JP-7854952-B2 - Information processing device, information processing method, and information processing program

Inventors

• 鍜治 伸裕
• 笹谷 奈翁美

Assignees

• ＬＩＮＥヤフー株式会社

Dates

Publication Date

20260507

Application Date

20230220

Claims (8)

1. When a search query is received that includes multiple keywords pre-set as not to be corrected, an estimation unit estimates the degree of relevance between each keyword, An information processing apparatus comprising: a correction unit that does not correct the search query if the degree of relevance estimated by the estimation unit exceeds a threshold, and corrects the search query if the degree of relevance falls below the threshold.
2. The estimation unit, The information processing apparatus according to claim 1, characterized in that it estimates the degree of relevance between each keyword according to the frequency with which each keyword was used together in previously used search queries.
3. The estimation unit, The information processing apparatus according to claim 1, characterized by estimating the degree of relevance between each keyword according to the frequency of occurrence of each keyword contained in the same content.
4. The correction section is, The information processing apparatus according to claim 1, characterized in that, when correcting the search query, the keyword that is not to be corrected is corrected to another keyword.
5. The estimation unit, The information processing apparatus according to claim 1, characterized in that it estimates the degree of relevance between each of the keywords based on the user context of the user who entered the search query.
6. The information processing apparatus according to claim 1, further comprising a providing unit that provides search results obtained by the search query after correction processing by the correction unit.
7. A method of information processing performed by a computer, When a search query containing multiple keywords pre-configured as non-correction targets is received, the estimation process involves estimating the relevance between each keyword, An information processing method characterized by including a correction step of correcting the search query if the degree of relevance estimated by the estimation step exceeds a threshold, and correcting the search query if the degree of relevance falls below the threshold.
8. When a search query containing multiple keywords pre-configured as non-correction targets is received, an estimation procedure is provided to estimate the relevance between each keyword, An information processing program characterized in that, if the degree of relevance estimated by the estimation procedure exceeds a threshold, the computer is instructed to perform a correction procedure to correct the search query if the degree of relevance falls below the threshold.

Description

This invention relates to an information processing device, an information processing method, and an information processing program. Conventionally, technologies have been provided to correct (convert) keywords entered by users. For example, if a user's search query contains spelling errors, technologies have been provided to correct these errors before providing search results to the user (e.g., Patent Document 1). Patent No. 6529456 Figure 1 shows an example of information processing according to the embodiment.Figure 2 is a block diagram showing an example configuration of an information providing device according to an embodiment.Figure 3 shows an example of a search log storage unit according to the embodiment.Figure 4 is a schematic diagram of the estimation process according to the embodiment.Figure 5 is a flowchart showing an example of the correction process according to this embodiment.Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program relating to this application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program relating to this application. [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. The information processing according to the embodiment is realized by the information processing device 1 shown in Figure 1. The information processing device 1 is a server device that provides various search services. For example, the information processing device 1 uses search queries entered from the user terminal 50 to search for target content, etc., and provides the search results to the user terminal 50. In this process, the information processing device 1 corrects any errors in keywords included in the search query received from the user terminal 50 using a correction model. The correction model is, for example, a machine learning model that uses the keyword to be corrected and its correct equivalent as ground truth data. Here, the correction model may perform overcorrection, correcting keywords that do not actually need correcting. As a countermeasure against overcorrection, the information processing device 1 creates a list L of "uncorrected keywords" containing keywords that should not be corrected, and ensures that keywords on list L are not corrected. On the other hand, in such cases, there are instances where keywords that should be corrected cannot be corrected. Specifically, as shown in Figure 1, when a search query containing multiple keywords such as "Kitami University" is input from the user terminal 50 (step S11), the information processing device 1, because "Kitami" and "University" are both included in list L, may not be corrected, and the search query that should have been corrected to "Kitami University" may not be corrected. Therefore, the information processing device 1 according to this embodiment estimates the degree of relevance between keywords when multiple keywords included in the search query are included in list L (step S12). Here, the degree of relevance is either co-occurrence or mutual information. For example, based on the usage history of the search query, the information processing device 1 estimates that the higher the frequency with which the target keywords are used together, the higher the degree of relevance between the keywords. In other words, the information processing device 1 estimates that the higher the search frequency of "Kitami University," the higher the correlation between "Kitami" and "University." Then, if the estimated correlation exceeds a threshold, the information processing device 1 does not correct the search query. If the estimated correlation is below the threshold, it corrects the search query by inputting it into the correction model (step S13). Subsequently, the information processing device 1 performs a search using the search query that was not subject to correction, or the corrected search query (step S14), and provides the search results to the user terminal 50 (step S15). Thus, the information processing device 1 according to this embodiment pre-creates a list L of keywords to be uncorrected, and when a search query consists of multiple keywords included in list L, it estimates the degree of relevance between the keywords. Furthermore, the information processing device 1 according to this embodiment does not correct the search query if the degree of relevance between the estimated keywords exceed