embodiment. A recommendation server 1 (also referred to simply as “server 1”) is connected from a content providing server 2 to a terminal via a communication network N (Internet, mobile phone network, etc.). This is an information processing apparatus that provides evaluation information (also referred to as “level”) indicating a level for content provided to T and provides a recommendation (recommendation) utilizing the evaluation information to the terminal T.

  The server 1 includes, as a computer configuration, an arithmetic control unit 6 such as a CPU, a storage device 7 such as a main memory and an auxiliary storage device, and a communication device 8 (such as a communication device and a communication adapter) with the communication network N. Have. According to the server 1, the terminal T and the content providing server 2 also have a computer configuration (not shown), but the types and models of the arithmetic control units, storage devices, and communication devices in the servers 1 and 2 and the terminal T need to be common. There is no.

  A large number of terminals T actually exist according to the number of users, and are not limited to portable information terminals such as smartphones and tablet PCs, but may be desktops or other personal computers. In the server 1, each element shown in FIG. 1 is realized by the arithmetic control unit 6 executing a computer program (for example, an application program or a web page script) (not shown) stored in the storage device 7.

  Among the realized elements, the information storage means is not limited to the so-called local storage in the terminal T, but may be remote storage by network computing (cloud). In addition, the storage means shown in the present application is the main unit shown for convenience of explanation, and in implementation, functions such as input / output and management associated with information storage are included, or the unit of the configuration is divided. Alternatively, other storage means such as a work area or the like may be used as appropriate.

  Note that the arrows in the figure (for example, FIG. 1) supplementarily indicate the main direction of the flow of data, control, etc., and do not mean the denial of other flows or the limitation of the direction. In addition, each means other than the storage means is a processing means for realizing and executing the functions and operations of information processing as described below, but these are functional units arranged for explanation, and actual hardware It doesn't matter if it matches elements or software modules.

[2. Action)
FIG. 4 is a flowchart showing a part related to the present invention in the operation procedure of the server 1 configured as described above. As a premise, the user browses the content provided by the content providing server 2 on the terminal T.

  The content for which the evaluation information of the relative level is to be created may be an electronic book or a destination web page or a website listed in an Internet search result corresponding to a specified condition. Further, the relative difficulty level, that is, the level may be evaluated between each web page or website belonging to the same domain, sub-domain or directory.

  The recommendation server 1 also starts and ends browsing of content on the terminal T from the content providing server 2 or a predetermined program in the terminal T, and performs operations such as page turning and scrolling regarding the content being browsed, as well as Internet search. Are obtained as data and used to create content evaluation information as follows.

  That is, when browsing of the content is started on the terminal T (step S11: “YES”), the character number acquisition unit 30 is first viewed after the content is newly created or updated (step S12: “YES”). It is obtained by counting the number of characters of the content (step S13) and stored in the character number storage means 35. The content providing server 2 or the terminal T may count the number of characters of the content and transmit it to the server 1.

  Moreover, the time acquisition means 20 acquires the browsing time accompanied with operation with respect to a content about the terminal T (step S14), and stores it in the browsing time storage means 25. The browsing time with operation is intended to exclude the time during which the user leaves the content for other errands during browsing.

  For this reason, the time acquisition means 20 acquires the time from which the predetermined input is detected more than the predetermined amount per predetermined time from the sensor of the terminal T during the display of the content as the browsing time with the operation. Here, the sensor is, for example, a touch sensor on a touch panel screen, an acceleration sensor, a brightness sensor, a screen-side camera, or the like.

  For example, in addition to operations on content such as page turning and scrolling, predetermined input includes input of illuminance exceeding the predetermined value indicating that it is held by hand without putting it in a bag, change in body angle, screen near the camera, etc. For example, detection of a face that is facing. Further, the predetermined amount in detection is, for example, the number of times, the amount of change, and the like.

  Then, the evaluation means 40 creates evaluation information in which content having a long browsing time per number of characters is relatively high and content having a relatively short browsing time per number of characters is relatively low (steps S15 to S17). The recommendation unit 50 recommends, that is, recommends the content to the terminal T used by the user based on the created evaluation information (steps S18 and S19). The user who receives the recommendation is typically a user other than the user who performed the browsing based on the evaluation information, but may be the user who performed the browsing.

  In the present embodiment, the amount of Internet search performed during browsing is also reflected in the creation of evaluation information. That is, the search amount acquisition means 60 acquires, as a search amount, the amount of words searched for on the terminal T or user identification information related to the browsing during the browsing of the content (step S16). The data is stored in the storage unit 65.

  Then, the evaluation unit 40 adds the browsing time per number of characters and the search amount per number of characters by adding a predetermined coefficient, respectively, as a basis for evaluation information (described later). The evaluation information is created so that the content with a relatively high content is relatively high and the content with a relatively small search amount per character is relatively low (step S17).

  The amount searched for in the “user identification information” is the same user identification information as the user identification information (for example, user ID) used for content subscription at the terminal T (for example, a smartphone), and another terminal (for example, a personal computer). ) And the number of times the Internet has been searched with the user identified by the cookie information stored in the terminal at the time of login.

  Here, an example of creating evaluation information is shown. For example, when recommending other contents A, B, C,... Included in the usage history of the user group (for example, A, B, etc.) having the usage history of the content X in common with the user を 受 け る receiving the recommendation to the user 丙. Think.

  FIG. 2 illustrates the contents of the browsing time storage means 25, the character count storage means 35, and the search amount storage means 65 as an integral table for the sake of explanation. In creating the evaluation information in this embodiment, the evaluation means 40 first normalizes the browsing time per number of characters related to the content to a relative value based on the user (step S15), and the normalized relative value (for example, FIG. The browsing time storage means 25 is updated with “normalized value” of 2).

  Normalization is performed based on the deviation value, the rank of the length, the distribution position between the maximum value and the minimum value. For example, the numerical value in the column of “minute / thousand characters” in the example of FIG. 2 is the browsing time per number of characters obtained by dividing the browsing time (minutes) by the number of characters (in thousands characters). When the user A browses the content B, the user browses 3,000 characters in 6 minutes, so the viewing time per number of characters is 2 (minutes / thousand characters).

  The numerical value in the column of “normalized value” gives “1” to relatively short content and “2” to relatively long content for the same user unit. Is. That is, a common measure of the browsing time per character (minute / thousand characters) is normalized to a normalized value that is a relative value for each user. Thereby, even if the content browsed by the user A (contents A and B) and the user B (contents A and C) are different as shown in FIG. 2, the browsing time of each content can be relatively normalized.

  Further, the evaluation means 40 creates the evaluation information for each content by counting the normalized relative values for each content, and updates the level storage means 35 with the created evaluation information (step S17). .

  For example, a new user whose browsing time is stored for at least one other content A, B, or C for which evaluation information already exists is browsed, and the browsing time for the number of characters for that user When the content is relatively longer than the other content that has been browsed, “2” is incremented by one in the normalized relative value of the evaluation information of the content.

  FIG. 3 exemplifies evaluation information for each content evaluated by aggregating the relative values (normalized values) normalized in this way for each content, and the evaluation information means a relative low level. Two categories of “basic” and “application” meaning relative altitude are used, but the expression format and the number of categories are not limited to this.

  In addition, in order to reflect the search amount in the evaluation information, for example, the search amount is also normalized as it is or in units of users according to the browsing time, and is evaluated by an appropriate calculation process such as adding the normalized value with a predetermined coefficient. Reflect in the information.

  In the example of FIG. 2, the content A has a normalized value “1” and is small, and becomes evaluation information “basic” as shown in FIG. 3, but relatively large search amounts “3” and “6” (see FIG. 2) If the evaluation information “basic” and “application” in FIG.

  FIG. 5 shows an example of a recommendation screen based on the evaluation information created as described above. In this screen example, a plurality of electronic books are divided into a “basic level” and an “applied level” and are displayed together with explanatory text.

[3. effect〕
(1) As described above, in the present embodiment, by creating evaluation information that makes a relatively high content with a relatively long net browsing time (for example, FIG. 2) per number of characters (for example, FIG. 2) (for example, 3), it is possible to evaluate the relative difficulty level between contents without burdens such as manual leveling and dictionary preparation, and to make use of the recommendations (for example, FIG. 5).

(2) Further, in this embodiment, by using the browsing time in which a predetermined input from the sensor is detected for a predetermined time or more, the time when the user is not watching the content can be easily excluded from the basis of judgment. It becomes possible.

(3) In this embodiment, the browsing time for each content is normalized to a relative value for each user (for example, step S15 in FIG. 4), and totalized for each content, so that browsing for each user is early and late. It can suppress that the dispersion | variation of is affecting evaluation information.

(4) Further, in the present embodiment, by creating evaluation information that makes the content relatively high per number of characters (for example, FIG. 2) the amount of words searched for while searching for words in the content (for example, FIG. 2). 4 step S16), the relative difficulty between contents can be more appropriately evaluated.

(5) Further, in the present embodiment, by applying the present invention to the web page of the net search result, the relative difficulty level between the web pages can be easily evaluated and used for the recommendation.

[4. Other embodiments]
In addition, the content of the said embodiment and figure is only an illustration, and the presence or absence and arrangement | positioning of each element, the order and content of a process, etc. can be changed suitably. For this reason, this invention also includes the modification illustrated below and other embodiments. For example, the recommendation server 1 and the content providing server 2 may be configured integrally. The number of characters of the content may be acquired every time the content is browsed, not only when the content is browsed for the first time after being newly created or updated (step S12: “YES”).

  Moreover, each aspect of the present invention can be understood as other categories (methods, programs, systems including terminals, etc.) that are not specified. In the category of method or program, “means” shown in the category of apparatus is appropriately read as “process” or “step”. In addition, all or any part of “means” can be read as “part” (unit, section, module, etc.).

  Also, the processes and steps shown in the embodiment can be changed by changing the order, executing some of them collectively, or executing them part by part. In addition, hardware elements that implement and execute individual means, processes, and steps may be common, or may differ for each means, process, step, or timing.

  The individual means shown in the present application may be realized by calling a function provided by an external server by an API (Application Program Interface) or network computing (so-called cloud or the like). Furthermore, each element such as means relating to the present invention may be realized by other information processing mechanisms such as a physical electronic circuit as well as a computer control unit.

DESCRIPTION OF SYMBOLS 1 Recommendation server 2 Content provision server 6 Arithmetic control part 7 Storage device 8 Communication apparatus 20 Time acquisition means 25 Browse time storage means 30 Character number acquisition means 35 Level storage means 35 Character number storage means 40 Evaluation means 50 Recommendation means 60 Search amount acquisition means 65 Search amount storage means A, B ... Content N Communication network T Terminal

Claims (6)

Time acquisition means for acquiring a browsing time accompanied by an operation on the content;
A character number obtaining means for obtaining the number of characters of the content;
An evaluation means for creating evaluation information that makes the content relatively long for the browsing time per number of characters relatively high for the content and relatively low for the content relatively short for the browsing time per number of characters; ,
Recommending means for recommending content to the user based on the created evaluation information;
An information processing apparatus comprising:   The time acquisition unit is configured to view, with the operation, a time during which a predetermined input is detected from a sensor of the information processing device during the display of the content more than a predetermined amount per predetermined time. The information processing apparatus according to claim 1, wherein the information processing apparatus is acquired as time. The evaluation means includes
Normalizing the browsing time per number of characters related to the content to a relative value based on the user,
The information processing apparatus according to claim 1, wherein the evaluation information for each content is created by aggregating the normalized relative values for each content. While browsing the content, comprising: a search amount acquisition means for acquiring, as a search amount, an amount of words in the content searched in the terminal or user identification information related to the browsing;
The evaluation means sets the content having a relatively high search amount per number of characters as a relatively high level, and sets the content as having a relatively low search amount per number of characters as a relatively low level. The information processing apparatus according to claim 1, wherein the information processing apparatus creates an information processing apparatus.   The information processing apparatus according to any one of claims 1 to 3, wherein the content is a destination web page among Internet search results corresponding to a specified condition. Time acquisition processing for acquiring browsing time accompanied by operations on content;
A character number acquisition process for acquiring the number of characters of the content;
An evaluation process for creating evaluation information in which the content for which the browsing time per number of characters is relatively long is relatively high, and the content for which the browsing time per number of characters is relatively short is relatively low; ,
Recommendation processing for recommending content to the user based on the created evaluation information;
An information processing method characterized in that a computer executes.

Images