JP2025028676A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To provide an information processing device, an information processing method, and an information processing program which propose an appropriate search query to a user.SOLUTION: An information processing device includes an extraction section, a generation section, a selection section, and a provision section. The extraction section extracts a search word estimated to be desired for a search by a user from a distribution article. The generation section generates an article content in which a link to a search result obtained by using the search word extracted by the extraction section as a search query is set for the search word displayed in the distribution article. The selection section selects a search query estimated to be desired for the search by the user from a plurality of search queries including the search word for which the link is set by the generation section. The provision section implements provision in such a manner that an additional content in which the links to the search result obtained by using the search query selected by the selection section are arrayed is superimposed on the article content.SELECTED DRAWING: Figure 2

Description

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

Technologies have been proposed to suggest search queries to users. For example, there is a technology that provides words contained in news articles on a news site that the user is presumed to want to search for as selectable search query candidates (see, for example, Patent Document 1).

JP 2017-73095 A

However, conventional technology leaves room for improvement in suggesting appropriate search queries to users. For example, conventional technology suggests words contained in content as search queries, but does not consider suggesting search queries related to the words.

The present invention has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can suggest appropriate search queries to a user.

In order to solve the above-mentioned problems and achieve the object, the information processing device according to the present invention includes an extraction unit, a generation unit, a selection unit, and a provision unit. The extraction unit extracts search words that are presumed to be desired by a user from a distributed article. The generation unit generates article content in which a link to a search result using the search word extracted by the extraction unit as a search query is set for the search word displayed in the distributed article. The selection unit selects a search query that is presumed to be desired by the user from a plurality of search queries including the search word to which the link is set by the generation unit. The provision unit provides additional content that includes an arrangement of links to search results using the search query selected by the selection unit by superimposing it on the article content.

According to the present invention, it is possible to suggest appropriate search queries to users.

FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of distribution content according to the embodiment. FIG. 3 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. FIG. 4 is a diagram illustrating an example of information stored in a distribution article storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of information stored in a word storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of information stored in a search query storage unit according to the embodiment. FIG. 7 is a flowchart illustrating an example of a providing process according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

Below, the information processing device, information processing method, and information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to these embodiments.

[Embodiment]
[1. Information Processing]
First, an example of an information processing system according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of an information processing system according to an embodiment.

As shown in FIG. 1, the information processing system S includes an information processing device 1 and multiple user terminals 100. The information processing device 1 is an information processing device that provides various web services, such as news sites, to each user terminal 100 through a predetermined network N.

The user terminal 100 shown in FIG. 1 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. The user terminal 100 also displays information delivered by the information processing device 1 using a web browser or an application.

Incidentally, conventionally, news sites have a technology for setting up links to search results using words such as proper nouns and names contained in distributed articles as search queries, and then providing the links to the user terminal 100.

With this technology, users can perform searches without inputting a search query, allowing them to seamlessly perform searches from news sites.

However, this technology has room for improvement in suggesting appropriate search queries to users. Specifically, because it suggests one-word search queries, the search results may be more abstract than the information the user actually wants to know.

The information processing device 1 according to the embodiment therefore sets a search result link for search words contained in distributed articles that are presumed to be what the user wishes to search for, and further provides a superimposed link to search results that use multiple words related to the search word as a search query.

Here, an example of the distribution content according to the embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of the distribution content according to the embodiment. As shown in FIG. 2, the distribution content Ct includes a title T, a main text B, and additional content A.

The title T is the title of the article to be distributed, and the body text B is the body text of the article to be distributed. For example, the title T and the body text B are determined by the contributor who submits the article to the information processing device 1.

The information processing device 1 extracts search words from the main text B of the distribution article submitted by the contributor, and sets a link to the search results using the search words as a search query for the corresponding search words.

Search words are words that users are expected to search for in distributed articles, for example, words with a high predicted click rate. In the example shown in FIG. 2, "COVID-19" and "labor shortage" correspond to search words, and direct links Lc1 and Lc2 are set for "COVID-19" and "labor shortage", respectively. Note that hereinafter, direct links Lc1 and Lc2 may be collectively referred to as direct links Lc.

Furthermore, the information processing device 1 selects a search query that is presumed to be desired by the user from among search queries that include a search word for which a direct link Lc has been set, and provides additional content A by superimposing thereon an array of links to search results using the selected search query.

The search query to be superimposed on the additional content A is a search query that is presumed to be the one that the user desires to search, among search queries consisting of multiple words including the search word of the direct link Lc. For example, the information processing device 1 selects, as the search query to be superimposed on the additional content A, the search query with the highest predicted click rate among search queries that include the search word and other words.

The example shown in Figure 2 shows a case where, as a search query, "COVID-19 infection count" and "COVID-19 group travel" are selected for the search word "COVID-19," and "labor shortage industry" is selected for the search word "labor shortage."

As shown in FIG. 2, in the distributed content Ct, additional links Lt1 to Lt3 to search results using the search queries "COVID-19 number of infected people," "COVID-19 group travel," and "labor shortage industry" are displayed superimposed on the additional content A. Note that hereinafter, the additional links Lt1 to Lt3 may be collectively referred to as the additional link Lt.

For example, the information processing device 1 may select a search query including a word (number of infected people) not listed in the main text B as the target of the additional link Lt, like the additional link Lt1, or may select a search query including a word (group travel) listed in the main text B as the target of the additional link Lt. For example, in the former case, an additional link Lt with an angle different from that of the main text can be generated, and in the latter case, an additional link Lt with an angle related to the main text can be generated.

The information processing device 1 may select only one additional link Lt for one direct link Lc. The information processing device 1 may also display the additional links Lt in the additional content A in the order in which the direct links Lc appear in the main text B, or may provide the additional links Lt in the additional content A in the order of the predicted click rates.

Then, when the user selects a direct link Lc or an additional link Lt through the distribution content Ct distributed from the information processing device 1 to the user terminal 100, the search results for the corresponding search query are displayed on the user terminal 100.

In this way, the information processing device 1 according to the embodiment sets a direct link Lc for the search word contained in the distributed article, and further provides distributed content Ct that superimposes additional content A in which additional links Lt for search queries containing the search word are arranged.

In other words, the information processing device 1 according to the embodiment can suggest appropriate search queries to the user by suggesting search queries with different levels of abstraction.

2. Information Processing Device
Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in the figure, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

The communication unit 2 is realized, for example, by a network interface card (NIC). The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) via a wired or wireless connection, and transmits and receives information to and from each of the user terminals 100 and the like via the communication network.

The storage unit 3 is realized, for example, by a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

As shown in FIG. 3, the memory unit 3 includes a distributed article memory unit 31, a word memory unit 32, and a search query memory unit 33.

The distributed article storage unit 31 stores distributed articles. Distributed articles are articles distributed on a news site, and are submitted by each contributor, for example. FIG. 4 is a diagram showing an example of information stored in the distributed article storage unit 31 according to an embodiment.

As shown in FIG. 4, the distributed article storage unit 31 stores information items such as "Article ID", "Distributed article", "Category", and "Word" in association with each other. The "Article ID" item stores an identifier for identifying each distributed article.

The "Distributed Article" item stores information about the distributed article itself, including the title T of the distributed article identified by the corresponding article ID and the main text B. The "Distributed Article" item may also store a thumbnail image on the news site and a main text image published in the main text B.

The "Category" item stores information about the category of the distributed article identified by the corresponding article ID. For example, categories are classified into categories on news sites such as economy, entertainment, sports, domestic, international, IT, science, and local.

The "word" item stores information about words contained in a distributed article identified by a corresponding article ID. The words here are words that are candidates for search words, and include, for example, proper nouns and names.

Returning to the explanation of FIG. 3, the word storage unit 32 will be described. The word storage unit 32 stores information about words that are candidates for search words. FIG. 5 is a diagram showing an example of information stored in the word storage unit 32 according to the embodiment.

As shown in FIG. 5, the word storage unit 32 stores information on items such as "word," "number of searches," and "estimated CTR (Click Through Rate)" in association with each other. Words are stored in the "word" item. Words stored in the "word" item are words that are candidates for search words, and include, for example, proper nouns and personal names.

The "number of searches" field stores information about the number of searches for the corresponding word. For example, the number of searches indicates the number of times the corresponding word was used as a search query on a search site that is linked to a news site, and the "number of searches" field stores information about the number of searches over a specified period of time (e.g., one week).

In addition, the "number of searches" item may store information about the number of searches broken down by user attributes. User attributes include demographic attributes and psychographic attributes.

Information stored in the "number of searches" item may also include, for example, the number of times a direct link Lc to the corresponding word on a news site was clicked, or the number of times the corresponding word was searched for in highlight. In this case, the "number of searches" item may also store information related to the content of the distributed article or the category of the distributed article in association with the number of clicks.

In the "Predicted CTR" item, information regarding the predicted CTR of the corresponding word is stored. The predicted CTR is calculated based on the number of searches for the corresponding word, etc. For example, the more recent searches there are, the higher the predicted CTR value will be, and the fewer recent searches there are, the lower the predicted CTR value will be.

The predicted CTR may include, for example, a value calculated for each user attribute, or may include a value calculated for the content of the distributed article or the category of the distributed article. The predicted CTR may also be a value calculated according to the frequency of appearance of each word contained in each distributed article distributed on a news site. In other words, if there are many distributed articles containing the same word, it can be assumed that the word is a word that attracts a lot of attention, and the predicted CTR for such words is calculated to be high.

Returning to the explanation of FIG. 3, the search query storage unit 33 will be described. The search query storage unit 33 stores information about search queries that are candidates for additional links Lt. FIG. 6 is a diagram showing an example of information stored in the search query storage unit 33 according to the embodiment.

As shown in FIG. 6, the search query storage unit 33 stores information for items such as "word 1," "word 2," "number of searches," and "estimated CTR" in association with each other. The "word 1" item stores information about words that are candidates for the above-mentioned search word.

The "Word 2" field stores information about the word that was entered as a search query together with "Word 1" on the search site. The "Number of searches" field stores information about the number of searches for search queries that combine "Word 1" and "Word 2."

The "Predicted CTR" item stores information about the predicted CTR of a search query that combines "word 1" and "word 2." As with the word storage unit 32 described in FIG. 5, the predicted CTR may include, for example, a value calculated for each user attribute, or may include a value calculated for the content of a distributed article or the category of the distributed article. The predicted CTR may also be a value calculated according to the frequency of occurrence of each word included in each distributed article distributed on a news site.

Returning to the explanation of FIG. 3, the control unit 4 will now be described. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 4 includes an acquisition unit 41, an extraction unit 42, a generation unit 43, a selection unit 44, and a provision unit 45, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 4 is not limited to the configuration shown in FIG. 3, and may be other configurations that perform the information processing described below. Also, the connection relationships between the processing units in the control unit 4 are not limited to the connection relationships shown in FIG. 3, and may be other connection relationships.

The acquisition unit 41 acquires information related to the distributed article. For example, the acquisition unit 41 acquires information related to the distributed article submitted by the contributor from the contributor terminal (not shown) via the communication unit 2, and registers the acquired information related to the distributed article in the distributed article storage unit 31.

The acquisition unit 41 also acquires information about search words and information about search queries from a server device that provides a search site or the like, and registers the information in the word storage unit 32 and the search query storage unit 33. The information about the "predicted CTR" registered in the word storage unit 32 and the search query storage unit 33 may be calculated by the server device that provides the search site or the like, or may be calculated on the information processing device 1 side.

The extraction unit 42 extracts search words that are estimated to be desired by users from the distributed articles. For example, the extraction unit 42 extracts, as search words, words with a high predicted CTR registered in the word storage unit 32 from among the words contained in the distributed articles stored in the distributed article storage unit 31.

At this time, the extraction unit 42 may extract search words based on the attributes of the user to whom the article is to be distributed and the predicted CTR calculated according to the category and content of the article to be distributed. In other words, the extraction unit 42 may extract different words as search words depending on the user, or may extract different words as search words depending on the category and content of the article to be distributed.

This allows the extraction unit 42 to extract search words that correspond to the user's interests and concerns, and search words that correspond to the category and content of the distributed article. For example, the extraction unit 42 extracts the top five search words with the highest predicted CTRs from among the words included in the distributed article, and passes information about the extracted search words to the generation unit 43 together with the distributed article.

The extraction unit 42 also extracts search words excluding preset prohibited words. Prohibited words include, for example, the names of celebrities of the same sex, words that lead to sexual expressions or adult sites, discriminatory expressions, words related to rumors, words that suggest suicide, ethically questionable words, words related to slander, and words related to the names of ordinary perpetrators or victims.

For example, when extracting search words from a distributed article, the extraction unit 42 refers to a prohibited word dictionary created in advance and extracts search words excluding prohibited words. In addition, the extraction unit 42 may not extract search words from distributed articles that include prohibited words registered in the prohibited word dictionary for distributed articles.

The prohibited word dictionary for distributed articles includes words such as "suspect," "accident," and "death," and the extraction unit 42 excludes distributed articles that match these words from the setting of direct links Lc and additional links Lt. In other words, such distributed articles are provided without setting direct links Lc and additional links Lt.

This allows "suspects" and "accidents" to avoid creating links to members of the public who are featured as suspects or victims in crime- or accident-related news articles. Also, for example, in sensitive articles such as obituary reports, incorrect links can lead to outrage or defamation. Therefore, by not posting incorrect links in obituary articles about celebrities such as "deaths," such problems can be avoided in advance.

The generation unit 43 generates article content in which a link to a search result using the search word extracted by the extraction unit 42 as a search query is set for the search word displayed in the distributed article.

First, the generation unit 43 generates a link of the search result using the search word extracted by the extraction unit 42 as a search query. Then, the generation unit 43 generates article content by setting the generated link as the search word to be displayed in the distributed article. In addition, the generation unit 43 passes information about the generated article content to the selection unit 44.

The selection unit 44 selects a search query that is estimated to be desired by the user from among multiple search queries that include search words linked in the article content generated by the generation unit 43.

The selection unit 44 refers to the search query storage unit 33 and selects, from among combinations of the search word and other words, the combination with the highest predicted CTR as the search query that is presumed to be desired by the user.

At this time, the selection unit 44 may select, as the combination of the search word and other words, a combination of the search word and a word contained in the distributed article, or may select a combination of the search word and a word not contained in the distributed article.

The selection unit 44 may also select a search query based on a predicted CTR corresponding to at least one of the user attributes of the user to whom the article is to be distributed, the category of the article to be distributed, and the content of the article to be distributed.

Then, the selection unit 44 selects one search query for the search word and passes article content including information about the selected search query to the provision unit 45. Note that the selection unit 44 may select multiple search queries for one search word.

The providing unit 45 superimposes additional content, which lists links to search results using the search query selected by the selecting unit 44, on the article content and provides it. For example, the providing unit 45 generates distribution content Ct by superimposing additional content A, which lists additional links Lt related to the search query selected by the selecting unit 44, on article content in which a direct link Lc is set to the search word, and provides the distribution content Ct to each user.

This allows the user to seamlessly search from the distributed content using the direct link Lc and the additional link Lt. In this way, the providing unit 45 can provide the user with an appropriate search query by providing the distributed content with the direct link Lc and the additional link Lt set.

3. Processing flow
Next, a process procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of a providing process according to the embodiment. Note that the process procedure shown below is repeatedly executed by the information processing device 1.

As shown in FIG. 7, when the information processing device 1 acquires a distributed article (step S101), it extracts a search word from the distributed article (step S102). Next, the information processing device 1 generates article content in which a link to a search result using the search word as a search query is set for the search word displayed in the distributed article (step S103).

Next, the information processing device 1 selects a search query based on the search word (step S104), superimposes the additional content on the article content and provides it (step S105), and ends the process.

4. Modifications
In the above embodiment, the distributed article is a news article posted on a news site, but the distributed article may be any other article distributed through each Web service. For example, the distributed article includes posted information posted by a user on a social networking site or product information when selling on a flea market site.

5. Effects
The information processing device 1 according to the embodiment includes an extraction unit 42 that extracts search words that are presumed to be desired by the user from the distributed article, a generation unit 43 that generates article content that sets links to search results using the search words extracted by the extraction unit 42 as search queries for the search words displayed in the distributed article, a selection unit 44 that selects the search query that is presumed to be desired by the user from a plurality of search queries including the search words to which the links have been set by the generation unit 43, and a provision unit 45 that provides additional content that includes an array of links to search results using the search queries selected by the selection unit 44 by superimposing it on the article content.

In addition, the extraction unit 42 extracts search words based on the click rate of each word contained in the distributed article. In addition, the extraction unit 42 extracts search words based on the click rate of each word expected in the category of the distributed article.

The extraction unit 42 also extracts search words based on the click rate of words predicted based on the log of highlight searches performed on the distributed article. The selection unit 44 also selects a search query that combines a search word to which a link has been set by the generation unit 43 and a word included in the distributed article. The selection unit 44 also selects a search query that combines a search word to which a link has been set by the generation unit 43 and a word not included in the distributed article.

The extraction unit 42 also extracts a number of search words that fit within the upper limit. The extraction unit 42 extracts search words excluding the prohibited words set in advance, and the selection unit 44 selects a search query that does not include the prohibited words.

By using any one or a combination of the above-mentioned processes, the information processing device according to the present application can suggest appropriate search queries to the user.

6. Hardware Configuration
The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

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

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 receives data from other devices via network (communication network) N and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 11, the output devices and input devices are collectively referred to as "input/output devices") via the input/output interface 1600. The CPU 1100 acquires data from the input devices via the input/output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input/output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the 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.

For example, when the computer 1000 functions as an information processing device according to an embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[7. Other]
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

For example, the information processing device described above may be realized by multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

The above-described embodiments and variations can be combined as appropriate to the extent that they do not cause inconsistencies in the processing content.

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

Reference Signs List 1 Information processing device 1 Word 2 Communication unit 2 Word 3 Storage unit 4 Control unit 31 Distribution article storage unit 32 Word storage unit 33 Search query storage unit 41 Acquisition unit 42 Extraction unit 43 Generation unit 44 Selection unit 45 Provision unit 100 User terminal

Claims (11)

An extraction unit that extracts search words that are estimated to be desired by a user from the distributed article;
a generation unit that generates article content in which a link to a search result using the search word extracted by the extraction unit as a search query is set for the search word displayed in the delivery article;
a selection unit that selects a search query that is estimated to be desired by the user from a plurality of search queries including the search word to which the link is set by the generation unit;
a providing unit that provides additional content, the additional content including links to search results using the search query selected by the selecting unit, superimposed on the article content. The extraction unit is
The information processing device according to claim 1 , wherein the words are extracted based on an expected click rate for each word included in the distributed article. The extraction unit is
The information processing device according to claim 2 , wherein the search word is extracted based on a click rate of the word predicted in a category of the distributed article. The extraction unit is
The information processing device according to claim 2 , wherein the search word is extracted based on the click rate of the word predicted in the content of the distributed article. The extraction unit is
The information processing device according to claim 2 , wherein the search word is extracted based on the click rate of the word predicted based on a log of a highlight search performed on the distributed article. The selection unit is
The information processing device according to claim 1 , further comprising: a search query that combines the search word to which the link is set by the generation unit and a word included in the distribution article. The selection unit is
The information processing device according to claim 1 , further comprising: a search query that combines the search word to which the link is set by the generating unit and a word that is not included in the distributed article. The extraction unit is
The information processing apparatus according to claim 1 , further comprising: extracting a number of the search words within an upper limit. The extraction unit is
Extracting the search words excluding predetermined prohibited words;
The selection unit is
The information processing device according to claim 1 , further comprising: selecting a search query that does not include the prohibited word. 1. A computer-implemented information processing method, comprising:
An extraction step of extracting search words that are estimated to be desired by users from the distributed articles;
a generating step of generating article content in which a link to a search result using the search word extracted by the extracting step as a search query is set for the search word displayed in the delivery article;
a selection step of selecting a search query that is estimated to be desired by the user from a plurality of search queries including the search word to which the link is set by the generation step;
and providing additional content, the additional content including an arrangement of links to search results using the search query selected in the selection step, superimposed on the article content and providing the additional content. An extraction step of extracting search words that are estimated to be desired by users from the distributed articles;
a generating step of generating article content in which a link to a search result using the search word extracted by the extracting step as a search query is set for the search word displayed in the delivery article;
a selection step of selecting a search query that is estimated to be desired by the user from a plurality of search queries including the search word to which the link is set by the generation step;
and a providing step of providing additional content, the additional content including links to search results using the search query selected by the selection step, superimposed on the article content.

Images