JP2022021099A - Information processing program, information processing apparatus and information processing method - Google Patents

Abstract

To perform adequate content evaluation, for example.SOLUTION: An information processing program causes a computer to perform content evaluation processing to identify an evidence material of a content using information associated with the content and to generate evaluation information of the content using information associated with the identified evidence material and information associated with the content.SELECTED DRAWING: Figure 3

Description

The present disclosure relates to information processing programs, information processing devices and information processing methods.

Currently, due to an increase in the number of users of SNS (Social Networking Service), a huge amount of content is appropriately provided on networks such as the Internet. For example, Patent Document 1 below discloses an information recommendation method for recommending information suitable for a user from such contents. In Patent Document 1, a list of information to be recommended to the user is generated based on "user's interest" or "user's behavior".

Japanese Unexamined Patent Publication No. 2013-206407

However, the above-mentioned conventional technique recommends information that is considered to be desired by the user, and it cannot be said that the content is properly evaluated from the viewpoint of reliability and the like.

One of the purposes of this disclosure is to propose an information processing program, an information processing device, and an information processing method capable of performing appropriate content evaluation.

The present disclosure is, for example,
Information that identifies the basis material for the content using information about the content, and causes the computer to execute a content evaluation process that generates evaluation information for the content using the identified information about the basis material and the information about the content. It is a processing program.

The present disclosure is, for example,
An evaluation information output process that identifies the basis material of the content using the information about the content and outputs the evaluation information of the content generated by using the specified information about the basis material and the information about the content is performed on the computer. It is an information processing program to be executed.

The present disclosure is, for example,
An information processing unit that identifies the basis material of the content using the information related to the content, and performs the content evaluation process to generate the evaluation information of the content using the identified information related to the basis material and the information related to the content. It is an information processing device that has.

The present disclosure is, for example,
The information processing unit identifies the basis material of the content by using the information about the content, and performs the content evaluation process to generate the evaluation information of the content by using the identified information about the basis material and the information about the content. It is an information processing method to be performed.

FIG. 1 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 2 is a sequence diagram showing an example of the flow of processing performed between the devices constituting the information processing system. FIG. 3 is a diagram for explaining an outline of content evaluation. FIG. 4 is a diagram showing a specific example of the content evaluation method. FIG. 5 is a diagram for explaining an evaluation example of the content. FIG. 6 is a diagram showing an example of information on the content to be evaluated. FIG. 7 is a diagram showing an example of information on an individual / corporate profile. FIG. 8 is a diagram for explaining an evaluation example of other contents. FIG. 9 is a diagram for explaining further evaluation examples of other contents. FIG. 10 is a diagram for explaining a first procedure for implementing the program. FIG. 11 is a diagram for explaining a second procedure for implementing the program. FIG. 12 is a diagram showing an example of displaying the evaluation result by the web browser. FIG. 13 is a diagram showing a configuration example of hardware of a content providing server, a content management server, and a user terminal.

Hereinafter, embodiments and the like of the present disclosure will be described with reference to the drawings. The explanation will be given in the following order.
<1. Background ＞
<2. Embodiment>
<3. Modification example>
The embodiments described below are suitable specific examples of the present disclosure, and the contents of the present disclosure are not limited to these embodiments and the like.

<1. Background ＞
First, in order to facilitate the understanding of the present disclosure, the background of the present disclosure will be described. Now that the information explosion has occurred, there is a flood of unreliable content. For example, there are many cases in which the identity of the originator of the content, the transmission route of the content, the accuracy of the content, and the validity of the content in the relevant field are not clarified. In addition, for example, copyright protection may hinder the improvement of reliability. Furthermore, for example, sloppy descriptions, advertisements aimed at improving business and sales, mere opinions of readers, content with political purpose, scientifically unfounded claims, false experimental results, and metaphorically. Information of unknown truth, such as invalid information, is widespread. As a result, our individual world and society are in a state of chaos.

In such situations, the "reliability" of the content is, for example, the number of viewers, the number of likes that represent the number of favorite votes, and other subjective ratings (eg, the number of stars that represent the rating, the emoticon (Emoticon). )), Etc. are currently ranked. In other words, the legitimacy and credibility of content are rated solely by the principles of democracy.

Network-related companies such as the Internet use advertisements and billing to earn income. And, in many cases, the more impressions, clicks, etc., the higher the income. Therefore, it emphasizes whether or not information can be sold rather than the subjective and objective rating of information, and the business model is based only on the principle of democracy, and there is no incentive to pursue absolute quality.

It suffices if the meta information is properly set for the content used (for example, browsing), but in reality, it is not set as such. The meta information here is, for example, the specialty, career, social achievement, occupation, ethics, reputation, purpose of activity of the information sender, and the universality, accuracy, scientificity, originality, and traceability of the information itself. , The validity, the origin of information on the time axis, history, transmission path, falsification, etc. Moreover, even if the information is rated by others, there is no reliability index specific to oneself. These can cause information consumers to be confused by the content on the network.

For example, at present, there are websites that rank researchers, such as ResearchGate (ReSEARCHGATE®), but in determining the reliability of a general web page, the reliability is supported. I can't find a web browser (hereinafter referred to as a browser as appropriate) that calculates and displays the above with the logic behind it.

For this reason, it cannot be said that the content is properly evaluated in terms of reliability, etc., using the current method alone. Therefore, in the embodiments described below, we propose an information processing program, an information processing device, and an information processing method that can appropriately evaluate the content from the aspect of reliability and the like.

<2. Embodiment>
[2-1. Information processing system configuration example]
FIG. 1 shows a configuration example of an information processing system (information processing system 1) according to an embodiment. The information processing system 1 has, for example, a content providing server 2, a content management server 3, and a user terminal 4. The content providing server 2, the content management server 3, and the user terminal 4 are each connected to the network N. The network N is, for example, the Internet. In the illustrated example, one content providing server 2, one content management server 3, and one user terminal 4 are shown, but a plurality of these may be present.

The content providing server 2 is a device on the content providing side (for example, a web server). Various contents are provided to the content providing server 2 by various content providers. The content management server 3 is a device responsible for managing content, and has, for example, a content search function by a search engine, a content evaluation function using an evaluation algorithm, and the like. Further, the content management server 3 has, for example, various databases necessary for content management. The user terminal 4 is a device (for example, a web client) on the content user side. The user terminal 4 is, for example, a personal computer, a smartphone, a tablet terminal, a mobile phone, a television device, an audio / video playback device, a game machine, or the like, but the specific product form is not limited. The user terminal 4 has, for example, a browser function for viewing content as a content usage function.

The information processing system 1 may have a part or all of the functions of the content management server 3 in another device. For example, the content search function and the content evaluation function of the content management server 3 described above may be performed by different devices. Further, at least one of these functions may be provided to the content providing server 2 or the user terminal 4. As a result, the processing load of the content management server 3 can be reduced or the content management server 3 can be omitted.

[2-2. Processing example in information processing system]
FIG. 2 is a sequence diagram showing an example of the flow of processing performed between the devices constituting the information processing system 1. First, in the information processing system 1, the content management server 3 performs an information collection process (step S1), and requests information about the content from the content providing server 2 (step S2). The information about the content includes, for example, the meta information of the content. The content management server 3 uses, for example, a search engine or the like to visit the network N in response to a request from the content providing server 2 or periodically to request information about the content.

When the content providing server 2 receives this request, it performs an information providing process (step S3) and provides information about the content to the content management server 3 (step S4). Information about the content provided by the content providing server 2 is stored in the database of the content management server 3, for example, and the content management server 3 is in a state where the content can be searched.

In this state, when the user terminal 4 performs the search word designation acceptance process (step S5) and the search word is designated by the user (for example, input by the input device), the designated search word is sent to the content management server 3. Provided (step S6). The content management server 3 performs a content search process using this search word and the information related to the above-mentioned content (step S7), and further performs a content evaluation process for evaluating the content of the search result (step S8).

The content search result and the evaluation result are provided to the user terminal 4 (step S9). The user terminal 4 outputs the evaluation result together with the content search result by displaying the evaluation result on a display, for example, by the first evaluation information output process (step S10). Then, the user terminal 4 performs a content selection acceptance process (step S11), and when the content is selected by the user, requests the content providing server 2 for the selected content (step S12). At the same time, the content management server 3 is requested to evaluate the selected content (step S13). The content providing server 2 performs a content providing process when a content is requested from the user terminal 4 (step S14), and provides the requested content to the user terminal 4 (step S15).

On the other hand, when the user terminal 4 requests the content evaluation, the content management server 3 performs a content evaluation process for evaluating the requested content (step S16) in the same manner as in step S8 described above, and the evaluation result is obtained. Is provided to the user terminal 4 (step S17). The user terminal 4 that receives the content provided from the content providing server 2 and the content evaluation result from the content management server 3 displays the content and the evaluation result on a display, for example, by the second evaluation information output process. Output by (step S18).

As a result, the user can know the evaluation result of the content at the time of content search and content use. The user terminal 4 outputs the evaluation result only in any one of the case of searching the content and using the content (for example, including the use of the direct selection of the content by the URL (Uniform Resource Locator)). May be.

[2-3. Overview of content evaluation process]
Next, the outline of the above-mentioned content evaluation process will be described with reference to FIG. As for the above-mentioned content search process, a known method can be adopted, and detailed description thereof will be omitted here.

When evaluating the content, the content management server 3 clarifies the information source of the content and identifies the supporting material. The content to be evaluated is content (tertiary content) including tertiary information (3rd Class information). Tertiary content includes, for example, content originating from self-proclaimed experts, advertisers, bloggers, consumers, etc., and Wikipedia: WIKIPEDIA (registered trademark). The contents of online encyclopedias such as. That is, the tertiary content refers to web content such as general web pages (including SNS). The type of content is not limited to documents (including figures, graphs, etc.), but may be images (including video), audio, and the like. The tertiary content is stored in, for example, the database of the content providing server 2 described above.

The content management server 3 classifies, for example, the content when specifying the basis material of the content. The classification items are predetermined items such as "IT security" and "machine learning". Then, the supporting material is extracted based on the primary and secondary information (1st and 2nd Class information) corresponding to the classification item. Primary and secondary information means, for example, relatively reliable predetermined information provided by academics, institutes, and the like.

Ideally, the primary information is physical (Real Documents), but in this era, there are web contents that can be primary information, and the boundaries are ambiguous. Therefore, in order to draw a clear line, the primary information is, for example, information provided by an independent public research institute that has no interest in religion, politics, economy, etc. (including web content). It may be limited to. For example, primary information includes highly reliable digital contents, information provided by research institutes, libraries, museums, publishers, and the like.

The content management server 3 attempts to extract the evidence material from the primary information, and if the evidence material cannot be extracted, the content management server 3 extracts the evidence material from the secondary information. Secondary information is placed under strict legal provisions that can be extracted from authors and materials that are relatively credible on expert network sites such as ResearchGate (ReSEARCHGATE®) and the web. Information provided by the organization or social manager. Web contents are also included in this secondary information.

For example, as shown in the figure, the content management server 3 has meta information such as NE extraction and meta tags of both the tertiary information of the content to be evaluated and the primary and secondary information for extracting the supporting material. Is used to calculate the degree of similarity to each other. Then, the content management server 3 creates a citation graph / edit graph based on the calculated similarity, and identifies the information source of the content and related materials in consideration of the relationship on the time axis.

The citation graph (as well as the edit graph) represents, for example, the time when the content was created on one of the two axes orthogonal to each other, and the classification to which the content belongs on the other, and the range to which each content corresponds is displayed on the graph. Arrange and create the figure to be represented. By creating a citation graph and an edit graph, it becomes possible to grasp the creation time and classification of each content. The information source of the content and the related material are not limited to this, and may be specified by another method. The content management server 3 is, for example, when related materials are included in primary and secondary materials (materials containing primary and secondary information), the primary and secondary materials thereof. If the relevant material is specified as the supporting material and is not included, the supporting material shall not be extracted.

Next, the content management server 3 obtains the reliability of the content to be evaluated. The content management server 3 has, for example, meta information (for example, the number of citations, logically inconsistent) between the content to be evaluated and the primary and secondary contents (web contents of the primary and secondary materials). While referring to the logical consistency score indicating the level of the absence, author attributes, reputation of the presenting institution, presence / absence of experimental information, similarity, traceability from the origin on the time axis of information, universal validity, etc.) Calculate the reliability.

More specifically, as illustrated, the content management server 3 may include, for example, meta-information on the tertiary content to be evaluated and meta-information on the primary and secondary content (eg, an individual regarding a source). The reliability of the content is calculated using the corporate profile and the information content analysis profile) and the user's pre-credit setting (individual setting) to evaluate the content. In this way, the originator of the information and the accuracy of the information are taken into consideration in the calculation of the reliability of the content. The meta information (including the profile) of the primary and secondary contents is stored in advance in the database of the content management server 3, for example.

The personal / corporate profile regarding the source includes, for example, information representing occupation (Profession), activity purpose (Objective), organizational form (Classification), specialty (Expertise), and reputation (Reputation). Information content analysis profiles that represent the reliability of information content include, for example, information trustability, scientific-ness, creative-ness, accuracy-ness, and universality (universality). It contains information that represents Universality).

The user's pre-credit setting is the setting of the reliability index specialized for each user, for example, the source credit list, the source suspicion list, and the analysis target setting (for example, the content in the IT field is analyzed). It contains information that represents. The user's pre-credit setting is, for example, set by each user independently in advance using the user terminal 4 or the like, and is stored in the storage device of the user terminal 4 or the database of the content management server 3.

The content management server 3 does not simply obtain the user's interest index, but evaluates the degree of matching with the user's subjective reliability, general credibility, and objective validity. Specifically, the content management server 3 generates a content profile (Content Profile) as content evaluation information. This content profile includes, for example, a list of supporting materials as information representing the supporting materials, self-matching degree, general credibility, and information representing the TSCAU index.

The evidence material list represents, for example, a list of the evidence materials of the above-mentioned contents. The self-matching degree represents, for example, the reliability of the content (subjective matching degree for the user) including the subjective credibility of each user, and the general credibility is based on, for example, supporting materials. It represents the objective reliability of content (general public credit index trusted by the general public). The TSCAU index represents each of the five levels of credibility, scientificity, originality, accuracy, and universality of the content to be evaluated as a numerical value (for example, a numerical value from 0 to 1). For example, the accuracy of the tertiary content is evaluated based on the credibility of the information source / sender and the degree of relevance of the primary information to the meta information.

In this way, the content management server 3 sets the attributes of the content to be evaluated while referring to the extracted primary information and the corresponding secondary information when the primary information is not extracted. Judgment of reliability, that is, judgment of the sender's identity, expertise, credibility, etc. of tertiary information, and content basis material, accuracy, scientificity, universality, originality, self-matching degree, general Judgment such as credibility is made. Then, a content profile based on the determination result is generated as an evaluation result, provided to the user terminal 4, and output by using, for example, the browser function of the user terminal 4.

The content management server 3 has a multifaceted rating of information such as a citation graph, an edit graph, and an information flow graph on a time axis within a specified range, and TSCAU, and the accuracy of the sender's identity and information source. The reliability can be obtained in consideration of the above, and the user terminal 4 can output the reliability.

When evaluating content, it is possible to classify not only the information that the user is vaguely interested in, but also the information that personally trusts the information that is of interest in more detail and the information that is suspected. While referring to the information sources belonging to the primary information as credible information, the multifaceted credit index of the tertiary content is obtained. This allows users to be alerted to suspicious information and develop critical thinking.

[2-4. Content evaluation method]
FIG. 4 shows a specific example of the content evaluation method. When evaluating the content, the content management server 3 uses information on primary and secondary materials such as books, papers, and research and research materials, and personally set information indicating the subjective reliability of the user. The personal setting information is the information set by the user's prior credit setting described above.

Information about primary and secondary materials is collected, for example, as follows: The content management server 3 collects vocabulary for each domain (field) of the contents of the primary and secondary materials from the content providing server 2. Further, the content management server 3 collects the structured knowledge when the information of the primary and secondary materials is structured and stored in the database.

Next, the content management server 3 performs content analysis and extraction of meta information using the collected vocabulary and structured knowledge. Then, the content management server 3 specifies author information / citation information, logical consistency index, domain tag, quantitative information in the material, and the like. Then, the content management server 3 uses the identified information to make primary and secondary materials (including general books) into a credit list and a suspicious list (for example, a numerical value of the credit list: 0 ≤ credibility ≤). It is divided into 0.5 and the numerical value of the suspicion list: 0.5 <credibility ≤ 1.0) and stored in the database. At this time, for example, the distribution is determined based on accuracy, scientificity, universality, and the like. The accuracy is calculated based on, for example, peer-reviewed information. Scientificity is determined, for example, by the presence or absence of experimental results. Universality is determined, for example, by the number of citations, field dependence, and the like.

The personal setting information is set as follows, for example. As described above, the personal setting includes the source credit list, the source suspicion list, and the like as setting items. Both of these lists are custom lists, and each contains items for determining the credibility of, for example, URL / DOI (Digital Object Identifier), author name, book, ISBN (International Standard Book Number), research institution, etc. I'm out.

Then, the evaluation of the content is performed, for example, as follows. Content evaluation first estimates the domain of the content to be evaluated. In addition, the author of the content to be evaluated is determined and meta information is extracted. Next, the pre-selection of the supporting material is performed using this information and the information of the primary and secondary materials stored in the database or the like. Here, for example, when there is no supporting material (when the supporting material cannot be extracted), it is set as "originality: 1.0 (numerical range: 0 to 1)". If there is evidence, the similarity between the content to be evaluated and the evidence is calculated. At this time, the originality is also calculated by, for example, "1.0-similarity (numerical range: 0 to 1)". Then, an evaluation list of the evidence material having a predetermined threshold value or more (for example, a list of the similarity between the evidence material and the evidence material) is generated. The evidence material and the evaluation list are sent to the user terminal 4, and the user terminal 4 displays the evidence material and the evaluation list as a credit evaluation of the browsing page by the browser function.

Further, the content management server 3 extracts from the meta information about the above-mentioned primary and secondary materials what is common to the meta information (source meta information) of the content to be evaluated, and uses it as the source metadata. Remember. Then, for example, at the time of content evaluation, the TSCAU index of the content to be evaluated is calculated using the source metadata, the above-mentioned author determination result, the meta information of the content, the supporting material, the evaluation list, and the like. For example, the calculation of credibility takes into consideration the author's specialty / activity purpose, content science, accuracy, and the like. The calculated TSCAU index is sent to the user terminal 4, and the user terminal 4 displays the TSCAU index, that is, accuracy, credibility, scientificity, universality, and originality as the credit evaluation of the browsed page by the browser function. do. In the illustrated example, accuracy: 0.7, credibility: 0.1, scientificity: 0.5, universality: 0.3, originality: 0.2 (numerical range: 0 to 1). The calculation of credibility ratings such as these TSCAU indicators is, for example, if there is a user or expert credibility rating for a dataset consisting of actual content (eg, a web page), with arbitrary rules as standard. It can be determined by machine learning by appropriately combining the credibility of business entities, authors, supporting materials, etc.

As for the supporting materials, the materials will be sorted by referring to the personal settings. Whether the supporting material is a credit material set in the personal settings (material included in the customized credit list), a suspicious material (material included in the customized suspicious list), or other materials. Is determined. In the case of credit material or suspicious material, subjective / objective matching degree calculation is performed by a predetermined algorithm, self-matching degree including user's subjectivity is calculated, and the calculated self-matching degree is sent to the user terminal 4. The user terminal 4 displays the degree of self-matching as a credit evaluation of the browsing page by the browser function. On the other hand, in the case of other materials, general credibility is calculated. The calculated general credibility is sent to the user terminal 4, and the user terminal 4 displays the general credibility as a credit evaluation of the browsing page by the browser function. In the illustrated example, the degree of self-matching is 0.3 and the general credibility is 0.6 (numerical range: 0 to 1).

In this way, the content management server 3 generates the basis material and the evaluation list, the TSCAU index, the self-matching degree, and the general credibility information as the evaluation result of the content, and provides the information to the user terminal 4. The user terminal 4 displays (outputs) the evaluation result by the browser function.

[2-5. Content evaluation example 1]
FIG. 5 is a diagram for explaining an evaluation example of the content. FIG. 6 shows an example of information of the content to be evaluated (in this example, a web page). The web page shown in FIG. 6 is a virtual one for explanation (https://www.●●●.com/▲▲▲-top100-wst-pw2020/). The same applies to the web pages appearing in the following explanations.

When evaluating a browsing page, the content management server 3 first extracts meta information about the browsing page, and identifies evaluation information such as domain, applicable time, author, information source, and quantitative information from the extracted meta information. do. The domain is specified, for example, by making a determination by a keyword. The relevant time is specified by extracting the time such as, for example, the date. Authors and sources of information are identified using, for example, Natural Language Processing (NLP) and references to known legal entity / individual lists such as the individual legal entity profile described above. Quantitative information is specified using, for example, natural language processing and extraction of numerical information.

In the information example shown in FIG. 6, for example, the domain is specified as "IT Security" because the keyword "Passwords" is included in the heading in the page. In addition, the relevant time is specified as "2020" from the page contents. Also, from the information "by JHON SMITH" in the page, the author is identified as "JOHN SMITH belonging to ■■■", and from the description "according to ▲▲▲" in the page, the information source is " ▲▲▲ ”is specified. In addition, it extracts the numerical information in the page and identifies the quantitative information as "evaluating more than 5 million passwords".

Then, the content management server 3 identifies the peculiarity of the browsed page from this evaluation information. In the illustrated example, the specificity is 1.0 (numerical range: 0 to 1).

Further, the content management server 3 determines the scientificity from the quantitative information. More specifically, the content management server 3 analyzes the content (in this case, the web page being browsed) to determine the presence or absence of quantitative information, the presence or absence of statistical survey data, and the like, and the content is determined according to the judgment result. Evaluate the degree of science. For example, in the illustrated example, the scientific value is determined to be 1.0 as having a statistical advantage from the quantitative information.

In addition, the content management server 3 determines the credibility of the identified author and the information source, respectively. For example, for the credibility of the author, John Smith: # 3845, ■■■: # 32 (# ... is an identification number) is registered as related information in the above-mentioned personal / corporate profile database (Parson / Org DB). Credibility of John Smith is 0.1, as it is a common person / organization name with unknown attributes. For example, the credibility of the information source is as follows: ▲▲▲: .com (business entity: Business Entity) is registered in the database of personal / corporate profile, and the credibility is 0.7, assuming that it is a surviving network-related company. It has become.

FIG. 7 shows an example of information on an individual / corporate profile. The personal / corporate profile information includes, for example, information for credibility such as the career and history of an individual / organization (including a corporation). The content management server 3 extracts, for example, attribute information of an individual / organization (for example, history, person in charge, specialized field, activity purpose, organizational form, etc.) based on the information for achieving credibility. For example, the information shown in FIG. 7 is related to ▲▲▲, and from this information etc., as attribute information of ▲▲▲, history: 10 years or more, responsible person: CEO (Chief Executive Officer), CPO (Chief Product Officer) ), Engineering Director (Director, Engineering), Specialty: Security applications, Activity purpose: Sales improvement (1 million customers), Organizational form: Small network-related companies, etc. are extracted. Then, the content management server 3 determines the credibility of the individual / organization based on the extracted attribute information, and stores the determined credibility in the database of the individual / corporate profile in association with the individual / organization, for example. is doing. In the illustrated example, ▲▲▲ is stored as credibility: 0.7.

Then, the content management server 3 determines the credibility of the browsing page based on, for example, the credibility of the author, the credibility of the information source, and the scientific nature. In the illustrated example, the credibility: 0.1 is obtained by calculating the minimum values of the author's credibility, the credibility of the source, and the scientificity by the function MIN.

In addition, the content management server 3 searches for related materials on the browsing page based on evaluation information (particularly, information source, author, domain), and from the primary and secondary materials stored in the database. Identify the underlying material for the browsing page. Then, the degree of similarity between the identified supporting material and the browsed page is determined, and the originality is obtained from the obtained degree of similarity. In the illustrated example, the similarity is determined to be 0.1 and the originality is determined to be 0.9. In addition, the universality of the browsed page is obtained by referring to the supporting material, and the general credibility of the browsed page is determined based on the obtained universality. In the illustrated example, universality: 0.0 and general credibility: 0.0 are determined.

Further, the content management server 3 refers to the personal setting and calculates the self-matching degree based on the information of the item corresponding to the content of the browsing page. In the illustrated example, the function AVG is used to calculate the average value of the corresponding items (John Smith: 0.3 included in the suspicion list, ▲▲▲: 0.7 included in the credit list), and the degree of self-matching: I'm looking for 0.5. The fields of the personal setting items referred to are "IT" and "safety", which are common to the domain of the browsing page. On the other hand, ■■■ is not set in the personal credit list or suspicion list, and the creditworthiness is ■■■: 0.4 (initial value of the database).

Further, the content management server 3 determines the accuracy by referring to the information of the item corresponding to the content of the browsing page, the credibility, and the general credibility by referring to the personal setting. In the illustrated example, the function MIN is used to calculate the minimum value of the corresponding item in the personal settings. Then, the minimum value: 0.3, the credibility: 0.1, and the maximum value of the general credibility: 0.0 are calculated by the function MAX to obtain the accuracy: 0.3.

In this way, the content management server 3 estimates the self-matching degree and accuracy of the browsing page from the "credibility" of the source based on the explicit personal settings (credit list / suspicion list) of the user. There is. Speaking of which, instead of sticking to one polar interest singularity, it is based on a more realistic view of the world that there are two polar sources of information, both positive and negative, scattered around the world. There is.

The content management server 3 provides the user terminal 4 with the information about the supporting material, the TSCAU index, the self-matching degree, the general credibility, etc. obtained as described above as the evaluation result of the browsing page.

[2-6. Content evaluation example 2]
FIG. 8 is a diagram for explaining an evaluation example of other contents. Note that FIG. 8 shows an evaluation example of a web page (https://○○○.net/news/wst-pw2020/).

In the example shown in FIG. 8, for example, the domain is specified as "IT Security" because the heading in the page includes a keyword related to security called "worst password". In addition, the relevant time is specified as "2020" from the page contents. Furthermore, by extracting the citation link in the page, the information source is specified as "www. ■■■ .com / *** /. The author is unknown, and there is no evidence information as quantitative information. It is supposed to be.

And, regarding the quantitative information, since there is no evidence information, the scientific value is set to 0.0. In addition, although the author is unknown and the credibility of the author is unknown, the credibility is set to 0.4 here because the information source is registered in the database of personal / corporate profiles. In addition, the degree of similarity with the supporting material is 1.0 and the originality is 0.0, assuming that there is no difference from the content of the information source. Furthermore, here, with reference to the scientificity: 1.0 and accuracy: 0.3 of the supporting material and the above-mentioned credibility: 0.4, the accuracy is set to 0.3. In this way, if the similarity with the supporting material is 1.0 (there is no difference in the content), the accuracy of the supporting material may be inherited as it is.

The universality (not shown) and general credibility are the same as in the previous specific example (universality: 0.0, general credibility: 0.0). Since the item corresponding to the organization name XX included in the URL is registered as XX: 0.2 in the suspicion list of personal settings, the degree of self-matching is 0.2.

The content management server 3 provides the user terminal 4 with the information about the supporting material, the TSCAU index, the self-matching degree, the general credibility, etc. obtained as described above as the evaluation result of the browsing page.

[2-7. Content evaluation example 3]
FIG. 9 is a diagram for explaining an evaluation example of other contents. FIG. 9 shows an evaluation example of a web page (https://△△△.jp/post-2006/).

In the example shown in FIG. 9, for example, the domain is specified as "IT Security" because the heading in the page includes the keyword "worst password" (not shown). In addition, the relevant time is specified as "2020" from the page contents. Also, although not shown here, the author is identified as "Jacob Brown" from the page content. In addition, the information source is specified as "▲▲▲" from the description that "▲▲▲ has announced ..." on the page. Regarding quantitative information, there is a description on the page that "If you are using a password included in the top 100, you should change it immediately" and "5 million passwords have leaked to the Internet". It cannot be used as evidence information. This is because it is quantitative, but statistical surveys are not mentioned.

And since the quantitative information cannot be used as evidence information in this way, the scientific value is set to 0.3. The author "Jacob Brown" is not registered in the personal / corporate profile database. Therefore, here, information about the author, such as history, affiliation, specialty, activity purpose, organizational form, etc., is extracted from the sender's profile (for example, web content), and the credibility of the author is determined using the extracted information. I have decided. For example, the profile of the author "Jacob Brown" has a history of "#### University, □□ Mag Analyst", a affiliation of "News Site ###, Senior Reporter", and a specialty of "history, BA". The purpose of the activity is to increase the number of readers, and the organizational structure is "network-related company". Based on this information, here, the credibility is set to 0.3 because the affiliation is a reporter and the specialty is history. Then, using the information of the corresponding item in the personal settings and this credibility: 0.3 etc., the accuracy is set to 0.27.

Since there is no evidence material, universality, similarity, and originality are unknown. Since there is no supporting material for general credibility, it is the same as the previous specific example (general credibility: 0.0). In this way, for example, when there is insufficient information, only items that can be calculated may be obtained. Since the item corresponding to the organization name △△△ included in the URL is registered as △△△: 0.9 in the personal setting credit list, the degree of self-matching is set to 0.9.

The content management server 3 provides the user terminal 4 with the information about the supporting material, the TSCAU index, the self-matching degree, the general credibility, etc. obtained as described above as the evaluation result of the browsing page. The user terminal 4 receiving the evaluation result outputs the evaluation result of the browsing page.

[2-8. Program implementation example]
Here, an example of implementing the program on the user terminal 4 will be described. 10 and 11 are diagrams for explaining an example of the mounting procedure. The program that performs the content evaluation process described above is implemented as an add-on function in the browser, for example. Thereby, for example, when searching for a desired document and displaying the search result, or when displaying the desired document, the user can browse the evaluation result according to the information reliability.

For example, access a web store to which an add-on program or the like is distributed as shown in FIG. 10, and select "search with information reliability" as a desired extended function. Next, as shown in FIG. 11, click (select) "Add to browser", implement it as an extension of the browser, and use "Search with information reliability" to display the evaluation result of the above-mentioned content. do.

Specifically, when displaying the content list of the search result by the content search function provided in the browser, the evaluation information of the content regarding the content of the search result is displayed. When the user searches for the content, the user can refer to the evaluation information described above and perform an efficient search suitable for the user's purpose. In addition, when using the content, the evaluation result of the content is displayed. This makes it possible to present the user with a rating of the content. The method of adding an extended function is not limited to this. For example, you may add it by another procedure provided in the browser. Further, this information reliability presentation function is not limited to the addition of the extension function, and may be incorporated as a standard function in the software program of the browser.

[2-9. Content evaluation display example]
FIG. 12 is a diagram showing an example of displaying the evaluation result by the browser. As shown in the figure, for example, if you enter "worst password" as the search word and execute a search, four types of evaluation items (list of evidence materials, self-matching degree, general credit degree and TSCAU index) will be displayed along with the content of the search result. The evaluation information to have is displayed.

The content evaluation information is displayed by sorting the content list of the search results based on the magnitude of the evaluation level of the evaluation item selected by the user. In the illustrated example, the search results are displayed in descending order of the degree of matching by the sort setting that can be appropriately set by the user. The content evaluation information may be sorted and displayed in descending order of general credit rating. In addition, these values may be sorted in ascending order. Further, it may be possible to display in a complex manner, such as displaying items having a high degree of scientificity and self-matching (for example, items having a threshold value or higher). Further, the display / non-display setting for each item of the evaluation result may be changed, or the display location, size, expression, etc. of each item of the evaluation result may be customized. .. As described above, the output form of the evaluation result is not limited to the illustrated one. By adopting such a display mode, the user's search efficiency can be improved.

[2-10. Hardware configuration example]
Finally, a configuration example of the hardware of the content providing server 2, the content management server 3, and the user terminal 4 will be described with reference to FIG.

The content providing server 2, the content management server 3, and the user terminal 4 each have an input unit 11, a storage unit 12, a communication unit 13, an output unit 14, and an information processing unit 15 as functional blocks, respectively. The input unit 11, the storage unit 12, the communication unit 13, the output unit 14, and the information processing unit 15 are interconnected via, for example, an interface or a bus.

The input unit 11 is composed of, for example, various switches, a keyboard, a touch panel, a mouse, a microphone, and the like, and has a function of inputting various information by user operation or the like. The storage unit 12 is composed of, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk drive (HDD: Hard Disk Drive), a solid state drive (SSD: Solid State Drive), or the like. It has a function to store various information. The storage unit 12 may be composed of removable removable media such as a USB memory, a memory card, and an optical disk. For example, the content providing server 2 and the content management server 3 have various databases as the storage unit 12.

The communication unit 13 has a communication function of connecting to the network N (see FIG. 1) and communicating with other devices on the network N. The connection to the network N may be wired or wireless. Examples of wireless communication include wireless LAN (Local Area Network) such as Wi-Fi (Wireless Fidelity), 4G (4th generation mobile communication system), Bluetooth (registered trademark) and the like. The output unit 14 is composed of, for example, a display, a speaker, and the like, and has a function of outputting various information.

The information processing unit 15 is composed of a processor such as a CPU (Central Processing Unit), and has a function of executing various processes (for example, processes related to the above-mentioned content evaluation) according to a program stored in the storage unit 12. have. The program is not limited to the one stored in the storage unit 12 in advance, and may be provided via a network (for example, network N). It may also be partially executed by other devices via the network. The function of the information processing unit 15 is not only realized by a program, but may also be realized by combining a dedicated device, a circuit, or the like by hardware having the function. The information processing apparatus according to the present disclosure includes at least an information processing unit 15 that executes processing related to content evaluation.

It should be noted that each functional block is not limited to being integrally configured, and a part or all of them may have a separate structure. In that case, the connection between the devices may be wired or wireless. In the case of wireless connection, for example, the above-mentioned wireless communication can be used. That is, the units constituting each functional block may be connected via a network.

[2-10. summary]
As described above, the program (information processing program) according to the present embodiment identifies the basis material of the content by using the information related to the content such as the meta information of the content, and the meta information of the specified basis material and the like. The information processing unit 15 of the content management server 3 is made to execute the content evaluation process for generating the evaluation information of the content by using the information about the basis material and the information about the content.

In addition, the program (information processing program) according to the present embodiment identifies the basis material of the content by using the information about the content, and the content generated by using the information about the specified basis material and the information about the content. The evaluation information output process for outputting the evaluation information of the above is executed by the information processing unit 15 of the user terminal 4.

As a result, it is possible to obtain an objective evaluation result based on the supporting material, and it is possible to appropriately evaluate the content from the aspect of reliability and the like.

More specifically, you can use TSCAU to rate tertiary content in more detail, as well as use personal belief settings to discover websites that are more subjective and more appropriate to you. In addition, it is possible to identify the supporting materials while utilizing the knowledge of experts so that a multifaceted subjective and objective evaluation of the information content and information source can be obtained. In other words, it can be a browser that can display multifaceted credit attribute information.

<3. Modification example>
Although the embodiments of the present disclosure have been specifically described above, the present disclosure is not limited to the above-described embodiments, and various modifications based on the technical idea of the present disclosure are possible. For example, various modifications as described below are possible. Further, in the following modification modes, one or a plurality of arbitrarily selected variants may be appropriately combined. In addition, the configurations, methods, processes, shapes, materials, numerical values, and the like of the above-described embodiments can be combined with each other as long as they do not deviate from the gist of the present disclosure. It is also possible to divide one thing into two or more.

For example, in the above-described embodiment, the case of evaluating the content on the Internet is illustrated, but the present invention is not limited to this, and the information is evaluated using the network such as the content on the closed network in the predetermined area. It should be.

Further, for example, in the above-described embodiment, the calculation method of the credibility evaluation value such as the self-matching degree, the general credibility, and the TSCAU index has been specifically described, but the calculation method is not limited to the above-mentioned one. For example, the above-mentioned various information, attributes, calculation algorithms, and the like may be appropriately changed and obtained.

The present disclosure may also have the following structure.
(1)
Information that identifies the basis material for the content using information about the content, and causes the computer to execute a content evaluation process that generates evaluation information for the content using the identified information about the basis material and the information about the content. Processing program.
(2)
The information processing program according to (1), which generates the evaluation information by further using the information representing the user's subjective reliability that can be set for each user.
(3)
The information processing program according to (2), wherein the evaluation information of the content includes information on the degree of matching with the subjective reliability of the user.
(4)
The information processing program according to any one of (1) to (3), wherein the evaluation information of the content includes general credibility information indicating an objective reliability based on the supporting material.
(5)
The information processing program according to any one of (1) to (4), wherein the evaluation information of the content includes information indicating the accuracy, credibility, scientificity, universality and originality of the content.
(6)
The information processing program according to any one of (1) to (5), wherein the evaluation information of the content includes information representing the supporting material.
(7)
The information processing program according to any one of (1) to (6), which extracts the above-mentioned basis material from a predetermined material having high reliability.
(8)
The information processing program according to any one of (1) to (7), wherein the information regarding the supporting material is information indicating the reliability of the information content of the supporting material.
(9)
The information processing program according to any one of (1) to (8), wherein the information regarding the supporting material is information regarding the source of the supporting material.
(10)
The information regarding the content includes at least one of information representing the field of the content, information representing the relevant time, information representing the author, information representing the information source, and quantitative information (1) to (9). Information processing program described in any.
(11)
The information processing program according to any one of (1) to (10), wherein the information regarding the content includes information regarding the source of the content.
(12)
The information processing program according to any one of (1) to (11), wherein the content is a document in a web page including an SNS (Social Networking Service), an image including a video, or an audio.
(13)
An evaluation information output process that identifies the basis material of the content using the information about the content and outputs the evaluation information of the content generated by using the specified information about the basis material and the information about the content is performed on the computer. Information processing program to be executed.
(14)
The information processing program according to (13), which can be implemented as an extension function in a web browser.
(15)
The information processing program according to (13) or (14), which displays the evaluation information of the content regarding the content of the search result when displaying the content list of the search result by the content search function provided in the web browser.
(16)
The content evaluation information has a plurality of evaluation items, and the content list of the search results is sorted and displayed based on the magnitude of the evaluation level of the evaluation items selected by the user (15). Information processing program.
(17)
An information processing unit that identifies the basis material of the content using the information about the content, and performs the content evaluation process to generate the evaluation information of the content by using the identified information about the basis material and the information about the content. Information processing device to have.
(18)
The information processing unit identifies the basis material of the content by using the information about the content, and performs the content evaluation process to generate the evaluation information of the content by using the identified information about the basis material and the information about the content. Information processing method to be performed.

1 ... Information processing system, 2 ... Content providing server, 3 ... Content management server, 4 ... User terminal, 11 ... Input unit, 12 ... Storage unit, 13 ... Communication Unit, 14 ... Output unit, 15 ... Information processing unit, N ... Network

Claims (18)

Information that identifies the basis material for the content using information about the content, and causes the computer to execute a content evaluation process that generates evaluation information for the content using the identified information about the basis material and the information about the content. Processing program. The information processing program according to claim 1, wherein the evaluation information is generated by further using information representing the user's subjective reliability that can be set for each user. The information processing program according to claim 2, wherein the evaluation information of the content includes information on the degree of matching with the subjective reliability of the user. The information processing program according to claim 1, wherein the evaluation information of the content includes general credibility information representing an objective reliability based on the supporting material. The information processing program according to claim 1, wherein the evaluation information of the content includes information representing the accuracy, credibility, scientificity, universality, and originality of the content. The information processing program according to claim 1, wherein the evaluation information of the content includes information representing the supporting material. The information processing program according to claim 1, wherein the evidence material is extracted from a predetermined material having high reliability. The information processing program according to claim 1, wherein the information regarding the supporting material is information indicating the reliability of the information content of the supporting material. The information processing program according to claim 1, wherein the information regarding the evidence material is information regarding the source of the evidence material. The information processing program according to claim 1, wherein the information regarding the content includes at least one of information representing the field of the content, information representing the relevant time, information representing the author, information representing the information source, and quantitative information. .. The information processing program according to claim 1, wherein the information regarding the content includes information regarding the source of the content. The information processing program according to claim 1, wherein the content is a document in a web page including an SNS (Social Networking Service), an image including a video, or an audio. An evaluation information output process that identifies the basis material of the content using the information about the content and outputs the evaluation information of the content generated by using the specified information about the basis material and the information about the content is performed on the computer. Information processing program to be executed. The information processing program according to claim 13, which can be implemented as an extension function in a web browser. The information processing program according to claim 13, which displays the evaluation information of the content regarding the content of the search result when displaying the content list of the search result by the content search function provided in the web browser. The content evaluation information has a plurality of evaluation items, and according to claim 15, the content list of the search results is sorted and displayed based on the magnitude of the evaluation level of the evaluation items selected by the user. Information processing program. An information processing unit that identifies the basis material of the content using the information related to the content, and performs the content evaluation process to generate the evaluation information of the content using the identified information related to the basis material and the information related to the content. Information processing device to have. The information processing unit identifies the basis material of the content by using the information about the content, and performs the content evaluation process to generate the evaluation information of the content by using the identified information about the basis material and the information about the content. Information processing method to be performed.

Images