JP7295821B2 - Information processing device, information processing method and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Conventionally, techniques for predicting various demands have been provided. For example, techniques have been provided for determining user needs information based on user search data including at least POI (Point of Interest) data.

JP 2017-16625 A

However, with the conventional technology described above, it is not always possible to improve the prediction accuracy when predicting demand from user's search behavior. For example, in the conventional technology described above, the user's needs information including at least the position of occurrence of the need is determined based on the user's search data including POI data, but the search data may contain a lot of noise. Conceivable.

For this reason, with the above-described conventional technology, it is not always possible to improve the prediction accuracy when predicting the demand from the user's search behavior.

The present application has been made in view of the above, and an object thereof is to provide an information processing device, an information processing method, and an information processing program that can improve the prediction accuracy when predicting demand from user's search behavior. and

An information processing apparatus according to the present application includes a calculation unit that calculates a weight value corresponding to a search mode indicating search behavior by a user; and an estimation unit that estimates the importance of performing the search action.

According to one aspect of the embodiment, it is possible to improve the prediction accuracy when predicting demand from user's search behavior.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating an example of demand level prediction according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of an information processing system according to the embodiment; FIG. 4 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; FIG. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment; 6 is a diagram illustrating an example of a query information storage unit according to the embodiment; FIG. 7 is a diagram illustrating an example of a search history storage unit according to the embodiment; FIG. 8 is a diagram illustrating an example of a score information storage unit according to the embodiment; FIG. 9 is a diagram illustrating an example of a prediction result storage unit according to the embodiment; FIG. FIG. 10 is a flowchart illustrating an information processing procedure according to the embodiment; FIG. 11 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Hereinafter, modes for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. In addition, in the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Overview of information processing according to the embodiment]
First, an overview of information processing according to the embodiment will be described along the premise. As in the conventional technology described above, there is known a technique for predicting what kind of demand is in what kind of place from search history. For example, there is a technology that visualizes the demand level of the search target in the search behavior based on the search behavior indicated in the search history and the location information associated with this search behavior.

However, since various biases are applied to the user's search behavior according to the search mode, the above-described conventional technology, which does not take such bias into consideration, cannot predict the demand from the user's search behavior. cannot be increased.

For example, when a user, who tends not to search at all, searches for a predetermined target, this search behavior of searching for the predetermined target is an important search behavior for predicting demand for users. I can say. Also, for example, when a user uses a search query that tends to be difficult to use in searches, the search behavior of searching with this search query is an important search behavior in predicting user demand. I can say. In addition, for example, when a search is performed in a place where search behavior is generally considered difficult, such as in a crowd or at an intersection, the search behavior in such a place corresponds to this location. It can be said that search behavior is important for predicting demand in an area.

In this way, the user's search behavior is biased to estimate the importance of the search behavior in predicting demand. However, it does not take into account how much bias is applied according to the search aspect that indicates search behavior. Therefore, in the above conventional technology, for example, noise such as search behavior unrelated to demand (search behavior with low importance to demand) is included, so it cannot be said that the prediction accuracy can be improved. There is

Therefore, in the present embodiment, by considering how much bias is applied to the search behavior of the user according to the search mode indicating this search behavior, the importance of this search behavior is determined. I got the idea of estimating the importance of predicting demand.

Specifically, in this embodiment, the following information processing is performed as the information processing according to the embodiment. For example, in the present embodiment, a weight value corresponding to a search mode indicating search behavior by a user is calculated, and based on the calculated weight value, the importance of the search behavior being performed in the state indicated by this search mode is calculated. to estimate Then, in this embodiment, based on the estimated importance, the demand level for the search target in the user's search behavior is predicted. For this reason, in the present embodiment, an index value (that is, a weight value) that indicates the bias, such as how much the search behavior is biased, according to the search mode indicating the search behavior of the user is corrected.

In addition, in the present embodiment, as an example of a search mode indicating a search behavior by a user, a search frequency, which is the frequency with which a search behavior is performed by a user, and a search query used in the search behavior by a user, Focusing on the frequency of use, which is the frequency of use, the difficulty of search behavior at the search location where the search behavior was performed by the user, and the type of terminal device used in the search behavior by the user there is On the other hand, the search mode that can be targeted by the information processing according to the embodiment is not limited to the above example, and any search mode can be used as long as the degree of bias (weight value) applied to the search behavior can be calculated. Can be targeted.

[2. Information processing system according to the embodiment]
Prior to describing information processing according to the embodiment, an information processing system according to the embodiment will be described using FIG. FIG. 3 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. The information processing system 1 according to the embodiment includes an external device 30 and an information processing device 100, as shown in FIG. The external device 30 and the information processing device 100 are communicably connected via a network N by wire or wirelessly. The information processing system 1 shown in FIG. 3 may include a plurality of external devices 30 and a plurality of information processing devices 100 .

The external device 30 is a server device corresponding to a predetermined service. For example, the external device 30 is a server device that provides a predetermined shopping service (for example, a shopping service such as an electronic mall). Also, the external device 30 may be a server device that supports a predetermined search service (search engine). For this reason, the information processing apparatus 100 according to the embodiment acquires a history of search behavior (search history) performed by the user in a predetermined shopping service or a predetermined search service from the external device 30. can be done.

The information processing device 100 is a device that performs information processing according to the above-described embodiments, and is realized by a server device, a cloud system, or the like. In this embodiment, the information processing device 100 is assumed to be a server device.

Although not shown in FIG. 2, the information processing system 1 according to the embodiment may also include an information processing terminal used by a user (end user). Such information processing terminals are, for example, smart phones, tablet terminals, notebook PCs (Personal Computers), desktop PCs, mobile phones, PDAs (Personal Digital Assistants), and the like.

[3. Example of information processing according to the embodiment]
From here, an example of information processing according to the embodiment will be described using FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 1 mainly uses a table TB to describe an example of information processing according to the embodiment. The information shown in the table TB corresponds to the later-described search history storage unit 123 (FIG. 7) and score information storage unit 124 (FIG. 8).

First, the user's search behavior shown in the table TB will be described. In table TB, "search history" is associated with "user ID (identifier)", and "history ID (identifier)", "date and time information", "query It includes items such as "information" and "location information".

"User ID" indicates identification information for identifying a user who performed a search action identified by the corresponding "history ID". The "history ID" indicates identification information for identifying a search action, with a set of corresponding "date and time information", "query information", and "location information" as one search action. “Date and time information” is information regarding the date and time when the search action identified by the corresponding “history ID” was performed. "Query information" is a keyword indicating a search target in the search behavior identified by the corresponding "history ID". “Position information” is information about the position (search location) where the search action identified by the corresponding “history ID” was performed.

That is, in the example of the table TB shown in FIG. 1, the user (user U1) identified by the user ID "U1" uses the search query "mask" at the date and time "DT11" and the location "LC11". An example of performing a search action of searching will be shown. Also, such a search action is described as "search action R1". Further, following this, in the example of the table TB shown in FIG. 1, the user U1 performs a search action R12 of searching using the search query "eye drops" at the date and time "DT12" and the search location "LC12". An example is given. In addition, the example of the table TB shown in FIG. 1 shows an example in which the user U2 performed a search action R21 of searching using the search query "mug cup" at the date and time "DT12" and the position "LC21".

Then, in such a state, the information processing apparatus 100 calculates a weight value corresponding to each search mode indicating the search action for each search action of the user (step S11). For example, the information processing apparatus 100 calculates a weight value corresponding to each search mode indicating one search action identified by the history ID.

Here, in the table TB, the "weight value" includes items such as "search frequency", "use frequency", "difficulty", and "terminal type". "Search frequency", "usage frequency", "difficulty", and "terminal type" are search modes targeted in the information processing according to the embodiment, and are examples of search modes indicating search behavior.

"Search frequency" is the frequency with which the user performs a search action. The "frequency of use" is the frequency with which the search query used in the search behavior of the user is used in searching. In other words, the "frequency of use" may be the tendency of use on the Internet (all users), or the tendency of use in the search behavior of each user. It may be a usage tendency of an individual. In this embodiment, the "frequency of use" is assumed to be the tendency of use on the Internet (all users).

"Difficulty" is the difficulty of performing the search action at the search location where the user performed the search action. "Terminal type" is the type of the terminal device (information processing terminal) used in the search behavior of the user.

For this reason, in step S11, the information processing apparatus 100 selects each search action identified by the history ID as a target for each search action such as "search frequency", "use frequency", "difficulty", and "terminal type". Identify what kind of situation each of the search modes is. Then, the information processing apparatus 100 calculates a weight value according to the specified situation. The weight value calculation will be described below with a focus on the search behavior R11 among the search behaviors of the user U1.

The information processing apparatus 100, for example, refers to the user information storage unit 121 (FIG. 5) to determine whether the user U1 performed the search action R11 under what "search frequency" (search tendency). Specify a search mode such as In the example of FIG. 1, the search frequency "X1 times/month" and the attribute information "attribute #1" are associated with the user U1. In this example, the information processing apparatus 100 specifies "X1 times/month" as the search frequency of the user U1, and specifies "attribute #1" as the attribute information of the user U1. The attribute information is information indicating various attributes such as the demographic attributes and psychographic attributes of the user, such as the user's sex, age, tastes and preferences.

Further, the information processing apparatus 100 refers to the query information storage unit 122, for example, to determine what kind of "frequency of use" (tendency of use) of the search query "mask" used by the user U1 in the search action R11 as a whole. ) to specify the search mode. Here, it is assumed that the information processing apparatus 100 has specified "Y 1 times/month" as the frequency of use of the search query "mask".

Further, the information processing apparatus 100, for example, refers to the user information storage unit 121 (FIG. 5) to determine what kind of "terminal type" information processing terminal the user U1 uses to perform the search action R11. Specify a search mode such as In the example of FIG. 1, the terminal type "type #1" is associated with user U1. This example shows an example in which information processing apparatus 100 identifies “type #1” as the type of information processing terminal used by user U1.

In addition, the information processing apparatus 100 identifies a search mode such as how difficult it is for the user U1 to perform the search action R11 in a place where the search action is performed. For example, based on the search location “LC11” where the search action R11 was performed and the difficulty score table shown in FIG. Identify how difficult the location is.

In the difficulty score table, various areas are associated with difficulty scores indicating how difficult it is to perform a search action in the area. Also, the higher the difficulty score, the more difficult it is to search in the corresponding area. For example, an intersection area is a high-risk area from the viewpoint of passers-by, moving objects such as automobiles, traffic lights, etc., and people cannot calmly search in such an area. Therefore, the intersection area is associated with the highest difficulty score of "10". On the other hand, the shop area is indoors, and it is considered that the search behavior can be performed relatively calmly. Therefore, the shop area is associated with a low difficulty score of "3".

Here, the information processing apparatus 100 determines what kind of objects and facilities the search location "LC11" includes in the area based on the search location "LC11" and the map information. Then, the information processing apparatus 100 compares the determined area with the difficulty score table to specify the difficulty score indicating how difficult it is to perform the search action R11 in the determined area. For example, the information processing apparatus 100 determines that the area corresponding to the search location "LC11" is the "intersection area" based on the search location "LC11" and the map information. Therefore, in this example, the information processing apparatus 100 compares the difficulty score table with the difficulty score table to specify "10" as the difficulty score of performing the search action R11 at the search location "LC11" that is included in the intersection area. do.

To summarize the examples so far, in FIG. The overall usage frequency (usage trend) of the search query “mask” used in R11 “Y1/month”, the difficulty score “10” that is the difficulty of performing the search action R11 at the search location “LC11”, The type “type #1” of the terminal device used for the search action R11 is specified.

In this example, the information processing apparatus 100 calculates a weight value according to the user U1's search frequency "X times/month". For example, the information processing apparatus 100 calculates a weight value according to the search frequency "X times/month" according to a rule that a higher weight value is calculated as the search frequency is lower. For example, it can be said that the more the search behavior is performed by a user with a lower search frequency, the higher the demand related to the search target for such user. That is, it can be said that search behavior performed by users with lower search frequency is more important search behavior in terms of predicting latent demands (real needs) by users. For this reason, by calculating a higher weight value as the search frequency is lower, it is possible to improve the prediction accuracy when predicting the demand from the user's search behavior.

An example of the table TB shows an example in which the information processing apparatus 100 calculates "WV111" as the weight value according to the search frequency "X times/month" of the user U1. Further, the information processing apparatus 100 may correct the weight value "WV111" according to the attribute #1 of the user U1. For example, it is known that search frequency differs depending on age. For example, the higher the age, the lower the search frequency tends to be. Therefore, for example, the information processing apparatus 100 can correct the weight value "WV111" according to the attribute #1 according to the rule that the older the age, the higher the weight value is used to correct the weight value.

Further, the information processing apparatus 100 calculates a weight value according to the overall use frequency "Y1/month" of the search query "mask" used in the search action R11. For example, the information processing apparatus 100 calculates a weight value according to the frequency of use “Y1/month” according to a rule that a higher weight value is calculated as the frequency of use is lower. For example, it can be said that as a search query with a lower frequency of use is used, there is a higher demand for search targets from users who have searched using this search query. In other words, it can be said that search behavior using search queries with lower frequency of use is more important search behavior in terms of predicting latent demand (real needs) by users. In short, the use of a search query that is rarely used means that the demand for the search target indicated by this search query is highly likely to be genuine. For this reason, by calculating a higher weight value as the frequency of use is lower, it is possible to improve the prediction accuracy when predicting demand from the search behavior of users.

The example of the table TB shows an example in which the information processing apparatus 100 calculates “WV112” as the weight value according to the overall use frequency “Y1/month” of the search query “mask” used in the search action R11. be

The information processing apparatus 100 also calculates a weight value corresponding to the difficulty score "10" indicating the difficulty of performing the search action R11 at the search location "LC11". For example, the information processing apparatus 100 calculates a weight value corresponding to a difficulty score of "10" according to a rule that the higher the difficulty score is, the higher the weight value is calculated. For example, if the search action is performed in a place where it is considered difficult to operate an information processing terminal such as a smartphone, such as an intersection or on the road, the user who performed the search action in such a place It can be said that there is a high demand for search targets. On the other hand, there is a possibility that search behavior in stores (indoors) such as cafes is performed only for killing time, regardless of demand. For this reason, it can be said that search behaviors performed in places with higher difficulty are more important search behaviors in terms of predicting latent demand (real needs) by users. Therefore, by calculating a higher weight value as the difficulty score is higher, it is possible to improve the prediction accuracy when predicting demand from the user's search behavior.

The example of the table TB shows an example in which the information processing apparatus 100 calculates "WV113" as the weight value corresponding to the difficulty score "10" indicating the difficulty of performing the search action R11 at the search location "LC11". be

The information processing apparatus 100 also calculates a weight value corresponding to the type “type #1” of the terminal device used for the search action R11. For example, the information processing apparatus 100 calculates a weight value corresponding to the type “type #1” of the terminal device according to a rule that the older the type of the terminal device used in the search action, the higher the weight value is calculated. do. For example, the older the terminal device is, the lower the operability and specifications tend to be, so the older the terminal device, the more likely it is used only for simple tasks (for example, making a phone call). Under such circumstances, if a search action is performed using an old terminal device, it can be said that there is a high demand for search targets among users who have performed search action using this terminal device. In other words, it can be said that search behavior using older terminal devices is more important search behavior in terms of predicting latent demands (real needs) by users.

In short, it is a point of view that they want to check as soon as demand arises, so they can not be concerned about the poor usability of the terminal device. For this reason, the older the type of the terminal device is, the higher the weight value is calculated, so that the prediction accuracy when predicting the demand from the user's search behavior can be improved.

The example of the table TB shows an example in which the information processing apparatus 100 calculates "WV114" as the weight value corresponding to the type "type #1" of the terminal device used in the search action R11.

Further, an example has been shown so far in which a weight value is calculated for each of the search behaviors indicating the search behavior R11. is calculated.

Next, based on the weight value for each search mode, the information processing apparatus 100 determines the degree (importance) that indicates how important it is for the search behavior to be performed in the state indicated by the search mode. Calculate (step S12). Specifically, the information processing apparatus 100 determines how important it is for the user's search behavior to be performed in the state indicated by the search mode to predict the potential demand (real need) of the user. Calculate the degree of indexing. In the following, among the search behaviors of the user U1, the importance calculation will be described with a focus on the search behavior R11.

For example, based on the weight value "WV111" corresponding to the search frequency "X1/month", the information processing apparatus 100 determines that the search behavior is performed by the user U1 whose search frequency is "X1/month". Calculate the degree of importance, which indicates how important the is. For example, assuming that the score of the search behavior R11 in a normal state, which is neither important nor unimportant, is "1", the information processing apparatus 100 calculates the degree of importance by "1" x the weight value "WV111". . An example of the table TB shows an example in which the information processing apparatus 100 calculates "IM111" as the importance level.

Further, for example, the information processing apparatus 100 uses a search query "mask" such as the frequency of use "Y1/month" based on the weight value "WV112" corresponding to the frequency of use "Y1/month" to search for the user U1. Calculate the importance indexing how important it is that the search action is performed by . For example, assuming that the score of the search behavior R11 in a normal state, which is neither important nor unimportant, is "1", the information processing apparatus 100 calculates the importance by "1" x the weight value "WV112". . The example of the table TB shows an example in which the information processing apparatus 100 calculates "IM112" as the importance level.

Further, for example, the information processing apparatus 100 determines that the user U1 performs a search action at a location with a difficulty score of "10" based on the weight value "WV113" corresponding to the difficulty score of "10." A degree of importance is calculated to indicate how important it is. For example, assuming that the score of the search behavior R11 in a normal state, which is neither important nor unimportant, is "1", the information processing apparatus 100 calculates the degree of importance by "1" x the weight value "WV113". . An example of the table TB shows an example in which the information processing apparatus 100 calculates "IM113" as the importance level.

Further, for example, the information processing apparatus 100 determines whether the search behavior of the user U1 using a terminal device such as “type #1” is based on the weight value “WV114” corresponding to the type “type #1” of the terminal device. Calculate the importance that indicates how important it is that the An example of the table TB shows an example in which the information processing apparatus 100 calculates "IM114" as the importance level.

Also, an example has been shown so far in which the importance is calculated for each of the search behaviors indicating the search behavior R11. is calculated.

Next, the information processing apparatus 100 determines the degree of importance (total importance) of the search behavior in a state in which the respective search modes are integrated, based on the importance of each search mode. Calculate (step S13). Specifically, the information processing apparatus 100 determines how important it is for the user's potential demand (real need) to be predicted that the search behavior is performed in a state in which each search mode is integrated. Calculate the degree of presence. More specifically, the information processing apparatus 100 performs a search with a search frequency of “X1/month”, a use frequency of “Y1/month”, a difficulty score of “10”, and a terminal device type of “type #1”. Calculate the total importance that indicates how important it is that the For example, in step S12, the information processing apparatus 100 calculates the total importance by adding (or multiplying) the importance for each search mode calculated for the search behavior R11.

The example of the table TB shows an example in which the information processing apparatus 100 calculates "SC11" as the total importance for the search behavior R11. The information processing apparatus 100 also calculates the total importance of each search behavior other than the search behavior R11 by the same method, as shown in the table TB.

Based on the total importance calculated in step S13, the information processing apparatus 100 estimates the importance of performing a search action in a state in which each search mode is integrated (step S14). For example, based on the relationship between the total importance and the predetermined threshold, the information processing apparatus 100 determines that the importance of the search action being performed in a state in which each search mode is synthesized is "high" or "intermediate". , "low". In the example of the table TB, the information processing apparatus 100 determines that the importance of performing the search action R11 in a state in which each search mode is integrated based on the total importance "SC11" corresponding to the search action R11 is "high". ” is shown.

Next, the information processing apparatus 100 predicts the demand level for search targets in search behavior based on the importance estimated in step S14 (step S15). For example, the information processing apparatus 100 predicts a demand level for a search target in search behavior estimated to be of high importance. Below, FIG. 2 is used to describe a case where the information processing apparatus 100 predicts a user demand level for a search target in a search behavior estimated to be highly important, and a case where the search behavior estimated to be highly important A case of predicting a demand level for a search target in an area corresponding to a position (search location) where an action is performed will be described separately.

FIG. 2 is a diagram illustrating an example of demand level prediction according to the embodiment. FIG. 2(a) shows a process for predicting a user's demand level for a search target in search behavior estimated to be of high importance. FIG. 2(b) shows the process of predicting the level of demand for a search target in an area corresponding to the position (search location) where a search action estimated to be of high importance is performed. Also, the search target here is the target indicated by the search query.

First, FIG. 2A will be described. In FIG. 2A, the information processing apparatus 100 predicts the user's demand level for the search target in the search behavior estimated to be of high importance (step S15-1). For example, the information processing apparatus 100 calculates the user's demand intensity (user demand intensity) for the search target in the search behavior estimated to be of high importance. Then, the information processing apparatus 100 predicts the user's demand level for the search target based on the user's demand intensity.

According to FIG. 2(a), following the example explained in FIG. 1, "mask" is shown as a search target in the search behavior whose importance is estimated to be "high". In addition, FIG. 2(a) shows "eye drops" as a search target in the search behavior whose importance is estimated to be "high". In the following, the processing of step S15-1 will be described using the case of the search target "mask" as an example.

For example, the information processing apparatus 100 calculates the user demand intensity of the user U1 for the search target "mask" based on the search action estimated to be highly important and the search target is "mask". calculate. As an example, the information processing apparatus 100 adds (or multiplies) the "total importance" calculated for each search action of the search target "mask", which is estimated to be highly important. Then, the user demand intensity of the user U1 for the search target "mask" is calculated.

For example, as shown in FIG. 2A, the information processing apparatus 100 calculates "SC111" as the user demand intensity of the user U1 for the search target "mask". In this case, the information processing apparatus 100 predicts the demand level of the user U1 for the search target "mask" based on the user demand intensity "SC111". For example, the information processing apparatus 100 determines that the user U1's demand level for the search target "mask" is "high", "intermediate", " Predict whether it is "low". FIG. 2A shows an example in which the information processing apparatus 100 predicts the user U1's demand level "high" for the search target "mask".

Also, the result of predicting the level of user demand for a search target can be used as a sample for analyzing what kind of demand the user has in what kind of context. In addition, such a prediction result can be used for advertisement distribution related to search targets.

Next, FIG. 2B will be described. In FIG. 2(b), the information processing apparatus 100 predicts the demand level for the search target in the area corresponding to the position (search location) where the search behavior estimated to be of high importance is performed (step S15- 2). For example, the information processing apparatus 100 identifies an area (processing target area) corresponding to the position where the search behavior estimated to be of high importance was performed. Then, the information processing apparatus 100 calculates the demand intensity (area demand intensity) in the processing target area for the search target in the search behavior estimated to be of high importance. Then, the information processing apparatus 100 predicts the demand level for search targets in the processing target area based on the area demand intensity.

For example, the information processing apparatus 100 selects, among the search behaviors of each user, search behaviors that are estimated to be of high importance, and based on the search behavior that is set as the search target “mask”, the search behavior is performed. The area corresponding to the position (area to be processed) is specified. For example, the information processing apparatus 100 identifies the area corresponding to the analysis result as the area to be processed by analyzing the position where the search behavior of the search target "mask" tends to be performed. do. FIG. 2B shows an example in which the information processing apparatus 100 specifies "A area", "B area", "C area", and "D area" as areas to be processed.

Then, the information processing apparatus 100 calculates the area demand intensity in each of the "A area", the "B area", the "C area", and the "D area" for the search target "mask". Taking the “A area” as an example, the information processing apparatus 100 adds up the “total importance” corresponding to each user who performed a search action at a position in the “A area” for the search target “mask”. For example, the area demand intensity for the search target "mask" in "area A" is calculated.

For example, as shown in FIG. 2B, the information processing apparatus 100 calculates "SCA" as the area demand intensity for the search target "mask" in "area A". In this case, the information processing apparatus 100 predicts the demand level for the search target "mask" in "area A" based on the area demand intensity "SCA". For example, the information processing apparatus 100 determines that the demand level for the search target "mask" in "area A" is "high", "intermediate", or Predict whether it is "low". FIG. 2B shows an example in which the information processing apparatus 100 predicts the demand level "high" for the search target "mask" in "area A".

Also, the result of predicting the demand level in the search target area can be used as a sample when analyzing what kind of demand is in what kind of place.

As described with reference to FIGS. 1 and 2, the information processing apparatus 100 according to the embodiment calculates a weight value corresponding to a search mode indicating search behavior by a user, and based on the calculated weight value, The importance of the search behavior being performed in the state indicated by this search mode is estimated. Based on the estimated importance, the information processing apparatus 100 predicts the demand level of the search target in the user's search behavior. According to the information processing apparatus 100 as described above, it is possible to extract, from among the user's search actions, search actions that are more important in predicting latent demand (real needs) by the user. Therefore, it is possible to improve the prediction accuracy when predicting the demand from the user's search behavior.

In addition, in the example of FIG. 1, the information processing apparatus 100 has shown the example which calculates a weight value and importance for every search action by a user. However, the information processing apparatus 100 may calculate the weight value and the degree of importance for each search action for each predetermined period by regarding, for example, search actions performed within a predetermined period as one search action. .

[4. Configuration of Information Processing Device]
Next, the information processing apparatus 100 according to the embodiment will be described using FIG. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 4, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section .

(Regarding communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits/receives information to/from the external device 30, for example.

(Regarding storage unit 120)
The storage unit 120 is realized by, for example, a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has a user information storage unit 121 , a query information storage unit 122 , a search history storage unit 123 , a score information storage unit 124 and a prediction result storage unit 125 .

(Regarding the user information storage unit 121)
The user information storage unit 121 stores various information about users. Here, FIG. 5 shows an example of the user information storage unit 121 according to the embodiment. In the example of FIG. 5, the user information storage unit 121 has items such as "user ID (Identifier)", "search frequency", and "attribute information".

"User ID" indicates identification information for identifying a user. "Search frequency" is the frequency with which the user performs a search action. In other words, the “search frequency” is information indicating the tendency of users to perform searches. The “attribute information” is information indicating various attributes such as demographic attributes and psychographic attributes of the user indicated by the “user ID”, such as sex, age, tastes and preferences. "Terminal type" is the type of the terminal device (information processing terminal) used in the search action by the user indicated by the "user ID". Examples of the “terminal type” include a foldable mobile terminal and a smart phone.

That is, in the example of FIG. 5, the search frequency of the user indicated by the user ID "U1" (user U1) is "X times/month", and the attribute information of user U1 is "attribute #1". , the type of the terminal device used by the user U1 in the search action is "type #1". In the example of FIG. 5, conceptual symbols such as "X times/month", "attribute #1", and "type #1" are used. be registered. Information registered in the user information storage unit 121 is acquired from the external device 30 by the acquisition unit 131, for example.

(Regarding the query information storage unit 122)
The query information storage unit 122 stores information related to search queries used in search behavior by users. Here, FIG. 6 shows an example of the query information storage unit 122 according to the embodiment. In the example of FIG. 6, the query information storage unit 122 has items such as "search query" and "frequency of use".

"Search query" indicates a search query used in search behavior by the user. “Frequency of use” is the frequency with which the corresponding “search query” is used in searches. In other words, the "frequency of use" may be the tendency of use on the Internet (all users), or the tendency of use in the search behavior of each user. It may be a usage tendency of an individual.

That is, in the example of FIG. 6, the frequency of use (tendency of use) of the search query "Q1", which is one of the search queries used in the search behavior of the user, on the Internet is "Y1 times/month". Give an example. In the example of FIG. 6, conceptual symbols such as "Y times/month" are used, but in practice, appropriate numerical values and information are registered. Information registered in the query information storage unit 122 is acquired from the external device 30 by the acquisition unit 131, for example.

(Regarding the search history storage unit 123)
The search history storage unit 123 stores a search history that is a history of search behavior by the user. Here, FIG. 7 shows an example of the search history storage unit 123 according to the embodiment. In the search history storage unit 123 shown in FIG. 7, a "user ID (identifier)" is associated with a "search history". Items such as "date and time information", "query information", and "location information" are included.

"User ID" indicates identification information for identifying a user who performed a search action identified by the corresponding "history ID". The "history ID" indicates identification information for identifying a search action, with a set of corresponding "date and time information", "query information", and "location information" as one search action. “Date and time information” is information regarding the date and time when the search action identified by the corresponding “history ID” was performed. "Query information" is a keyword indicating a search target in the search behavior identified by the corresponding "history ID". "Position information" is information about the position (that is, search location) where the search action identified by the corresponding "history ID" was performed.

That is, in the example of FIG. 7, the user (user U1) identified by the user ID "U1" performs a search using the search query "mask" at the date and time "DT11" and the location "LC11". An example of performing an action is shown, and an example in which such one search action is distinguished by the history ID "R11" is shown. Note that conceptual symbols such as "DT11" and "LC11" are used in the example of FIG. 7, but in practice appropriate numerical values and information are registered. Information registered in the search history storage unit 123 is acquired from the external device 30 by the acquisition unit 131, for example.

(Regarding the score information storage unit 124)
The score information storage unit 124 stores various scores such as weight values and degrees of importance. Here, FIG. 8 shows an example of the score information storage unit 124 according to the embodiment. In the score information storage unit 124 shown in FIG. 8, a "weight value" and an "importance" are associated with a set of a "user ID (identifier)" and a "history ID (identifier)". The "weight value" includes items such as "search frequency", "use frequency", "difficulty", and "terminal type". "Importance" includes items such as "search frequency", "use frequency", "difficulty", "terminal type", and "total".

“User ID” corresponds to “user ID” in search history storage unit 123 . “History ID” corresponds to “history ID” in search history storage unit 123 . The "search frequency" included in the "weight value" indicates a weight value corresponding to the search frequency, which is the frequency of search actions performed by the user indicated by the "user ID". The “frequency of use” included in the “weight value” is the search behavior of the user indicated by the “user ID”, and the search query used in the search behavior identified by the “history ID” is used by all users. indicates a weight value according to the frequency of use, which is the frequency of use as a

The "difficulty" included in the "weight value" is the difficulty of the search action at the search location where the search action identified by the "history ID" was performed by the user indicated by the "user ID". (difficulty score). The “terminal type” included in the “weight value” is the search behavior of the user indicated by the “user ID”, and is based on the type of terminal device used in the search behavior identified by the “history ID”. Indicates a weight value.

That is, the example of FIG. 8 shows an example in which "WV111" is calculated as the weight value according to the search frequency "X1 times/month" of user U1. Further, the example of FIG. 8 shows an example in which "WV112" is calculated as a weight value according to the overall usage frequency "Y1/month" of the search query "mask" used in the search action R11. Further, the example of FIG. 8 shows an example in which "WV113" is calculated as the weight value corresponding to the difficulty score "10" indicating the difficulty of performing the search action R11 at the search location "LC11". Further, the example of FIG. 8 shows an example in which "WV114" is calculated as the weight value corresponding to the type "type #1" of the terminal device used in the search action R11. In the example of FIG. 8, conceptual symbols such as "WV111", "WV112", "WV113", and "WV114" are used, but in practice, appropriate numerical values and information are registered. .

Also, the "search frequency" included in the "importance" is a user who is in a state similar to the "search frequency" in the user information storage unit 121, and the user indicated by the "user ID" Indicates a value that indicates how important it is that the search action identified by the corresponding "history ID" is performed. The "frequency of use" included in the "importance" is obtained by the user indicated by the "user ID" using a search query such as "frequency of use" in the query information storage unit 122. indicates a value that indicates how important it is that the search action identified by is performed.

The "difficulty" included in the "importance" is determined by the user indicated by the "user ID" in the area corresponding to the search location indicated by the "location information" in the search history storage unit 123. indicates a value that indicates how important it is that the search action identified by is performed. The "terminal type" included in the "importance" is stored by the user indicated by the "user ID" using a terminal device such as the "terminal type" in the user information storage unit 121. ” indicates a value that indicates how important it is that the search action identified by ” is performed.

"Total" indicates a value that indicates how important it is that the search action identified by the corresponding "history ID" is performed in a state where each search mode is integrated.

That is, in the example of FIG. 8, based on the weight value "WV111" corresponding to the search frequency "X1/month", the search behavior R11 is performed by the user U1 whose search frequency is "X1/month". An example is shown in which "IM111" is calculated as the degree of importance that indicates how important an event is in demand forecasting. Further, in the example of FIG. 8, based on the weight value "WV112" corresponding to the usage frequency "Y1/month", the user U1 searches using the search query "mask" such as the usage frequency "Y1/month". An example is shown in which "IM112" is calculated as the degree of importance that indicates how important it is that an action is performed in the demand forecast.

Further, in the example of FIG. 8, based on the weight value "WV113" corresponding to the difficulty score "10", it is predicted that the user U1 will perform a search action at a location with a difficulty score of "10". An example is shown in which "IM113" is calculated as the degree of importance that indicates how important the item is. Further, in the example of FIG. 8, based on the weight value "WV114" corresponding to the terminal device type "type #1", the user U1 performs a search action using a terminal device of "type #1". An example is shown in which "IM114" is calculated as the degree of importance that indicates how important it is for demand forecasting to be delivered.

Further, the example of FIG. 8 shows an example in which "SC11" is calculated as the total importance by synthesizing the weight value "WV111", the weight value "WV112", the weight value "WV113", and the weight value "WV114". In the example of FIG. 8, conceptual symbols such as "IM111", "IM112", "IM113", and "IM114" are used, but in reality, appropriate numerical values and information are registered. .

(Regarding prediction result storage unit 125)
The prediction result storage unit 125 stores a prediction result obtained by predicting a demand level related to a search target. Here, FIG. 9 shows an example of the prediction result storage unit 125 according to the embodiment. Further, as shown in FIG. 9, the prediction result storage unit 125 includes, for example, a prediction result storage unit 125-1 that stores a prediction result in which the user's demand level for the search target is predicted, and an area corresponding to the search location. and a prediction result storage unit 125-2 that stores the prediction result of the demand level for the search target in .

In the example of FIG. 9, the prediction result storage unit 125-1 has items such as "user ID (identifier)", "search target", "user demand intensity", and "demand level". “User ID” corresponds to “user ID” in search history storage unit 123 . The "search target" indicates an object that is a search target in the search behavior of the user indicated by the "user ID" whose importance is estimated to be "high". Such a search target is, for example, a target indicated by a search query used in a search behavior whose importance is estimated to be “high”.

The “user demand intensity” indicates the demand intensity of the user who performed the search action for the search target of the search action whose importance is estimated to be “high”. The "demand level" is a demand level predicted based on the "user demand intensity" and indicates the user's demand level for the search target.

That is, in the example of FIG. 9, among the search actions by the user indicated by the user ID "U1", one of the search targets in the search actions whose importance is estimated to be "high" is "mask". An example in which "SC111" is calculated as the user demand intensity of user U1 for the search target "mask" is shown. Further, the example of FIG. 9 shows an example in which "high" is predicted as the demand level of the user U1 for the search target "mask" based on the user demand intensity "SC111". In the example of FIG. 9, conceptual symbols such as "SC11" are used, but in practice appropriate numerical values and information are registered.

In addition, in the example of FIG. 9, the prediction result storage unit 125-2 has items such as "search target", "area", "area demand intensity", and "demand level". The "search target" is an object that is the search target in the search action estimated to be "high" in importance among the search actions of the user indicated by the "user ID" in the prediction result storage unit 125-1. show. "Area" refers to the search behavior estimated to be "high" in importance among the search behavior of each user, and the position (search location) where the search behavior corresponding to the corresponding "search target" was performed. The corresponding area (area to be processed) is shown.

"Area demand intensity" indicates the demand intensity for the "search target" in the corresponding "area". The "demand level" is a demand level predicted based on the "area demand intensity" and indicates the demand level for the "search target" in the corresponding "area".

That is, in the example of FIG. 9, "SCA" is calculated as the area demand intensity for the search target "mask" in the area "A area", and based on the area demand intensity "SCA", the search target in the area "A area" An example in which a demand level of "high" for "mask" is predicted is shown. In the example of FIG. 9, conceptual symbols such as "SCA" are used, but in practice appropriate numerical values and information are registered.

(Regarding the control unit 130)
Returning to FIG. 4, the control unit 130 executes various programs stored in a storage device inside the information processing apparatus 100 using a RAM as a work area by a CPU (Central Processing Unit), MPU (Micro Processing Unit), or the like. It is realized by Also, the control unit 130 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a calculation unit 132, an estimation unit 133, and a prediction unit 134, and implements or executes the information processing functions and actions described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be another configuration as long as it performs information processing described later. Moreover, the connection relationship of each processing unit of the control unit 130 is not limited to the connection relationship shown in FIG. 4, and may be another connection relationship.

(Regarding the acquisition unit 131)
The acquisition unit 131 acquires information necessary for information processing according to the embodiment. For example, the acquisition unit 131 acquires information about the user's search frequency, information about the user's attribute information, and information about the type of terminal device used by the user, and stores them in the user information storage unit 121 .

The acquisition unit 131 also acquires information about the frequency of use of search queries, and stores the information in the query information storage unit 122 .

The acquisition unit 131 also acquires information about the user's search history and stores it in the search history storage unit 123 .

For example, the acquisition unit 131 can acquire part or all of the information described above from the external device 30 . Further, the acquisition unit 131 acquires information necessary for the information processing from the storage unit 120 when the information processing according to the embodiment is performed. Then, the acquisition unit 131 outputs the acquired information to an appropriate processing unit.

(Regarding the calculator 132 and the estimator 133)
The calculation unit 132 calculates a weight value according to a search mode indicating search behavior by the user. For example, the calculation unit 132 calculates a weight value according to a search mode indicating the search action for each search action by the user. Based on the weight value calculated by the calculation unit 132, the estimation unit 133 estimates the importance of the search action being performed in the state indicated by this search mode.

For example, the calculation unit 132 calculates a weight value corresponding to the search frequency, which is the frequency with which a search action is performed by the user, and the estimation unit 133 calculates the search related by the user based on the weight value corresponding to the search frequency. Estimate the importance of search behavior with frequency. For example, the calculator 132 calculates a higher weight value as the search frequency is lower. Further, the calculation unit 132 may correct the weight value according to the attribute of the user.

Also, for example, the calculation unit 132 calculates a weight value according to the frequency of use, which is the frequency with which a search query used in a search action by a user is used in a search, and the estimation unit 133 calculates a weight value corresponding to the frequency of use. Estimate the importance of the search action being performed using this search query based on the weight value according to . For example, the calculator 132 calculates a higher weight value as the usage frequency is lower.

Further, for example, the calculation unit 132 calculates a weight value corresponding to the difficulty of the search action at the search location where the user performed the search action, and the estimation unit 133 calculates the weight value corresponding to the difficulty. Based on the value, estimate the importance of the search action taking place at this search location. For example, the calculator 132 calculates a higher weight value as the difficulty is higher.

Further, for example, the calculation unit 132 calculates a weight value according to the type of the terminal device used in the search behavior of the user, and the estimation unit 133 calculates the weight value according to the type of the terminal device. The importance of the search behavior being performed on the type of terminal device is estimated. For example, the calculation unit 132 calculates a higher weight value as the type of the terminal device is older.

Further, according to the example of FIG. 1, the calculator 132 performs the weight value calculation process described in step S11. Also, according to the example of FIG. 1, the estimation unit 133 performs the estimation process described in steps S12 to S14.

(Regarding the prediction unit 134)
Based on the importance estimated by the estimation unit 133, the estimation unit 134 estimates the level of demand for the search target in the user's search behavior. As described in FIG. 2A, the prediction unit 134 predicts the demand level for each user. For example, the prediction unit 134 predicts, for each user, the demand level of the user for the search target in the search behavior estimated to be of high importance among the search behaviors of the user.

Also, the prediction unit 134 predicts the demand level in the area corresponding to the location where the user has performed a search action. As described with reference to FIG. 2B, the prediction unit 134 identifies an area (area to be processed) corresponding to the position where the search behavior estimated to be of high importance was performed, and Forecast demand levels in the area being processed for a search target.

[5. Processing procedure]
Next, an information processing procedure according to the embodiment will be described with reference to FIG. 10 . FIG. 10 is a flowchart illustrating an information processing procedure according to the embodiment;

First, the calculation unit 132 calculates, for each search action of the user, a weight value corresponding to each search mode indicating the search action (step S101). For example, the calculation unit 132 calculates the user's search frequency, the overall frequency of use in the search query used for the user's search, the difficulty of performing the search action at the search location, the terminal device used for the search action , and a weight value corresponding to each type is calculated for each search behavior of the user.

Next, the estimating unit 133 calculates, based on the weight value corresponding to the search mode, the degree of importance that indicates how important it is for the demand prediction that the search action is performed in this search mode (step S102). For example, the estimating unit 133 determines that one search action is performed in a state in which each search action is integrated based on the weight value calculated for each search action indicated by one search action. A degree of importance (total importance) is calculated to indicate how important it is in prediction.

Next, the estimation unit 133 estimates the importance of the search action being performed in the state indicated by the search mode based on the importance calculated in step S102 (step S103). For example, the estimating unit 133 estimates how important it is in demand forecasting that each search behavior indicated by one search action is integrated, and that one search action is performed. do.

Based on the importance estimated in step S103, the prediction unit 134 predicts the demand level of the search target in the user's search behavior (step S104). For example, the prediction unit 134 predicts, for each user, the demand level of the user for the search target in the search behavior estimated to be of high importance among the search behaviors of the user. Further, for example, the prediction unit 134 identifies an area (area to be processed) corresponding to the position where the search behavior estimated to be of high importance is performed, Forecast demand levels in your area.

[6. Hardware configuration]
Further, the information processing apparatus 100 according to the above embodiment is implemented by a computer 1000 configured as shown in FIG. 11, for example. FIG. 11 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the information processing apparatus 100. As shown in FIG. Computer 1000 has CPU 1100 , RAM 1200 , ROM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

HDD 1400 stores programs executed by CPU 1100 and data used by these programs. Communication interface 1500 receives data from other devices via communication network 50 and sends the data to CPU 1100 , and transmits data generated by CPU 1100 to other devices via communication network 50 .

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the RAM 1200 . In addition, the data in storage unit 120 is stored in HDD 1400 . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via communication network 50 .

[7. others〕
Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

As described above, the embodiments of the present application have been described in detail based on several drawings, but these are examples, and various modifications and It is possible to carry out the invention in other forms with modifications.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 information processing system 30 external device 100 information processing device 120 storage unit 121 user information storage unit 122 query information storage unit 123 search history storage unit 124 score information storage unit 125 prediction result storage unit 130 control unit 131 acquisition unit 132 calculation unit 133 Estimation unit 134 Prediction unit

Claims (17)

a calculation unit that calculates a weight value corresponding to a search frequency, which is the frequency of a search action performed by the user, as a weight value corresponding to a search mode indicating search action by the user;
An estimating unit for estimating the importance of the user performing a search action at the search frequency based on a weight value corresponding to the search frequency and a predetermined reference value for the search action. and,
a prediction unit that predicts a level of demand for the search target in the user's search behavior based on the importance estimated by the estimation unit ;
The calculation unit calculates a higher weight value as the search frequency is lower.
An information processing device characterized by: A weight value corresponding to the frequency of use, which is the frequency with which the search query used in the search behavior of the user is used in searching, is calculated as a weight value corresponding to the search mode indicating the search behavior of the user. a calculation unit;
an estimating unit for estimating the importance of performing a search action using the search query based on the weight value according to the frequency of use and a predetermined reference value for the search action;
a prediction unit that predicts a demand level of a search target in search behavior of the user based on the importance estimated by the estimation unit;
has
The calculation unit calculates a higher weight value as the frequency of use is lower.
An information processing device characterized by: Based on a database in which candidate areas for search behavior and index values indicating the difficulty of searching in the areas are associated with each other, a weight value corresponding to a search mode indicating search behavior by a user, a calculation unit that calculates a weight value according to the difficulty of the search action at the search location where the search action is performed by the user;
an estimation unit for estimating the importance of performing a search action at the search location based on the weight value corresponding to the difficulty and a predetermined reference value for the search action;
a prediction unit that predicts a demand level of a search target in search behavior of the user based on the importance estimated by the estimation unit;
An information processing device comprising: The information processing apparatus according to claim 3 , wherein the calculator calculates a higher weight value as the difficulty is higher. a calculation unit that calculates a weight value corresponding to the type of terminal device used in the search behavior of the user as a weight value corresponding to a search mode indicating the search behavior of the user;
an estimating unit for estimating the importance of performing a search action on a terminal device of the type based on a weight value corresponding to the type of terminal device and a predetermined reference value for the search action;
a prediction unit that predicts a level of demand for a search target in search behavior by the user, based on the importance estimated by the estimation unit;
An information processing device comprising: The information processing apparatus according to claim 5 , wherein the calculation unit calculates a higher weight value as the type of the terminal device is older. The information processing apparatus according to any one of claims 1 to 6, wherein the prediction unit predicts the demand level for each user. The information processing apparatus according to any one of claims 1 to 7, wherein the prediction unit predicts the demand level in an area corresponding to a place where the user has performed a search action. The information processing apparatus according to any one of claims 1 to 8, wherein the calculator corrects the weight value according to the attribute of the user. A computer-executed information processing method comprising:
a calculation step of calculating a weight value corresponding to a search frequency, which is the frequency of a search action performed by the user, as a weight value corresponding to a search mode indicating search action by the user;
an estimation step of estimating the importance of the user performing a search action at the search frequency based on the weight value corresponding to the search frequency and a predetermined reference value for the search action; and,
a prediction step of predicting a demand level for the search target in the user's search behavior based on the importance estimated by the estimation step ;
The calculating step calculates a higher weight value as the search frequency is lower.
An information processing method characterized by : A computer-executed information processing method comprising:
A weight value corresponding to the frequency of use, which is the frequency at which the search query used in the search behavior of the user is used in searching, is calculated as a weight value corresponding to the search mode indicating the search behavior of the user. a calculation step;
an estimation step of estimating the importance of performing a search action using the search query based on the weight value according to the frequency of use and a predetermined reference value for the search action;
a prediction step of predicting the level of demand for the search target in the user's search behavior based on the importance estimated by the estimation step;
including
The calculating step calculates a higher weight value as the frequency of use is lower.
An information processing method characterized by: A computer-executed information processing method comprising:
Based on a database in which candidate areas for search behavior and index values indicating the difficulty of searching in the areas are associated with each other, a weight value corresponding to a search mode indicating search behavior by a user, a calculation step of calculating a weight value according to the difficulty of the search action at the search location where the search action was performed by the user;
an estimation step of estimating the importance of performing a search action at the search location based on the weight value corresponding to the difficulty and a predetermined reference value for the search action;
a prediction step of predicting the level of demand for the search target in the user's search behavior based on the importance estimated by the estimation step;
An information processing method comprising: A computer-executed information processing method comprising:
a calculating step of calculating a weight value corresponding to the type of terminal device used in the search behavior of the user as a weight value corresponding to the search mode indicating the search behavior of the user;
an estimating step of estimating the importance of performing a search action on the type of terminal device based on a weight value corresponding to the type of the terminal device and a predetermined reference value for the search action;
a prediction step of predicting the level of demand for the search target in the user's search behavior based on the importance estimated by the estimation step;
An information processing method comprising: a calculation procedure for calculating a weight value corresponding to a search frequency, which is the frequency of a search action performed by the user, as a weight value corresponding to a search mode indicating search action by the user;
An estimation procedure for estimating the importance of the user performing a search action at the search frequency based on a weight value corresponding to the search frequency and a predetermined reference value for the search action. and,
causing a computer to execute a prediction procedure for predicting the level of demand for a search target in the user's search behavior based on the importance estimated by the estimation procedure ;
The calculation step calculates a higher weight value as the search frequency is lower.
An information processing program characterized by: A weight value corresponding to the frequency of use, which is the frequency with which the search query used in the search behavior of the user is used in searching, is calculated as a weight value corresponding to the search mode indicating the search behavior of the user. a calculation procedure;
an estimation procedure for estimating the importance of performing a search action using the search query based on the weight value according to the frequency of use and a predetermined reference value for the search action;
a prediction procedure for predicting a demand level for a search target in search behavior by the user based on the importance estimated by the estimation procedure;
on the computer, and
The calculating procedure calculates a higher weight value as the frequency of use is lower.
An information processing program characterized by: Based on a database in which candidate areas for search behavior are associated with index values indicating the difficulty of searching in the areas, a weight value corresponding to a search mode indicating search behavior by a user, a calculation procedure for calculating a weight value according to the difficulty of the search action at the search location where the user performed the search action;
an estimation procedure for estimating the importance of performing a search action at the search location based on the weight value corresponding to the difficulty and a predetermined reference value for the search action;
a prediction procedure for predicting a demand level for a search target in search behavior by the user based on the importance estimated by the estimation procedure;
An information processing program characterized by causing a computer to execute a calculation procedure for calculating a weight value corresponding to the type of terminal device used in the search behavior of the user as a weight value corresponding to a search mode indicating the search behavior of the user;
an estimation procedure for estimating the importance of performing a search action on a terminal device of the type based on a weight value corresponding to the type of the terminal device and a predetermined reference value for the search action;
a prediction procedure for predicting a demand level for a search target in search behavior by the user based on the importance estimated by the estimation procedure;
An information processing program characterized by causing a computer to execute

Images