JP2007164382A - Information processor, information processing method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To set a category for classifying a characteristic of a user on the basis of actual action of the user to a system, and to classify the user by the categories. <P>SOLUTION: A communication part 11 receives log information from a log 23 of a server 2, a response time information generation part 12 generates response time information showing a response time of a client 3 to browsing screen data of the user, a histogram generation part 1302 generates a histogram showing relation between the response time and the number of the users from the response time information, an evaluation value derivation part 1303 regards the histogram as composition of a plurality of normal distributions corresponding to a plurality of categories showing the user characteristic to the browsing screen data, and derives an average value and a distributed value or the like of each the normal distribution as an evaluation value for the category classification, a communication part 11 receives information about the response time to the browsing screen data of the user using the server 2 from the log 23, and a category determination part 15 performs the category classification of the user on the basis of the evaluation value. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to, for example, a technique for categorizing the characteristics of a service user who uses a service, and more particularly, to a technique for performing categorization for measuring satisfaction of a service user.

In recent years, opportunities to receive services in the face of machines and computers on behalf of service providers (people) are increasing day by day. A wide variety of services such as ATM (Automated Teller Machine), ticket vending machines, EC (Electronic Commerce) sites, etc. are provided using computers and networks. The developers of these systems have set targets for screen display time, response performance, and multiple performance, and are developing the system so that users can use it smoothly.
However, there are still many complaints such as “difficult to use” and “difficult to understand”. Conventionally, when a service is provided by a person, the service provider can grasp the satisfaction and dissatisfaction of the user by directly contacting the service user. Dissatisfaction cannot be detected by the system, and it becomes obvious by taking a questionnaire.

As a technique for measuring user satisfaction, there is a usability evaluation support device disclosed in Japanese Patent Application Laid-Open No. 2004-102868. This usability evaluation support device uses an operation history information detection device as a means for acquiring operation information for a device having a display unit and an operation unit, and a biological information detection device as a means for acquiring information about a user's living body. Resources used to collect information about users, and accuracy or completeness in achieving the user's specified goals, and resources spent in relation to accuracy and completeness in achieving the user's goals The degree of satisfaction is measured using information obtained from the operation history information detection device, and the degree of satisfaction is measured using a question to the user by the SD (Semantic Differential) method and information obtained from the biological information detection device.
Japanese Patent Application Laid-Open No. 2004-102868, page 10, table 1

  A conventional usability evaluation support apparatus is a method in which a user's operation history is not considered to have a different tendency depending on the user's characteristics and the like, and the measurement result is assumed to be one normal distribution and is evaluated by arithmetic mean In the actual distribution, there was a fear that the evaluation would have a value with almost no corresponding person. In addition, the SD method is not appropriate to the actual situation because it will answer the post facts of the user, and the measurement of the viewpoint, pupil, α wave, etc. by the biological information detection device complementing this will be a large-scale device. It was impossible to measure at the time of use.

  The present invention is intended to solve the above-described problems, for example, and sets a category for classifying the user's image and characteristics based on the user's actual behavior with respect to the system. The main purpose is to determine which category each individual user using the system belongs to.

An information processing apparatus according to the present invention includes:
A response time information input unit for inputting response time information indicating response times of a plurality of users for specific data;
Based on the response time information, a histogram generation unit that generates a response time histogram indicating the relationship between the response time and the number of users,
The response time histogram is a composite of a plurality of normal distributions corresponding to a plurality of user characteristic categories representing user characteristics for the specific data, and the average value and the variance value of each normal distribution are used as the plurality of users. And an evaluation value deriving unit derived for setting the characteristic category.

  According to the present invention, since the evaluation value for setting the user characteristic category is derived based on the response time with respect to the data representing the actual behavior of the user with respect to the data, it appears unconsciously in the behavior of the user. It is possible to accurately determine the degree of user satisfaction and interest in the data.

Embodiment 1 FIG.
FIG. 1 is a configuration diagram illustrating a system configuration example that includes a categorization / discrimination device 1 (information processing device) according to the present embodiment and devices that are to be evaluated by the categorization / discrimination device 1.

The client 3 is a terminal device operated by a service user and is equipped with a Web browser. The client 3 is, for example, a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), an ATM terminal, a ticket issuing terminal, a kiosk terminal, or the like. The client 3 can be connected to the server 2 through a network such as the Internet or a LAN (Local Area Network).
The client 3 includes a control unit 31 that controls the operation of the client 3, an operation unit 32 that is operated by the user, and a display screen that displays various information (for example, data transmitted from the server 2) to the user. The display unit 33 includes a network interface 34 for connecting to a network.

The server 2 is a Web server, for example, and provides various services in response to requests from the client 3.
The server 2 includes a Web control unit 21 that passes information through a network interface 24 according to a request from the client 3, a storage unit 22 that stores information, a log 23 that records a request from the client 3, and a network interface 24 for connecting to the network. Consists of

  The categorization / discrimination device 1 derives an evaluation value for setting a plurality of user characteristic categories indicating the characteristics of the user, and after the plurality of user characteristic categories are set, It is determined which user characteristic category the characteristic is classified into. The categorization / discrimination device 1 acquires log information from the log 23 of the server 2 and derives evaluation values for setting a plurality of user characteristic categories based on the log information.

In the categorization / discrimination device 1, the communication unit 11 communicates with the server 2 and receives log information.
The response time information generation unit 12 generates response time information indicating response time until the user responds to specific data from the log information. In this embodiment, as will be described later, an example of generating response time information indicating a response time until a response to data (viewing screen data) displayed on the display screen by the display unit 33 of the client 3 is shown. .
The categorization processing unit 13 derives an evaluation value for setting the user characteristic category from the response time information. The categorization processing unit 13 includes a response time information input unit 1301, a histogram generation unit 1302, and an evaluation value derivation unit 1303.
The response time information input unit 1301 inputs the response time information generated by the response time information generation unit 12.
The histogram generation unit 1302 generates a response time histogram (hereinafter also simply referred to as a histogram) indicating the relationship between the response time and the number of users based on the response time information.
The evaluation value deriving unit 1303 derives an evaluation value from the histogram generated by the histogram generating unit 1302.
The categorization storage unit 14 stores the evaluation values derived by the categorization processing unit 13, and further, when a plurality of user characteristic categories are set based on the evaluation values, a plurality of user characteristic categories and evaluations The correspondence with the value is stored.
The category determination unit 15 determines which category of the plurality of user characteristic categories the user belongs from the response time of a specific user.

  In service engineering, a service providing system is positioned as a service medium. This not only provides a service, but also evaluates and measures the service, and proposes a model that feeds back to the system as user satisfaction. If the system can sense the evaluation of the user's service, the above problems will be solved.

  The reason why the system has not measured the evaluation and satisfaction level of users' services so far is that it was not clear what to sense. For example, even if a questionnaire menu is added to the user interface so as to obtain a user's evaluation directly, it is doubtful that a dissatisfied person will bother to answer this questionnaire. In addition, since the questionnaire is post-mortem, it does not represent satisfaction at the moment of use, and it tends to be an answer that departs from the truth with preconceptions.

  The user's satisfaction / dissatisfaction, the degree of interest, etc. appear in the behavior unconsciously, and if the behavior is evaluated, the user's satisfaction / dissatisfaction, the degree of interest, etc. can be captured. If it involves screen operation, how to touch the operation screen and the time required for operation differ between those who are interested and eager to use interactively and those who are not interested and tend to be slow, The person who can operate smoothly and the person who feels difficult to operate are different. For this reason, it is considered that the user's behavior unconsciously shows a tendency that reflects the user's characteristics and image such as the user's satisfaction / dissatisfaction, the degree of interest, and the system being easy to operate / hard to operate.

  In the present embodiment, category setting for measuring user satisfaction is performed by measuring the behavior of the user of the Web service. A service using the Web is configured by a simple protocol such as a request by a mouse operation and display of a screen of the result. Paying attention to the response time (screen viewing time) from when the screen is displayed until the next action is taken, it is aimed at categorizing and discriminating users from this time.

Next, the hardware configuration of the categorization / discrimination device 1 will be described.
FIG. 12 is a diagram illustrating a hardware configuration example of the categorization / discrimination device 1.
In FIG. 12, the categorization / discrimination device 1 includes a CPU (Central Processing Unit) 137 that executes a program. The CPU 137 is connected via a bus 138 to a ROM (Read Only Memory) 139, a RAM (Random Access Memory) 140, a communication board 144, a CRT (Cathode Ray Tube) display device 141, a K / B 142, a mouse 143, and an FDD (FlexibleDrivableD). 145, a magnetic disk device 146, a CDD (Compact Disk Drive) 186, a printer device 187, and a scanner device 188.
The RAM is an example of a volatile memory. ROM, FDD, CDD, magnetic disk device, and optical disk device are examples of nonvolatile memory. These are examples of the categorization storage unit 14.
The communication board 144 may be connected to the FAX machine 310, the telephone device 320, the LAN 105, or the like.

Here, the communication board is not limited to the LAN 105, and may be directly connected to the Internet or a WAN (Wide Area Network) such as ISDN. In the present embodiment, communication with the server 2 can be performed via the Internet, LAN, or WAN.
The magnetic disk device 146 stores an operating system (OS) 147, a window system 148, a program group 149, and a file group 150. The program group is executed by the CPU 137, the OS 147, and the window system 148.

The program group 149 stores a program for executing a function described as “˜unit” in the description in this specification. The program is read and executed by the CPU.
In the file group 150, for example, what is described as “response information”, “histogram”, “evaluation value”, and “category discrimination result” are stored as files.
In addition, arrows in the flowchart mainly indicate data input / output, and for the data input / output, the data is a magnetic disk device, FD (Flexible Disk), optical disk, CD (compact disk), MD (mini disk). And other recording media such as a DVD (Digital Versatile Disk). Alternatively, it is transmitted through a signal line or other transmission medium.

  Further, what is described as “˜unit” may be realized by firmware stored in the ROM 139. Alternatively, it may be implemented by software alone, hardware alone, a combination of software and hardware, or a combination of firmware.

  The program is also stored by using a recording device such as a magnetic disk device, an FD (Flexible Disk), an optical disc, a CD (Compact Disc), an MD (Mini Disc), a DVD (Digital Versatile Disk) or the like. It does not matter.

Next, the operation will be described.
The operation unit 32 senses the operation of the client 3 by the user, and issues a processing request to the control unit 31. For example, there is a case where the user clicks an icon displayed on the display unit 33 in advance with a mouse and requests display of a Web page connected to the icon. The control unit 31 transmits a Web request to the server 2 via the network interface 34.
The server 2 receives a Web request via the network interface 24, the Web control unit 21 searches for the corresponding Web page from the storage unit 22, sends the content to the client 3 via the network interface 24, and simultaneously accesses the log 23. Record what happened.
In the client 3, the control unit 31 receives the content via the network interface 34, and prompts the display unit 33 to display the content of the Web page. When the display unit 33 displays the page on the display screen, one request of the user is completed.
This series of operations is repeated until the user achieves the purpose, and the user's operation is recorded in the log 23 each time.

  Next, an operation example of the categorization / discrimination device 1 will be described with reference to the flowchart of FIG.

First, in step S <b> 201, the communication unit 11 of the categorization / discrimination device 1 receives log information from the log 23 of the server 2.
The log information is a record including data such as (1) session ID, (2) time, (3) screen ID, and (4) user ID. Here, (1) the session ID is a unique code given when a certain user performs a series of operations, and (2) the time is the time when the Web control unit 21 receives the request. (3) The screen ID is a unique code for identifying the requested screen, and (4) the user ID is a unique code for identifying the user who has performed a series of operations.
The log information records in time series that a plurality of screens have been displayed for a plurality of users.

  Next, in step S202, the response time information generation unit 12 generates response time information from the log information. The response time information shows response times of a plurality of users for each screen ID. Details of the response time information generation procedure will be described later.

  Next, in step S203, the response time information input unit 1301 of the categorization processing unit 13 inputs the response time information (response time information input step).

Next, in step S204, the histogram generation unit 1302 of the categorization processing unit 13 generates a response time histogram (histogram generation step).
The response time information is information indicating response times of a plurality of users for each screen ID, and a histogram indicating the relationship between the response time and the number of users can be generated from the response time information. Details of the response time histogram generation procedure will be described later.

Next, in step S205, the evaluation value deriving unit 1303 of the categorization processing unit 13 supports the histogram generated in step S204 for a plurality of user characteristic categories representing user characteristics for specific data (viewing screen data). The average value (μ), the variance value (σ), and the ratio (α) of each normal distribution are derived as evaluation values (evaluation value deriving step). The number of normal distributions composing the histogram is determined in advance.
In this embodiment, an example will be described in which a histogram is regarded as a combination of three normal distributions.
This is because of the relationship with response time, “users who are interested and enthusiastically operate interactively and are satisfied with the service (response time is fast)” and “the operation is slow because there is not much interest. By the way, it is assumed to be classified into three user characteristic categories: “Users who are not satisfied with the service (slow response time)” and “None of them (no response time is characteristic)” Therefore, assuming that the histogram is a combination of three normal distributions, the evaluation values of the respective normal distributions are derived. Assuming that the histogram is a combination of three normal distributions, three evaluation values (average value (μ), variance value (σ), and ratio (α)) are derived for each normal distribution. Nine evaluation values are derived.
When step S205 is executed once, three normal distribution evaluation values (9) are derived from a histogram indicating the relationship between the response time and the number of users for one browsing screen data. When there are a plurality of screen IDs in the log information acquired from the log 23, step S205 is executed for the number of browsing screen data (number of screen IDs). Details of the evaluation value derivation procedure will be described later.

  Finally, in step S206, the evaluation value deriving unit 1303 of the categorization processing unit 13 stores the derived evaluation value in the categorization storage unit 14.

Next, details of a process of generating response time information from log information, a process of generating a histogram from response information, and a process of deriving an evaluation value from the histogram will be described with reference to FIG.
As described above, the log information includes (1) session ID, (2) time, (3) screen ID, and (4) user ID.
When this log is sorted in the order of (1) session ID and (2) time, the record order is in accordance with the operation order for each user. This is called WORK1.
Next, in the record of the same user, the browsing time of the screen corresponding to each record can be obtained from the difference between the time of the record on the screen and the time of the next record. However, when the session ID of the next record is different from the record of the screen, the browsing time is set to NULL and excluded from the subsequent aggregation. That is, the browsing time for each screen is calculated for each user. Here, the browsing time is the time taken to move from one screen to the next screen, and can be considered as the response time for a certain screen. Then, after calculating the browsing time, a file having a record including the screen ID and the browsing time is created. This is called WORK2.

Next, from the WORK2 file, the number of records having the same viewing time for a specific screen is tabulated as a histogram. The screen browsing time is set to y _i , the number of users of the browsing time is set to frequency G (y _i ), placed in the categorization storage unit 14, and used in subsequent processing.
In addition, when the web control unit 21 outputs the browsing time of each screen directly to the log 23, G (y _i ) may be obtained using that. In this case, the response time information generation unit 12 is not necessary.

When the screen browsing time is y _i and the number of users of the browsing time is the frequency G (y _i ), the probability density function g (y _i ) can be expressed by the following equation.

This is obtained and placed in the categorization storage unit 14.
Here, a probability density function f (y _i ) is introduced as a categorization model. This f (y _i ) is expressed by the following mathematical formula.

However, here, μ ₁ , μ ₂ , μ ₃ and σ ₁ ² , σ ₂ ² , σ ₃ ² are distributions of users in categories _{１ 1} , Π ₂ , and Π ₃ , respectively. Mean and variance. α ₁ , α ₂ , and α ₃ are ratios occupied by the respective categories, and Σα ₁ = 1.
This equation (1.2) assumes that the user belongs to one of the groups having three normal distributions.
By obtaining f (y _i ) approximate to the observed g (y _i ), the user can be categorized into three groups Π ₁ , Π ₂ , and Π ₃ .
The approximation may be performed by deriving μ ₁ , μ ₂ , μ ₃ and σ ₁ ² , σ ₂ ² , σ ₃ ² , α ₁ , α ₂ , α ₃ that minimize χ ² . That is, in the following formula, the above nine parameter combinations that minimize χ ² are determined by trial.

Specifically, assuming the range of possible values for each parameter, an 18-stage loop (if α _i is determined, one is determined automatically) and the calculation of equation (1.3) is performed. repeat. The finer the accuracy of the parameter to be tested, the better the approximation of f (y _i ), but this accuracy is a design matter in implementation.
Μ ₁ , μ ₂ , μ ₃ and σ ₁ ² , σ ₂ ² , σ ₃ ² , α ₁ , α ₂ , α _{3 obtained} by this are placed in the categorization storage unit 14.
When performing the χ ² goodness-of-fit test for how much approximation has been performed, the equation (1.3) is obtained for the parameter determined above, and this may be set to a multiple represented by the following equation (4).

Here, χ ² is used, but the parameters of the approximate expression may be similarly obtained by the least square method.

  Through the above procedure, response time information is generated from the log information, a response time histogram indicating the relationship between the response time (browsing time) and the number of users is generated from the response time information, and a user characteristic category is generated from the response time histogram. Evaluation values (average value (μ), variance value (σ), ratio (α)) of each normal distribution are derived, and these evaluation values are stored in the categorization storage unit 14.

From the derived μ ₁ , μ ₂ , μ ₃ and σ ₁ ² , σ ₂ ² , σ ₃ ² , for example, “the user who is satisfied with the service (response time is fast)” is the smallest μ the user characteristic category Π _i with _i, "(there is no feature to response time) the user is neither" in the user-characteristic category Π _i with a maximum of σ _i ^2, "so much interest there is no operation is slow “Users who are not satisfied with the service (slow response time)” tend to be categorized into user characteristic categories _{ｉ i} having σ _i ² other than the above.

  In the following, the category of “users who are satisfied with the service” is also referred to as category 1, the category of “users who are not any” is also referred to as category 2, and “there is not so much interest and the operation tends to be slow. The category “users who are not satisfied with the service” is also referred to as category 3.

  The setting of the user characteristic category (association between the user characteristic category and the evaluation value) may be performed manually by the operator of the categorization / discrimination device 1 or automatically by the categorization / discrimination device 1. Good.

Here, “Non-None” may be approximated by the following expression using a characteristic having a large variance. Here, however, α ₃ is the ratio of “anyone”.

  Here, the experimental result which shows the relationship between the response time (viewing time) with respect to the user data (viewing screen data) described above and the user characteristic category will be described.

This experiment targets a system in which about 70 registered users access several times a week. Each time a screen is displayed to the user on the Web server, the time is recorded up to the second unit. From this record, it is possible to know how many seconds each screen was displayed (how many seconds the user response time was). .
Note that the user's PC and Web server are connected via a LAN, and the time until information is displayed on the screen is stable and has no delay.
Logs were collected for one month when the user became accustomed to the operation three months after the system started operation.
FIG. 8 shows a histogram of the distribution g (y) when the display time is y for a specific screen on which about 700 displays have been performed in one month. Although 70 results are obtained by random operation, the distribution is not a normal distribution as shown in FIG.
It can be seen from the graph of FIG. 8 that about 70 users are not a uniform group, but are composed of several groups with different response times (viewing times).

  Here, as described above, it is assumed that this histogram is a superposition of three normal distributions representing three groups, and from the above equations (1.1), (1.2), and (1.3), 3 FIG. 9 shows the results of calculating the average value (μ), the variance value (σ), and the ratio (α) for each of the two normal distributions.

Then, the frequency obtained from the equation (1.2) with the parameters shown in FIG. FIG. 10 shows a superposition of a graph showing group 1, a graph showing group 2, a graph showing group 3, and a graph of group 1 to group 3. According to FIG. 10, it can be seen that the group is divided into a group 1 that moves to the next page in a relatively short browsing time, a group 3 that requires a long browsing time, and a group 2 that has no characteristics in the browsing time.
Observed observation frequency (histogram) (Fig. 8), formula (1.2) and theoretical frequency (superposition) (Fig. 10) obtained from the parameters of Fig. 9 are superimposed on the graph as shown in Fig. 11. It can be seen that the theoretical frequency represents the characteristics of frequency.
This is subjected to a χ ² fitness test according to equation (1.3).
The result of calculating χ ² from the equation (1.3) using the parameters of FIG. 9 is χ ² = 99.11.
Since this measurement has a frequency of 101 terms from 0 to 100 seconds, the degree of freedom ν is 100. From the χ ² distribution table, this example in which the measured data and the hypothetical data match at a significance level of 10% is not rejected.

  Next, the processing after the user characteristic category is set will be described with reference to the flowchart of FIG.

First, in step S <b> 301, the communication unit 11 obtains information indicating response time for specific browsing screen data for a specific user, for example, a user who is currently receiving service from the server 2, from the log 23 of the server 2. Receive (notification reception step).
Next, in step S302, the category determination unit 15 receives information indicating the response time of the user from the communication unit 11, and evaluates values (average value (μ), variance value ( σ) and ratio (α)) are read from the categorization storage unit 14. As described above, when three user characteristic categories are set, nine evaluation values of three normal distributions are read out.
Next, in step S303, the category determination unit 15 determines the user characteristic category to which the user corresponds from the evaluation value of each normal distribution read in step S302 and the response time of the specific user (category) Determination step). The detailed procedure for category determination will be described later.
Next, in step S304, the category determination unit 15 outputs the determined category. For example, the determined category may be displayed on a CRT display device or the like not shown in FIG. 2, or the category may be notified to the server 2 via the communication unit 11.

FIG. 5 is a diagram illustrating an example of the category discrimination operation.
The parameters α ₁ , α ₂ , and α ₃ obtained by the categorization processing unit 13 can be regarded as the prior probabilities w _i for the newly observed z. Here, the new observed value z means a response time (viewing time) for a specific screen of a specific user.
The posterior probability w ′ _i in Bayesian estimation is as shown in the equation.

However, f _i (z) is as shown below.

Observe z and classify z into the one with the largest posterior probability w ′ _i . That is, by observing z and obtaining _i according to the following formula, category _i corresponding to _i becomes a user characteristic category into which the user is classified.

In this way, the category determination unit 15 performs category determination, and the determination result is returned to the Web control unit 21 of the server 2 through i as a result of the determination, for example, as shown in FIG. Return as.
When equation (1.4) is used, category discrimination is performed according to the following equation.

  As described above, the categorization / discrimination device according to the present embodiment inputs response time information indicating response times of a plurality of users for specific data, and based on the response time information, the response time and the number of users. A response time histogram showing the relationship is generated, and the response time histogram is a composite of a plurality of normal distributions corresponding to a plurality of user characteristic categories representing user characteristics for specific data, and the average value of each normal distribution and A variance value is derived for setting a plurality of user characteristic categories.

  In other words, a viewing time histogram is generated from the viewing time of the user's screen in the system that prompts the operation by displaying information on the user's facing screen. It is a composite of the distributions of the three categories of “persons who are”, “unsatisfied people who are not so interested and tend to be slow”, and “people who are not any”. An approximate value of the ratio is derived.

  In addition, the categorization / discrimination device according to the present embodiment further specifies the specific data after the plurality of user characteristic categories are set based on the average value and the variance value of the plurality of derived normal distributions. The response time of the specified user is notified, and the user characteristics of the specific user for the specific data are determined using the notified response time of the specific user and the average value and variance value of multiple normal distributions. It is characterized in that it belongs to a plurality of user characteristic categories.

  In other words, based on the current user's browsing time from the system that prompts the operation by displaying information on the screen facing the user, the ratio of the category of the categorization result is the prior probability, and depending on the average and variance of each category Users who are currently using the system by determining the probability density at the current user's browsing time, comparing this value with the prior probability, and determining that the probability of belonging to the category with the highest value is the highest. However, the probability of being in any of the categories of “satisfied people who are interested and eager to use interactively”, “unsatisfied people who are not so interested and tend to be sluggish”, and “none” It is characterized by determining whether or not is high and returning the result.

  Further, the present embodiment is characterized in that it is determined by Bayesian estimation which user characteristic of a specific user for specific data belongs to which of a plurality of user characteristic categories.

  Further, it is characterized by approximating “anyone” as a steady value of a uniform distribution, and performing categorization and discrimination.

According to the present embodiment, the evaluation value for setting the user characteristic category is calculated based on the response time (viewing time) with respect to the data representing the actual behavior of the user with respect to the data, User characteristics such as user satisfaction / dissatisfaction with the services that appear unconsciously in the user's behavior, easy to operate / hard to operate, because user characteristics are categorized by response time and evaluation value for data Can be accurately identified.
As a result, for example, when manually supporting a user who is difficult to operate with ATM, the probability of belonging to which category is high according to the viewing time of the screen is determined by Bayesian estimation, and “the operation becomes slow It is possible to support users who have a high probability of “prone users”.

  In addition, it is not necessary to measure biological information such as the viewpoint, pupil, α wave, etc., and it is not necessary to increase the scale of the apparatus, and the user satisfaction can be measured at a low cost.

Embodiment 2. FIG.
In the present embodiment, an example will be described in which an evaluation value for data is updated based on a new observation value for specific data.

  The configurations of the categorization / discrimination device 1, the server 2, and the client 3 according to the present embodiment are the same as those shown in FIG.

In the present embodiment, the communication unit 11 receives new response time information (new observation value z) for a certain browsing screen data (screen ID) from the log 23, and the evaluation value deriving unit 103 derives the previous one. The evaluation values ((average value (μ), variance value (σ), ratio (α)) of the browse screen data are updated using new response time information (new observation value z).
Specifically, the evaluation value deriving unit 1303 reflects the new observation value z in G (y _i ) and minimizes the expression (1.3). The parameters μ ₁ , μ ₂ , μ ₃ (category 1, 2, 3), and σ ₁ ² , σ ₂ ² , σ ₃ ² (category values of categories ₁ , ₂ , ₃ ), α ₁ , α ₂ , α ₃ (category 1, ₂ , ₃ ratio) ) Can be updated to update the prior probability for discrimination. Repeating this will enrich the population and improve the accuracy of prior probabilities. Specifically, a new observation value is reflected in the evaluation value by executing the processing of the evaluation value deriving unit 1303 at an appropriate interval.

  As described above, in the present embodiment, after deriving the average value and the variance value of a plurality of normal distributions, a notification of a response time of a specific user for specific data is received, and a plurality of times are determined based on the notified response time. The average value and the variance value of the normal distribution are updated.

  In other words, the accuracy of prior probabilities for discrimination is improved by recalculating and updating the average and variance of categorization and the ratio of each category as appropriate by adding the viewing time of the screen of a new user. It is characterized by that.

  Thereby, by updating the evaluation value from time to time. Even if the tendency of user characteristics changes with time, accurate categorization can be maintained, and support for users can be enhanced.

Embodiment 3 FIG.
In this embodiment, in a system in which a user operates a terminal, an example of prompting intervention / support by an operator when the user can receive a service when support by the operator is possible by a videophone as necessary. To do.

FIG. 4 shows a system configuration example according to the present embodiment.
In FIG. 4, an operator terminal 4 is added as compared to the configuration of FIG. The operator terminal 4 is a terminal device used by an operator who supports a service user. The operator terminal 4 may be communicable with the client 3. When the operator terminal 4 receives a support instruction message for instructing support for the user from the communication unit 11 of the categorization / discrimination device 1, the operator supports the user of the client 3. The support method is, for example, performing an operation instruction by a videophone. The operator terminal 4 is an example of a support device.
In the present embodiment, the communication unit 11 can communicate with the operator terminal 4 and corresponds to an example of a support device communication unit.

Next, the operation will be described.
First, according to the procedure shown in FIGS. 3 and 5, the category determination unit 15 receives the response time (viewing time) information for the specific screen of the user who uses the client 3 and uses the user based on this information. It is determined which user characteristic category the user characteristic belongs to.
If it is determined that the user characteristic of the user belongs to a specific user characteristic category, for example, category 2 or category 3 of the above three user characteristic categories, the user's interest is low and the operation is slow. The support instruction message is generated to instruct the operator to support the user, assuming that the operation is unsuccessful or the operation is taking a long time.
And the communication part 11 can transmit this assistance instruction | indication message to the operator terminal 4, and can urge the operator to assist a user.

  As described above, the categorization / discrimination device according to the present embodiment is specified when the user characteristic of a specific user is determined to belong to a specific user characteristic category among a plurality of user characteristic categories. A support instruction message for instructing support for a user is generated, and the support instruction message is transmitted to an operator terminal (support apparatus).

  In other words, if the result of the identification of the user who is currently using the service is “unsatisfied person who is not so interested and tends to be slow” or “nobody”, call the operator and It is characterized by encouraging support.

  In this way, by encouraging the support by the operator, it is possible to enhance support for users who find it difficult to operate the screen.

Embodiment 4 FIG.
In the present embodiment, an example will be described in which the content of data to be displayed on the client 3 is switched according to the category determination result.

The system configuration diagram in the present embodiment is the same as FIG.
However, in the present embodiment, the storage unit 22 of the server 2 stores a plurality of versions of data for the same data content. For example, browsing screen data with the same display contents but with a large display size and a browsing screen data with a small display size and a version with explanations only written in text It has multiple versions of data in the form of screen data and a version of browsing screen data whose explanation is illustrated. In the present embodiment, the server 2 is an example of a data providing device.
Moreover, the category discrimination | determination part 15 instruct | indicates to provide the said user the data (browsing screen data) of another version different from the data (browsing screen data) currently provided to the specific user in a specific case. Generate another version provision instruction message. Further, the communication unit 11 transmits another version provision instruction message to the server 2. In the present embodiment, the communication unit 11 corresponds to an example of a data providing device communication unit.

Next, the operation will be described.
First, according to the procedure shown in FIGS. 3 and 5, the category determination unit 15 receives the response time (viewing time) information for the specific screen of the user who uses the client 3 and uses the user based on this information. It is determined which user characteristic category the user characteristic belongs to.
If it is determined that the user characteristic of the user belongs to a specific user characteristic category, for example, category 2 or category 3 among the above three user characteristic categories, the user's interest is low and the operation is slow. Therefore, another version providing instruction message for instructing transmission of another version of data is generated on the assumption that the operation has been taking a long time.
Then, the communication unit 11 transmits this separate version provision instruction message to the server 2, and the server 2 switches the version data that is easier to understand and operate to the current viewing screen data or the next viewing screen data. The display screen data of the client 3 can be switched and transmitted to display easy-to-understand and easy-to-operate display screen data.

  The categorization / discrimination device according to the present embodiment provides a specific user with a specific user when it is determined that the user characteristic of the specific user belongs to the specific user characteristic category of the plurality of user characteristic categories. Generating another version providing instruction message for instructing a specific user to provide another version of data different from the currently provided data, and transmitting the different version providing instruction message to the data providing apparatus; .

  In other words, if the result of the discrimination of the user who is currently using the service becomes “unsatisfied person who is not so interested and tends to be slow”, “person who is not any”, the user faces The system is characterized in that information is displayed on the screen and the result is notified to a system that prompts an operation to prompt display of more easily understood information.

  As described above, according to the present embodiment, a user who has a high probability of belonging to category 2 or category 3 on a certain screen is more easily understood than the standard screen on the current screen or the next screen. It is possible to switch to the version and enhance support for users who find it difficult to operate the screen.

Embodiment 5 FIG.
In the present embodiment, an example will be described in which a category discrimination result is analyzed, data having some problem is extracted, and improvement of the data is promoted.

FIG. 7 shows a system configuration example according to the present embodiment.
In FIG. 7, compared to FIG. 1, a determination result analysis unit 16 is added.
In the present embodiment, the category determination unit 15 records the category determination result in the categorization storage unit 14 each time the category determination process shown in FIGS. 3 and 5 is performed.
Then, the discrimination result analysis unit 16 analyzes the category discrimination result stored in the categorization storage unit 14, and outputs a warning message when the ratio of the specific user characteristic category is equal to or higher than a predetermined level.

Specifically, the discrimination result analysis unit 16 has α ₂ or α ₃ (category 2 ratio or category 3 ratio) exceeding 0.5, for example, when μ ₁ ≦ μ ₂ and μ ₃ . Such a system has more users who are sluggish in operation than category 1 which can be operated smoothly, and it can be determined that there is a problem in the system. That is, the discrimination result analysis unit 16 refers to the ratio α between categories for each data (display screen), and when the category 2 or the category 3 exceeds 0.5, for example, many users can smoothly In this case, warning data is output to promote improvement of the data (display screen).

  As described above, the categorization / discrimination device according to the present embodiment analyzes the category discrimination results accumulated and recorded, and the ratio of specific user characteristic categories among a plurality of user characteristic categories is a predetermined level. In the case described above, a warning message is output.

  In other words, as a result of analyzing the results of categorization, if the ratio of the category of “unsatisfied people who are not so interested and tend to be sluggish” or “none” is over 50%, there is a problem in the system This is characterized in that improvement of data that outputs a warning message is promoted.

  As a result, improvement of data with poor operability for the user is promoted. As a result, data with improved operability can be provided to the user, and the convenience of the user can be enhanced. .

FIG. 3 is a diagram illustrating an example of a system configuration according to the first embodiment. FIG. 6 is a diagram illustrating an operation example of the categorization / discrimination device according to the first embodiment. FIG. 6 is a diagram illustrating an operation example of the categorization / discrimination device according to the first embodiment. FIG. 6 is a diagram illustrating an operation example of the categorization / discrimination device according to the first embodiment. FIG. 6 is a diagram illustrating an operation example of the categorization / discrimination device according to the first embodiment. FIG. 6 is a diagram showing a system configuration example according to the third and fourth embodiments. FIG. 10 is a diagram showing a system configuration example according to a fifth embodiment. FIG. 6 is a histogram diagram in an experiment according to the first embodiment. The figure which shows the average value in the experiment which concerns on Embodiment 1, a dispersion value, and a ratio. FIG. 5 is a diagram showing three normal distribution graphs and a superposition graph in the experiment according to the first embodiment. FIG. 6 is a diagram showing a histogram and a superposition graph in the experiment according to the first embodiment. The figure which shows the hardware structural example of the categorization / discrimination apparatus which concerns on Embodiment 1-5.

Explanation of symbols

  1 categorization / discrimination device, 2 server, 3 client, 4 operator terminal, 11 communication unit, 12 response time information generation unit, 13 categorization processing unit, 14 categorization storage unit, 15 category discrimination unit, 16 discrimination result analysis unit , 21 Web control unit, 22 storage unit, 23 log, 24 network interface, 31 control unit, 32 operation unit, 33 display unit, 34 network interface, 1301 response time information input unit, 1302 histogram generation unit, 1303 evaluation value derivation unit .

Claims (14)

A response time information input unit for inputting response time information indicating response times of a plurality of users for specific data;
Based on the response time information, a histogram generation unit that generates a response time histogram indicating the relationship between the response time and the number of users,
The response time histogram is a composite of a plurality of normal distributions corresponding to a plurality of user characteristic categories representing user characteristics for the specific data, and the average value and the variance value of each normal distribution are used as the plurality of users. An information processing apparatus comprising: an evaluation value deriving unit derived for setting a characteristic category. The information processing apparatus further includes:
After the plurality of user characteristic categories are set based on an average value and a variance value of a plurality of normal distributions derived by the evaluation value deriving unit, a response time of a specific user for the specific data is notified. received,
Using the notified response time of the specific user and the average value and variance value of a plurality of normal distributions derived by the evaluation value deriving unit, the user characteristics of the specific user with respect to the specific data The information processing apparatus according to claim 1, further comprising: a category determination unit that determines which one of the plurality of user characteristic categories belongs to. The category discriminating unit
The information processing apparatus according to claim 2, wherein a user characteristic of the specific user with respect to the specific data belongs to which of the plurality of user characteristic categories by Bayesian estimation. The evaluation value deriving unit
After derivation of the average value and variance value of a plurality of normal distributions, the response time of a specific user for the specific data is notified, and the average value and variance value of the plurality of normal distributions based on the notified response time The information processing apparatus according to claim 1, wherein the information processing apparatus is updated. The information processing apparatus further includes:
A support device communication unit that communicates with a support device that supports data users;
The category discriminating unit
When it is determined that the user characteristic of the specific user belongs to a specific user characteristic category of the plurality of user characteristic categories, a support instruction message is generated to instruct support for the specific user. ,
The support device communication unit
The information processing apparatus according to claim 2, wherein the support instruction message generated by the category determination unit is transmitted to the support apparatus. The information processing apparatus further includes:
A data providing device communication unit that communicates with a data providing device that provides data to a data user;
The category discriminating unit
When it is determined that the user characteristic of the specific user belongs to a specific user characteristic category of the plurality of user characteristic categories, a different version different from the data currently provided to the specific user Generating another version provision instruction message instructing the specific user to provide the data of
The data providing device communication unit includes:
The information processing apparatus according to claim 2, wherein another version providing instruction message generated by the category determining unit is transmitted to the data providing apparatus. The information processing apparatus further includes:
A discrimination result recording unit for accumulating and recording a category discrimination result by the category discrimination unit;
Analyzing the category discrimination result recorded in the discrimination result recording unit, and outputting a warning message when a ratio of a specific user characteristic category among the plurality of user characteristic categories is a predetermined level or more The information processing apparatus according to claim 2, further comprising an analysis unit. The response time information input unit
Enter information indicating the time until multiple users transition from browsing specific browsing screen data to browsing the next browsing screen data, as response time information,
The evaluation value derivation unit is a composition of a plurality of normal distributions corresponding to a plurality of user characteristic categories whose response time histograms represent the degree of interest of the user with respect to the content of the specific browsing screen data, The information processing apparatus according to claim 1, wherein an average value and a variance value are derived for setting the plurality of user characteristic categories. The information processing apparatus further includes:
After the plurality of user characteristic categories are set based on an average value and a variance value of a plurality of normal distributions derived by the evaluation value deriving unit, a specific user follows the browsing of the specific browsing screen data. The time to shift to the browsing of the browsing screen data is notified as the response time of the specific user,
Using the notified response time of the specific user and the average value and variance value of a plurality of normal distributions derived by the evaluation value deriving unit, the specific user for the content of the specific browsing screen data The information processing apparatus according to claim 8, further comprising: a category determination unit that determines which one of the plurality of user characteristic categories belongs to the user. The category discriminating unit
The degree of interest of the specific user with respect to the content of the specific browsing screen data is “high interest and satisfied with the content of the browsing screen data”, “low interest and dissatisfaction with the content of the browsing screen data” and “ The information processing apparatus according to claim 9, wherein the information processing apparatus determines which of the three user characteristic categories “not” belongs. A response time information input step for inputting response time information indicating response times of a plurality of users for specific data;
A histogram generation step for generating a response time histogram indicating the relationship between the response time and the number of users based on the response time information;
The response time histogram is a composite of a plurality of normal distributions corresponding to a plurality of user characteristic categories representing user characteristics for the specific data, and the average value and the variance value of each normal distribution are used as the plurality of users. And an evaluation value deriving step derived for setting the characteristic category. The information processing method further includes:
After the plurality of user characteristic categories are set based on an average value and a variance value of a plurality of normal distributions derived by the evaluation value deriving step, a response time of a specific user for the specific data is notified. A notification receiving step,
Using the notified response time of the specific user and the average value and variance value of a plurality of normal distributions derived by the evaluation value deriving step, the user characteristics of the specific user with respect to the specific data The information processing method according to claim 11, further comprising: a category determination step of determining which of the plurality of user characteristic categories belongs to. Response time information input processing for inputting response time information indicating response times of a plurality of users for specific data;
Histogram generation processing for generating a response time histogram indicating the relationship between the response time and the number of users based on the response time information;
The response time histogram is a composite of a plurality of normal distributions corresponding to a plurality of user characteristic categories representing user characteristics for the specific data, and the average value and the variance value of each normal distribution are used as the plurality of users. A program that causes a computer to execute an evaluation value deriving process derived for setting a characteristic category. The program further includes:
After the plurality of user characteristic categories are set based on an average value and a variance value of a plurality of normal distributions derived by the evaluation value derivation process, a response time of a specific user for the specific data is notified. Receive notifications,
Using the notified response time of the specific user and the average value and variance value of a plurality of normal distributions derived by the evaluation value deriving process, the user characteristics of the specific user for the specific data 14. The program according to claim 13, which causes a computer to execute category discrimination processing for discriminating which one of the plurality of user characteristic categories belongs to.

Images