Granted Patent B2

US 12,277,180 · App. 18/147,992 · Granted Apr 15, 2025

Inventor: Kazuhiro Miyajima (Tokyo, JP)

G06F16/953G06N20/00

Abstract

Claims (62)

1. An information processing apparatus comprising a processing circuitry, wherein

the information processing apparatus stores in a storage unit a trained model generated by training using as training data multiple types of words and a result of searching Internet with a search engine using the multiple types of words as a search query, the multiple types of words being selected from a first type of words indicating areas, a second type of words indicating industry types, a third type of words indicating products or services, a fourth type of words describing or modifying areas, a fifth type of words describing or modifying industry types, or a sixth type of words describing or modifying products or services;

the trained model receives, as an input, designated words designated by a user, and thereby outputs an article content, and

the information processing apparatus causes the processing circuitry to execute:

receiving an input of at least a first word and a second word different in type from the first word as first designated words, the first word being one of the first, second, third, fourth, fifth, or sixth types of words; and

outputting a first article content corresponding to the received first designated words, based on the received first word and second word and the trained model,

wherein the trained model is generated by training based on a result in a predetermined search ranking range among results of a search on the Internet based on the search query;

wherein, the trained model is generated by training using as training data the multiple types of words and generalized sentences included in an article content included in the results of searching Internet with a search engine using the multiple types of words as a search query; and

the processing circuitry outputs the first article content separated from the generalized sentences included in the training data held in the storage unit by a predetermined range with respect to a distance between sentences included or a similarity between words included, based on the received first word and second words and the trained model.

2. The apparatus according to claim 1 , wherein

the receiving includes receiving, as the first word and the second word included in the first designated words, a combination including at least one selected from a group consisting of a word relating to an industry type of the user, a word relating to a commercial area of the user, and a word describing or modifying the industry type or the commercial area, and

the outputting includes outputting the first article content based on the received first designated words and the trained model.

3. The apparatus according to claim 1 , wherein

the information processing apparatus causes the processing circuitry to further execute acquiring, from the user, information of a plurality of words describing or modifying a product or service that an organization to which the user belongs plans to newly release,

the receiving includes receiving, as the first designated words, at least one word selected from a group consisting of a plurality of words describing or modifying the product or service that the organization to which the user belongs plans to newly release, and

the outputting includes outputting the first article content based on the received first designated words and the trained model.

4. The apparatus according to claim 1 , wherein

when a second article content different from the first article content is output to the same user, the information processing apparatus causes the processing circuitry to:

receive an input of second designated words including at least one word different from the words constituting the first designated words; and

output the second article content corresponding to the second designated words, based on the received second designated words and the trained model.

5. The apparatus according to claim 1 , wherein

the first article content is associated with a website managed by the user, and

the information processing apparatus causes the processing circuitry to further execute acquiring a result of an access by a second user, the second user having accessed the first article content to the website managed by the user, and presenting to the user a graph illustrating the acquired result of the access.

6. The apparatus according to claim 1 , wherein

the information processing apparatus further stores in the storage unit a second trained model generated by training using as training data a result of associating an article content with a result of an access by a second user, the second user having accessed the article content to a website managed by the user,

the second trained model receives, as an input, designated words designated by the user, and thereby outputs a prediction result of a number of accesses by the second user who has accessed the article content to the website, and

the information processing apparatus causes the processing circuitry to execute:

receiving an input of at least a third word and a fourth word different from the third word as third designated words; and

outputting, based on the received third word and fourth word, the trained model, and the second trained model, a third article content corresponding to the received third designated words together with a prediction result of a number of accesses by the second user who has accessed the third article content to the website.

7. The apparatus according to claim 1 , wherein

the information processing apparatus causes the processing circuitry to further execute:

receiving from the user an input operation for setting a schedule for outputting the article content;

receiving, in response to the set schedule, the input of at least a first word and a second word different from the first word as the first designated words without receiving an input operation from the user; and

outputting the first article content corresponding to the received first designated words, based on the received first word and second word and the trained model.

8. An information processing apparatus comprising a processing circuitry, wherein

the information processing apparatus stores in a storage unit a trained model generated by training using as training data multiple types of words and a result of searching Internet with a search engine using the multiple types of words as a search query, the multiple types of words being selected from a first type of words indicating areas, a second type of words indicating industry types, a third type of words indicating products or services, a fourth type of words describing or modifying areas, a fifth type of words describing or modifying industry types, or a sixth type of words describing or modifying products or services;

the trained model receives, as an input, designated words designated by a user, and thereby outputs an article content, and

the information processing apparatus causes the processing circuitry to execute:

receiving an input of at least a first word and a second word different in type from the first word as first designated words, the first word being one of the first, second, third, fourth, fifth, or sixth types of words; and

outputting a first article content corresponding to the received first designated words, based on the received first word and second word and the trained model,

wherein the trained model is generated by training based on a result in a predetermined search ranking range among results of a search on the Internet based on the search query, wherein the processing circuitry executes to:

search on the Internet with the search engine using the first word and the second word as a search query;

extract, among results of the search, words with high frequency of appearance included in top search articles published on the Internet;

add the extracted words to the received first word and the second word; and

output the first article content, based on the received first word and second word and the added words and the trained model.

9. The apparatus according to claim 8 , wherein

the information processing apparatus further stores in the storage unit a second trained model generated by training using as training data a result of associating an article content with a result of an access by a second user, the second user having accessed the article content to a website managed by the user,

the second trained model receives, as an input, designated words designated by the user, and thereby outputs a prediction result of a number of accesses by the second user who has accessed the article content to the website, and

the information processing apparatus causes the processing circuitry to execute:

receiving an input of at least a third word and a fourth word different from the third word as third designated words; and

outputting, based on the received third word and fourth word, the trained model, and the second trained model, a third article content corresponding to the received third designated words together with a prediction result of a number of accesses by the second user who has accessed the third article content to the website.

10. A method executed by a computer comprising a processor and a memory, wherein

the computer stores in a storage unit a trained model generated by training using as training data multiple types of words and generalized sentences included in an article content included in results of searching Internet with a search engine using the multiple types of words as a search query, the multiple types of words being selected from a first type of words indicating areas, a second type of words indicating industry types, a third type of words indicating products or services, a fourth type of words describing or modifying areas, a fifth type of words describing or modifying industry types, or a sixth type of words describing or modifying products or services;

the trained model receives, as an input, designated words designated by a user, and thereby outputs an article content, the method comprises the following steps executed by the processor: receiving an input of at least a first word and a second word different in type from the first word as first designated words, the first word being one of the first, second, third, fourth, fifth, or sixth types of words; and

outputting a first article content separated from the generalized sentences included in the training data held in a storage unit by a predetermined range with respect to a distance between sentences included or a similarity between words included, based on the received first word and second words and the trained model, wherein the trained model is generated by training based on a result in a predetermined search ranking range among results of a search on the Internet based on the search query.

11. A method executed by a computer comprising a processor and a memory, wherein

the computer stores in a storage unit a trained model generated by training using as training data multiple types of words and a result of searching the Internet with a search engine using the multiple types of words as a search query, the multiple types of words being selected from a first type of words indicating areas, a second type of words indicating industry types, a third type of words indicating products or services, a fourth type of words describing or modifying areas, a fifth type of words describing or modifying industry types, or a sixth type of words describing or modifying products or services;

the trained model receives, as an input, designated words designated by a user, and thereby outputs an article content, the method comprises the following steps executed by the processor:

receiving an input of at least a first word and a second word different in type from the first word as first designated words, the first word being one of the first, second, third, fourth, fifth, or sixth types of words;

searching on the Internet with the search engine using the first word and the second word as a search query;

extracting, among results of the search, words with high frequency of appearance included in top search articles published on the Internet;

adding the extracted words to the received first word and the second word; and outputting the first article content, based on the received first word and second word and the added words and the trained model, wherein the trained model is generated by training based on a result in a predetermined search ranking range among results of a search on the Internet based on the search query.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (14)