JP2019067226A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide an information processing device, an information processing method, and a program, which reduce the burden on a user in retrieval processing and increase the amount of information provided to the user.SOLUTION: An information processing device includes an acquisition unit configured to acquire a retrieval query input by a user, a recommendation query determination unit configured to determine a recommendation query including the retrieval query acquired by the acquisition unit and a related query associated with the retrieval query, and a generation unit configured to generate information for displaying a plurality of retrieval results, which is information for preferentially displaying a retrieval result having a low degree of association with the recommendation query determined by the recommendation query determination unit.SELECTED DRAWING: Figure 8

Description

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

  In the field of web search, a method of providing information such as various products or services related to a search query is performed according to a keyword (hereinafter, referred to as a "search query") input by a user. In addition, a method for reducing the burden on the user in search processing is performed by presenting and recommending the user, as a related query, a character string having relevance to the search query input by the user (for example, Patent Document 1) reference).

JP, 2009-169541, A

  When a search result page is generated in the conventional method, for example, based on usage records such as the degree of association between a search query and a product serving as a candidate and the click rate of a page of the product site, The position of the page is determined. However, in this method, there is a case in which a product to be posted is biased, and a user has an opportunity to browse information of more products.

  The present invention has been made in consideration of such circumstances, and reduces the burden on the user in search processing, and can increase the amount of information provided to the user, and an information processing method, And to provide one of the programs.

  One aspect of the present invention is a recommendation for determining a recommendation query including an acquisition unit for acquiring a search query input by a user, a search query acquired by the acquisition unit, and a related query associated with the search query. Information for displaying a search result having a low degree of association with the recommendation query determined by the recommendation query determination unit, which is information for displaying a plurality of search results, is generated. It is an information processing apparatus provided with a production | generation part.

  According to one aspect of the present invention, it is possible to reduce the burden on the user in search processing and to increase the amount of information provided to the user.

It is a functional block diagram of search server 1 of a 1st embodiment. It is a flowchart which shows an example of the flow of a search process of the search server 1 of 1st Embodiment. It is a figure which shows an example of recommendation query data D2 of 1st Embodiment. It is a figure which shows an example of the search result page P1 of 1st Embodiment. It is a figure explaining that the amount of information provided to a user increases by search processing of search server 1 of a 1st embodiment. It is a figure explaining that the amount of information provided to a user increases by search processing of search server 1 of a 1st embodiment. It is a flow chart which shows an example of the flow of adjustment processing of search server 1 of a 1st embodiment. It is a figure explaining the utilization environment of search server 2 and search support server 3 in a 2nd embodiment.

  Hereinafter, embodiments of an information processing device, an information processing method, and a program will be described with reference to the drawings.

First Embodiment
<Overview>
Hereinafter, a first embodiment of the present invention will be described. The information processing apparatus according to the present embodiment generates information for displaying a search result according to a search query input by a user. The information for displaying the search result includes information of a search query and information of a recommendation query including a related query which is a character string associated with the search query, and information of a search result. In the information of this search result, the publication position (display order) of the search result is determined based on the degree of association with the recommendation query. For example, in the information of the search results, search results having a low degree of association with the recommendation query are placed at the top, and search results having a high degree of association with the recommendation query are placed at the lower side. In the present embodiment, an example will be described in which the information processing apparatus is a search server that provides search results of contents such as products.

<System configuration>
FIG. 1 is a functional block diagram of a search server 1 (information processing apparatus) of the present embodiment. The search server 1 is connected to a terminal device T or the like via the network NW. The network NW includes, for example, a wide area network (WAN), a local area network (LAN), the Internet, a dedicated line, a wireless base station, a provider, and the like.

  The terminal device T is operated by the user who uses the search service provided by the search server 1. The terminal device T is, for example, a computer device such as a personal computer, a mobile phone such as a smartphone, a tablet terminal, or a PDA (Personal Digital Assistant). The terminal device T transmits, for example, a search query requesting information provision to the search server 1 and a browser or an application program that operates based on a user operation, and receives information associated with the search query from the search server 1 Do.

  The search server 1 transmits, to the terminal device T, page information of search results associated with the search query input from the terminal device T. The search server 1 generates page information of a search result using search data in which a search query and reference information for referring to a page of a site associated with the search query are associated. The reference information includes, for example, a URL (Uniform Resource Locator).

  For example, the search server 1 includes a communication unit 10 (acquisition unit), a search unit 11, a recommendation query determination unit 12, an order determination unit 14, a search result generation unit 16 (generation unit), and an adjustment unit 18. And a storage unit 20. The communication unit 10 communicates with the terminal device T or the like via the network NW. The communication unit 10 receives a search query from the terminal device T via the network NW, and transmits page information of a search result to the terminal device T. The communication unit 10 includes, for example, a communication interface such as a NIC.

  The storage unit 20 stores, for example, search data D1 including reference information for referring to a page of a site associated with a search query, and recommendation query data D2 including information of recommendation queries. The storage unit 20 is realized by, for example, a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), a flash memory, or a hybrid storage device in which a plurality of them are combined. In addition, a part or all of the storage unit 20 may be an external device that can be accessed by the search server 1, such as a NAS or an external storage server.

  The search unit 11 searches and acquires, from the search data D1 stored in the storage unit 20, information of the page of the site associated with the search query acquired via the communication unit 10. The information of the page of the site associated with the search query includes, for example, the URL of the page of this site, the title information of the product displayed on this page, the information of the image of the product, and the like.

  The recommendation query determination unit 12 determines, according to the search query acquired via the communication unit 10, at least one recommendation query that is a combination of the search query and the related query associated with the search query. The recommendation query may be a set of a related query and a query in which part of the search query string has been changed in consideration of variations in the search query. For example, when the search query is "earphone", the query in which a part of the search query string is changed in consideration of the notation fluctuation is "earphone" or the like. Since the “earphone” and the “earphone” indicate the same object, these queries are treated as the same in the processing of the recommendation query determination unit 12.

  Based on the degree of association between the information on the page of the site acquired by the search unit 11 and the recommendation query determined by the recommendation query determination unit 12, the order determination unit 14 determines the information on the page of each site in the search result page Determine the display order. For example, in the search result page, the ranking determination unit 14 has information on the page of the product site with a low degree of association with the recommendation query placed at the top, and information of the page with a product site with a high degree of association with the recommendation query Decide the display order so that it will be placed lower.

  The order determination unit 14 calculates the degree of association based on the appearance frequency of the character string of the recommendation query in each of the product site pages. The order determining unit 14 calculates the degree of association, for example, based on the appearance frequency of the character string of the recommendation query in various fields (product name, product description, spec information, etc.) included in each of the product site pages. The higher the appearance frequency, the higher the degree of association, and the lower the appearance frequency, the lower the degree of association. That is, the order determination unit 14 calculates the degree of association in a tendency that the degree of association increases as the appearance frequency of the recommendation query at the link destination transitioning from the plurality of search results becomes higher.

  The order determination unit 14 may calculate the degree of association with the tendency that the appearance frequency of the search query decreases and the appearance frequency of the related query increases in each of the product site pages. In addition, the order determining unit 14 may calculate the degree of association by weighting each of the various fields included in each of the pages of the product site.

  In addition to or in place of the relevance, the ranking determination unit 14 uses the number of clicks on each page of a product site, such as the click rate (CTR: Click Trough Rate), the customer conversion rate (CVR: Conversion Rate), etc. The display order of the information of the page of each site in the search result page may be determined in consideration of the results. In this case, first, the order determination unit 14 scores the pages of each site based on the usage results (eg, the higher the usage results, the higher the score). Next, the ranking determination unit 14 re-scores so as to penalize (minus the score) when a recommendation query appears on a page of each site. The number of recommendation queries used for scoring is predefined. In addition, after performing the scoring based on the usage record, the ranking determination unit 14 performs the re-scoring based on the recommendation query only for a predetermined ranking or higher (for example, the page of the top 10 sites). May be This can reduce the processing load associated with scoring.

  The search result generation unit 16 simultaneously searches the recommendation query determined by the recommendation query determination unit 12 and the search result including the information of the page of the product site arranged based on the display order determined by the order determination unit 14. Generate a search results page to display. That is, the search result generation unit 16 is information for displaying a plurality of search results, and preferentially displays a search result having a low degree of association with the recommendation query determined by the recommendation query determination unit 12. Generate information. The search result generation unit 16 transmits the generated search result page to the terminal device T via the communication unit 10.

  In the scoring process of the ranking determination unit 14, the adjustment unit 18 adjusts a process (how much the score is to be subtracted) to which penalty (weight) is to be imposed on the page of the site of the product having a high degree of association. Do. For example, the adjustment unit 18 increases the weight of the degree of association when the use result of the search result is rising, and reduces the weight of the association degree when the use result of the search result is falling The adjustment process may be, for example, a batch process performed at a predetermined timing such as daily or weekly.

  Each functional unit of the search server 1 is realized, for example, by a hardware processor such as a central processing unit (CPU) executing a program (software) in a computer. In addition, some or all of these components may be hardware (circuits) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), etc. Circuit (including circuitry) or may be realized by cooperation of software and hardware.

<Search processing>
The search processing of the search server 1 will be described below. FIG. 2 is a diagram showing an example of the flow of the search process of the search server 1. FIG. 3 is a diagram showing an example of the recommendation query data D2. FIG. 4 is a diagram showing an example of the search result page P1 of the embodiment.

  The communication unit 10 acquires a search query input by the user operating the terminal device T (S101). Next, in accordance with the search query acquired via the communication unit 10, the recommendation query determination unit 12 sets at least one recommendation query that is a combination of the search query and the related query associated with the search query. It determines (S103). The number of recommendation queries determined by the recommendation query determination unit 12 is previously defined.

  The recommendation query determination unit 12 refers to the recommendation query data D2 stored in the storage unit 20 to determine a recommendation query. The recommendation query data D2 illustrated in FIG. 3 includes, for example, data in which a “search query”, a “recommendation query”, and a “search number” indicating the number of times a recommendation query has been searched in the past (history) are associated. . When the search query acquired via the communication unit 10 is an “earphone”, the recommendation query determination unit 12 searches the recommendation query data D2 for a recommendation query associated with the search query “earphone”.

  For example, when the number of recommendation queries to be determined is defined as four, the recommendation query determination unit 12 determines the number of recommendation queries among the recommendation queries associated with the search query “earphone” in the recommendation query data D2 The four recommendation queries of are determined as recommendation queries of the search query. In the example shown in FIG. 3, the recommendation query determination unit 12 determines “Bluetooth (registered trademark) earphone”, “Product A earphone”, “Bluetooth (registered trademark) earphone”, and “Earphone canal” as a recommendation query.

  Next, the search unit 11 performs a search on the search data D1 using the search query acquired via the communication unit 10, and acquires information on the page of the product site (S105). The search unit 11 may execute the search process in parallel with the process of determining the recommendation query by the recommendation query determination unit 12 described above. Next, the order determination unit 14 calculates the degree of association with the recommendation query for each of the information of the page of the product site acquired by the search unit 11 (S107).

  Next, the order determining unit 14 determines the display order of the information of the page of the site of the product in the search result page based on the calculated degree of association (S109). The ranking determination unit 14 is arranged such that the information of the product site page having a low degree of association with the recommendation query is placed at the top, and the information of the product site page having a high degree of association with the recommendation query is placed at the low order. , Determine the display order.

  Next, the search result generation unit 16 generates a search result including the recommendation query determined by the recommendation query determination unit 12 and the page information of the product site arranged according to the display order determined by the order determination unit 14; A search result page including the above is generated and transmitted to the terminal device T (S111). Thus, the process of this flowchart ends.

  FIG. 4 shows an example of a search result page P1 generated when the user operates the terminal device T, inputs a search query “earphone” in the query input field E1 and presses the search button B1. As shown in FIG. 4, in the recommendation query display area R1 of the search result page P1, as a recommendation query (displayed as "related search word" in FIG. 4), "Bluetooth earphone", "Product A earphone", "Bluetooth earphone" And “Earphone Canal” are displayed as links. By clicking one of these recommendation queries, the user can transition to a search result page when the clicked recommendation query is used as a search query.

  In the search result display area R2 of the search result page P1, the information of the page of the product site having a low degree of association with the recommendation query is placed at the top, and the information of the page of the product site with a high degree of association with the recommendation query The search results arranged at the lower level are displayed. That is, in the example shown in FIG. 4, the information on the page of the product site is arranged such that the degree of association decreases in the order of “earphone G”, “earphone F”, and “earphone A”. Moreover, in the example shown in FIG. 4, the information of the page of the site of the product is arranged such that the degree of association decreases as going from the right to the left of the search result page P1.

  FIG. 5 and FIG. 6 are diagrams for explaining that the amount of information (for example, the number of items) of items provided to the user is increased by the search process of the search server 1 described above. FIG. 5 shows search result pages P10, P12 and P14 provided to the user by the conventional search processing, and search result pages P20, P22 and P24 provided to the user by the search processing of the present embodiment.

  In the search result page P10 provided to the user by the conventional search processing, when the search query input by the user is "earphone", for example, the degree of association with the search query "earphone" and the page of the site of each product Based on the actual value such as the number of clicks, information on the page of the product site included in the search result is determined. In the search result page P10, the information of the page of the site of 5 products related to "Bluetooth earphone", the information of the page of the site of 5 products related to "Product A earphone", "(normal) Information on the page of the site of the 10 articles related to the earphone is displayed.

  When the user presses the link of the recommendation query “Bluetooth earphone” included in the search result page P10, the process transitions to a search result page P12 in the case where “Bluetooth earphone” is a search query. In the search result page P12, information of the page of the site of the 20 articles related to the "Bluetooth earphone" is displayed. When the link of the recommendation query “Product A earphone” included in the search result page P10 is pressed, the screen transitions to a search result page P14 in the case where “Product A earphone” is a search query. In the search result page P14, information of the page of the site of the 20 products associated with the "product A earphone" is displayed.

  On the other hand, in the search result page P20 provided to the user by the search process of the present embodiment, if the search query input by the user is "earphone", the search query of the recommendation query, "Bluetooth earphone" and "Product A earphone" The information of the product site page included in the search result is determined based on the degree of association and the actual value such as the number of clicks on the page of each product site. In the search result page P20, the information of the page of the site of one product related to "Bluetooth earphone", the information of the page of the site of one product related to "Product A earphone", "(normal) Information on the page of the site of the 18 articles related to the earphone is displayed. Since the information on the page of the site of the product related to the "Bluetooth earphone" and the related product of the product related to the "Product A earphone" is placed at a lower level, the displayed product is displayed The number of page information on the site is smaller than that of the conventional search result page P10 described above.

  When the user presses the link of the recommendation query “Bluetooth earphone” included in the search result page P20, the process transitions to a search result page P22 in the case where “Bluetooth earphone” is a search query. In the search result page P22, information of the page of the site of the 20 articles related to the "Bluetooth earphone" is displayed. When the link of the recommendation query “product A earphone” included in the search result page P20 is pressed, the screen transitions to a search result page P24 in the case where “product A earphone” is a search query. In the search result page P24, information of the page of the site of the 20 products associated with the "product A earphone" is displayed.

  FIG. 6 is a diagram showing the total number of times information on a page of a site of a product is displayed in the search result page shown in FIG. In the conventional search result pages P10, P12, and P14, the display number of the information on the page of the site of the product related to the "Bluetooth earphone" is 25 times in total of P10 (5) and P12 (20), " The number of information displayed on product A earphones and related product site pages is a total of 25 times for P10 (5) and P14 (20), and for the (general) earphones and related products of the site The number of display of page information is 10 times in total of P10 (10). Here, the distribution of the user's search intention for the search query “earphones” is 20% for “Bluetooth earphones”, 20% for “Product A earphones”, and 60% for “(normal) earphones” Assuming that, the average value of the display number between the users is 16 times (25 × 0.2 + 25 × 0.2 + 10 × 0.6).

  On the other hand, in the search result pages P20, P22, and P24 of the present embodiment, the number of displayed information of the page of the site of the product related to the "Bluetooth earphone" is 21 times in total of P20 (one) and P22 (20). The display number of the information on the page of the site of the product related to "Product A earphone" is 21 times in total of P20 (1) and P24 (20), and is related to "(normal) earphone" The number of information displayed on the product site page is a total of 18 times for P20 (18 items). In this case, the average value of the display number between the users is 19.2 times (21 × 0.2 + 21 × 0.2 + 18 × 0.6).

  As described above, while the average value of the display number between the users in the conventional search result pages P10, P12 and P14 is 16 times, the search result pages P20, P22 and P24 in this embodiment are inter-user The average value of the display number of is 19.2 times, and it can be seen that the number of pages (the amount of information) provided to the user is increased by the search processing of the present embodiment.

<Adjustment processing>
The adjustment processing in the search server 1 will be described below. As described above, in the search process in the search server 1 of the present embodiment, the information of the page of the product site having a low degree of association with the recommendation query is placed at the top, and the product site with a high degree of association with the recommendation query Page information is placed at the bottom. However, if only information on pages of products with low relevance is placed at the top of the search results page P1, search results different from the user's search intention will be provided, which may lead to a decrease in search accuracy. is there. For this reason, in the search server 1, processing is performed to adjust how much penalty is imposed on the information of the page of the site of the product having a high degree of association. This adjustment process may be, for example, a batch process performed at a predetermined timing such as daily or weekly.

  FIG. 7 is a flowchart showing an example of the flow of adjustment processing of the search server 1. First, the adjustment unit 18 refers to the access log of the target site (for example, the shopping site A), and implements the search processing of the present embodiment, so that the site of the product is more than when the conventional search processing is performed. It is determined whether the total number of clicks has increased (S201).

  When the number of clicks on the entire site of a product is increased by performing the search process of the present embodiment, it is assumed that the control of the display order in the present embodiment is effectively functioning. Therefore, the adjustment unit 18 strengthens the degree of the penalty imposed on the page of the site of the product having a high degree of association in the scoring process of the order determination unit 14 (S203). On the other hand, when the number of clicks on the entire site of a product is reduced by performing the search process of the present embodiment, it is assumed that the control of the display order in the present embodiment does not function effectively. Therefore, the adjustment unit 18 weakens the degree of the penalty imposed on the page of the site of the product having a high degree of association in the scoring process of the order determination unit 14 (S205). Thus, the process of this flowchart ends.

  The above-mentioned penalty adjustment process may be performed for each category of goods, each category of users, each search query, or each combination of any two or more of them. For example, when the penalty adjustment process is performed for each product category, the category "home appliance" increases the degree of strengthening or weakening the penalty, and the category "fashion" class increases or decreases the degree of penalty. Control to lower than in the case of "home appliances".

  Further, for example, in the case of performing the adjustment process of the penalty for each category of the user, when the type of the terminal device T used by the user is “PC”, the degree of strengthening or weakening the penalty is enhanced, and the type of the terminal device T In the case of “smart phone”, the degree of strengthening or weakening the penalty is controlled to be lower than in the case of the type of the terminal device T being “personal computer”. Also, if the attribute of the user is "male", the degree of strengthening or weakening the penalty is increased, and if the attribute of the user is "female", the degree of increasing or weakening the penalty is lower than that of the attribute "male" To control.

  Also, for example, when the penalty adjustment process is performed for each search query, if the search query is a term indicating a specific product such as “earphone”, the degree of strengthening or weakening the penalty is increased, and the search query If the term is a broad term, not a specific item such as "golf", the degree of strengthening or weakening the penalty is controlled to be lower than in the case of the "earphone" of the search query.

  According to the search server 1 of the present embodiment described above, the burden on the user in the search process can be alleviated, and the amount of information provided to the user can be increased.

  Although the example of the shopping site which provides the information of goods was explained in the above, this embodiment is applicable if it is a service with search processing of information, such as an auction site and an in-house document search system.

  Furthermore, although the example in which the number of search keywords input by the user is one has been described above, the number of search keywords may be two or more. In this case, the recommendation query may include two or more search keywords and one related keyword. Furthermore, although the example in which the number of related keywords associated with one search query is one in one recommendation query has been described above, the number of related keywords may be two or more.

Second Embodiment
Hereinafter, a second embodiment of the present invention will be described. The search server according to the present embodiment does not have the function of determining the display order of a plurality of search results (does not include the order determining unit) as compared with the first embodiment, and the search server is physically The difference is that the function of determining the display order is realized by the search support server (information processing apparatus) separated into. Therefore, for the configuration and the like, the drawings described in the first embodiment and the related descriptions are incorporated, and the detailed description is omitted.

<System configuration>
FIG. 8 is a diagram for explaining the usage environment of the search server 2 and the search support server 3 in the present embodiment. The search server 2 and the search support server 3 are connected via the network NW.

<Search server>
The search unit 11 searches and acquires, from the search data D1 stored in the storage unit 20, information of the page of the site associated with the search query acquired via the communication unit 10. The search unit 11 transmits a search query and information on a plurality of pages associated with the search query to the search support server 3 via the communication unit 10.

  The recommendation query determination unit 12 determines, according to the search query acquired via the communication unit 10, at least one recommendation query that is a combination of the search query and the related query associated with the search query. The recommendation query determination unit 12 transmits information of the determined recommendation query to the search support server 3 via the communication unit 10.

<Search support server>
The search support server 3 includes, for example, a communication unit 30 and an order determination unit 32. The communication unit 30 communicates with the search server 2 and the like via the network NW. The communication unit 30 receives the search query, the information of the plurality of pages associated with the search query, and the information of the recommendation query from the search server 2 via the network NW, and displays the information of the plurality of pages The information on the order is sent to the search server 2. The communication unit 30 includes, for example, a communication interface such as a NIC.

  The order determining unit 32 calculates the degree of association based on the search query received from the search support server 3, the information on the plurality of pages associated with the search query, and the information on the recommendation query, and the calculated degree of association Based on the search result page, the display order of the information of the page of each site is determined. The order determining unit 32 transmits the information of the determined display order to the search server 2 via the communication unit 10.

  According to the search server 2 and the search support server 3 of the present embodiment described above, the burden on the user in the search process can be alleviated, and the amount of information provided to the user can be increased.

  According to the information processing apparatus of some embodiments described above, an acquisition unit that acquires a search query input by a user, a search query acquired by the acquisition unit, and a relation associated with the search query A recommendation query determination unit that determines a recommendation query including a query, and information for displaying a plurality of search results, and gives priority to a search result having a low degree of association with the recommendation query determined by the recommendation query determination unit By providing a generation unit that generates information to be displayed in a similar manner, it is possible to reduce the burden on the user in the search process and to increase the amount of information provided to the user.

  As mentioned above, although the form for carrying out the present invention was explained using an embodiment, the present invention is not limited at all by such an embodiment, and various modification and substitution within the range which does not deviate from the gist of the present invention Can be added.

1, 2 ... Search server (information processing device)
3 ... Search support server (information processing device)
10: Communication unit (acquisition unit)
12 ... recommendation query determination unit 14 ... order determination unit 16 ... search result generation unit (generation unit)
18 ... adjustment unit 20 ... storage unit 30 ... communication unit (acquisition unit)
32 ... Rank determination unit

Claims (12)

An acquisition unit for acquiring a search query input by a user;
A recommendation query determination unit configured to determine a recommendation query including the search query acquired by the acquisition unit and the related query associated with the search query;
A generation unit configured to generate information for displaying a plurality of search results, and for preferentially displaying a search result having a low degree of association with the recommendation query determined by the recommendation query determination unit; Information processing device. As the appearance frequency of the recommendation query at the link destination transitioning from the plurality of search results increases, the degree of association increases, and the degree of association is calculated, and the plurality of searches are calculated based on the calculated degree of association The system further comprises a rank determination unit that determines the display rank of the results,
The generation unit generates the information based on the display order determined by the order determination unit.
An information processing apparatus according to claim 1. The ranking determination unit determines that the degree of association decreases as the appearance frequency of the search query at a link destination transitioning from the plurality of search results increases, and the degree of association increases as the appearance frequency of the related query increases. Calculate the degree of association with an increasing tendency of
The information processing apparatus according to claim 2. The recommendation query determination unit determines the recommendation query based on an actual value of the number of searches of a set of the search query and the related query.
The information processing apparatus according to claim 2. The order determining unit displays the display based on the appearance frequency of the search query at the link destination transitioning from the plurality of search results, the usage result of the link destination transitioning from the plurality of search results, and the degree of association. Determine the order,
The information processing apparatus according to any one of claims 2 to 4. The generation unit generates information for simultaneously displaying the recommendation query determined by the recommendation query determination unit and the plurality of search results.
The information processing apparatus according to any one of claims 1 to 5. The order determining unit further includes an adjusting unit that adjusts the weight of the degree of association when the display order is determined based on the appearance frequency of the search query, the usage record, and the degree of association.
The information processing apparatus according to claim 5. The adjustment unit increases the weight of the degree of association when the use result of the search result is increasing, and the adjustment unit sets the weight of the degree of association when the use result of the search result is decreasing. Reduce
The information processing apparatus according to claim 7. The adjustment unit adjusts the weight of the degree of association for each category of the search result, for each category of the user, or for each search query.
The information processing apparatus according to claim 7. An acquisition unit that acquires a search query input by a user, a recommendation query including the search query and a related query associated with the search query, and a plurality of search results associated with the search query;
The degree of association between the recommendation query and each of the plurality of search results, and the degree of association of the recommendation query calculated as the appearance frequency of the recommendation query at the link destination transitioning from the plurality of search results increases And an order determining unit configured to determine a display order of the plurality of search results based on the calculated degree of association. The computer is
Get the search query entered by the user,
Determining a recommendation query including the acquired search query and a related query associated with the search query;
Information for displaying a plurality of search results, and generating information for preferentially displaying a search result having a low degree of association with the determined recommendation query,
Information processing method. On the computer
Get the search query entered by the user,
Determining a recommendation query including the acquired search query and a related query associated with the search query;
Information for displaying a plurality of search results, and generating information for preferentially displaying a search result having a low degree of association with the determined recommendation query,
program.

Images